1
|
Zhang Q, Fotaki A, Ghadimi S, Wang Y, Doneva M, Wetzl J, Delfino JG, O'Regan DP, Prieto C, Epstein FH. Improving the efficiency and accuracy of CMR with AI - review of evidence and proposition of a roadmap to clinical translation. J Cardiovasc Magn Reson 2024:101051. [PMID: 38909656 DOI: 10.1016/j.jocmr.2024.101051] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/17/2024] [Revised: 06/09/2024] [Accepted: 06/18/2024] [Indexed: 06/25/2024] Open
Abstract
Cardiovascular magnetic resonance (CMR) is an important imaging modality for the assessment of heart disease; however, limitations of CMR include long exam times and high complexity compared to other cardiac imaging modalities. Recently advancements in artificial intelligence (AI) technology have shown great potential to address many CMR limitations. While the developments are remarkable, translation of AI-based methods into real-world CMR clinical practice remains at a nascent stage and much work lies ahead to realize the full potential of AI for CMR. Herein we review recent cutting-edge and representative examples demonstrating how AI can advance CMR in areas such as exam planning, accelerated image reconstruction, post-processing, quality control, classification and diagnosis. These advances can be applied to speed up and simplify essentially every application including cine, strain, late gadolinium enhancement, parametric mapping, 3D whole heart, flow, perfusion and others. AI is a unique technology based on training models using data. Beyond reviewing the literature, this paper discusses important AI-specific issues in the context of CMR, including (1) properties and characteristics of datasets for training and validation, (2) previously published guidelines for reporting CMR AI research, (3) considerations around clinical deployment, (4) responsibilities of clinicians and the need for multi-disciplinary teams in the development and deployment of AI in CMR, (5) industry considerations, and (6) regulatory perspectives. Understanding and consideration of all these factors will contribute to the effective and ethical deployment of AI to improve clinical CMR.
Collapse
Affiliation(s)
- Qiang Zhang
- Oxford Centre for Clinical Magnetic Resonance Research, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK; Big Data Institute, University of Oxford, Oxford, UK.
| | - Anastasia Fotaki
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK; Royal Brompton Hospital, Guy's and St Thomas' NHS Foundation Trust, London, UK.
| | - Sona Ghadimi
- Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA.
| | - Yu Wang
- Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA.
| | | | - Jens Wetzl
- Siemens Healthineers AG, Erlangen, Germany.
| | - Jana G Delfino
- US Food and Drug Administration, Center for Devices and Radiological Health (CDRH), Office of Science and Engineering Laboratories (OSEL), Silver Spring, MD, USA.
| | - Declan P O'Regan
- MRC Laboratory of Medical Sciences, Imperial College London, UK.
| | - Claudia Prieto
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK; School of Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile.
| | - Frederick H Epstein
- Department of Biomedical Engineering, University of Virginia, Charlottesville, VA, USA.
| |
Collapse
|
2
|
Wang Y, Sun Z, Liu Z, Lu J, Zhang N. A Motion-Aware DNN Model with Edge Focus Loss and Quality Control for Short-Axis Left Ventricle Segmentation of Cine MR Sequences. JOURNAL OF IMAGING INFORMATICS IN MEDICINE 2024; 37:1-13. [PMID: 38366295 DOI: 10.1007/s10278-023-00942-6] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 07/27/2023] [Revised: 09/27/2023] [Accepted: 09/28/2023] [Indexed: 02/18/2024]
Abstract
Accurate segmentation of the left ventricle myocardium is the key step of automatic assessment of cardiac function. However, the current methods mainly focus on the end-diastolic and the end-systolic frames in cine MR sequences and lack the attention to myocardial motion in the cardiac cycle. Additionally, due to the lack of fine segmentation tools, the simplified approach, excluding papillary muscles and trabeculae from myocardium, is applied in clinical practice. To solve these problems, we propose a motion-aware DNN model with edge focus loss and quality control in this paper. Specifically, the bidirectional ConvLSTM layer and a new motion attention layer are proposed to encode motion-aware feature maps, and an edge focus loss function is proposed to train the model to generate the fine segmentation results. Additionally, a quality control method is proposed to filter out the abnormal segmentations before subsequent analyses. Compared with state-of-the-art segmentation models on the public dataset and the in-house dataset, the proposed method has obtained high segmentation accuracy. On the 17-segment model, the proposed method has obtained the highest Pearson correlation coefficient at 14 of 17 segments, and the mean PCC of 85%. The experimental results highlight the segmentation accuracy of the proposed method as well as its availability to substitute for the manually annotated boundaries for the automatic assessment of cardiac function.
Collapse
Affiliation(s)
- Yu Wang
- School of Biomedical Engineering, Fengtai District, Capital Medical University, 10 Xitoutiao, YouanmenwaiBeijing, 100069, China
- Beijing Key Laboratory of Fundamental Research On Biomechanics in Clinical Application, Fengtai District, Capital Medical University, 10 Xitoutiao, YouanmenwaiBeijing, 100069, China
| | - Zheng Sun
- School of Biomedical Engineering, Fengtai District, Capital Medical University, 10 Xitoutiao, YouanmenwaiBeijing, 100069, China
- Beijing Key Laboratory of Fundamental Research On Biomechanics in Clinical Application, Fengtai District, Capital Medical University, 10 Xitoutiao, YouanmenwaiBeijing, 100069, China
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, 100053, China
| | - Zhi Liu
- Department of Cardiology, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, 100053, China
| | - Jie Lu
- Department of Radiology and Nuclear Medicine, Xuanwu Hospital, Capital Medical University, 45 Changchun Street, Xicheng District, Beijing, 100053, China.
| | - Nan Zhang
- School of Biomedical Engineering, Fengtai District, Capital Medical University, 10 Xitoutiao, YouanmenwaiBeijing, 100069, China.
- Beijing Key Laboratory of Fundamental Research On Biomechanics in Clinical Application, Fengtai District, Capital Medical University, 10 Xitoutiao, YouanmenwaiBeijing, 100069, China.
| |
Collapse
|
3
|
Coraducci F, De Zan G, Fedele D, Costantini P, Guaricci AI, Pavon AG, Teske A, Cramer MJ, Broekhuizen L, Van Osch D, Danad I, Velthuis B, Suchá D, van der Bilt I, Pizzi C, Russo AD, Oerlemans M, van Laake LW, van der Harst P, Guglielmo M. Cardiac magnetic resonance in advanced heart failure. Echocardiography 2024; 41:e15849. [PMID: 38837443 DOI: 10.1111/echo.15849] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/18/2024] [Revised: 05/14/2024] [Accepted: 05/16/2024] [Indexed: 06/07/2024] Open
Abstract
Heart failure (HF) is a chronic and progressive disease that often progresses to an advanced stage where conventional therapy is insufficient to relieve patients' symptoms. Despite the availability of advanced therapies such as mechanical circulatory support or heart transplantation, the complexity of defining advanced HF, which requires multiple parameters and multimodality assessment, often leads to delays in referral to dedicated specialists with the result of a worsening prognosis. In this review, we aim to explore the role of cardiac magnetic resonance (CMR) in advanced HF by showing how CMR is useful at every step in managing these patients: from diagnosis to prognostic stratification, hemodynamic evaluation, follow-up and advanced therapies such as heart transplantation. The technical challenges of scanning advanced HF patients, which often require troubleshooting of intracardiac devices and dedicated scans, will be also discussed.
Collapse
Affiliation(s)
| | - Giulia De Zan
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
| | - Damiano Fedele
- Cardiology Unit, Cardiac Thoracic and Vascular Department, IRCCS Azienda, Ospedaliero-Universitaria di Bologna, Bologna, Italy
- Department of Medical and Surgical Sciences - DIMEC, University of Bologna, Bologna, Italy
| | - Pietro Costantini
- Department of Radiology, Ospedale Universitario Maggiore della Carità di Novara, University of Eastern Piedmont, Novara, Italy
| | - Andrea Igoren Guaricci
- Department of Emergency and Organ Transplantation, Institute of Cardiovascular Disease, University Hospital Policlinico of Bari, Bari, Italy
| | - Anna Giulia Pavon
- Division of Cardiology, Cardiocentro Ticino Institute Ente Ospedaliero Cantonale, Lugano, Switzerland
| | - Arco Teske
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
| | - Maarten Jan Cramer
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
| | - Lysette Broekhuizen
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
| | - Dirk Van Osch
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
| | - Ibrahim Danad
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
| | - Birgitta Velthuis
- Division of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Dominika Suchá
- Division of Radiology, University Medical Center Utrecht, Utrecht, The Netherlands
| | - Ivo van der Bilt
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
- Cardiology Department, HAGA Ziekenhuis, Den Haag, The Netherlands
| | - Carmine Pizzi
- Cardiology Unit, Cardiac Thoracic and Vascular Department, IRCCS Azienda, Ospedaliero-Universitaria di Bologna, Bologna, Italy
- Department of Medical and Surgical Sciences - DIMEC, University of Bologna, Bologna, Italy
| | | | - Marish Oerlemans
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
| | - Linda W van Laake
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
| | - Pim van der Harst
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
| | - Marco Guglielmo
- Division Heart and Lung, Cardiology Department, University Medical Centre Utrecht, Utrecht, The Netherlands
- Cardiology Department, HAGA Ziekenhuis, Den Haag, The Netherlands
| |
Collapse
|
4
|
Onnis C, van Assen M, Muscogiuri E, Muscogiuri G, Gershon G, Saba L, De Cecco CN. The Role of Artificial Intelligence in Cardiac Imaging. Radiol Clin North Am 2024; 62:473-488. [PMID: 38553181 DOI: 10.1016/j.rcl.2024.01.002] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 04/02/2024]
Abstract
Artificial intelligence (AI) is having a significant impact in medical imaging, advancing almost every aspect of the field, from image acquisition and postprocessing to automated image analysis with outreach toward supporting decision making. Noninvasive cardiac imaging is one of the main and most exciting fields for AI development. The aim of this review is to describe the main applications of AI in cardiac imaging, including CT and MR imaging, and provide an overview of recent advancements and available clinical applications that can improve clinical workflow, disease detection, and prognostication in cardiac disease.
Collapse
Affiliation(s)
- Carlotta Onnis
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA; Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari-Polo di Monserrato, SS 554 km 4,500 Monserrato, Cagliari 09042, Italy. https://twitter.com/CarlottaOnnis
| | - Marly van Assen
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA. https://twitter.com/marly_van_assen
| | - Emanuele Muscogiuri
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA; Division of Thoracic Imaging, Department of Radiology, University Hospitals Leuven, Herestraat 49, Leuven 3000, Belgium
| | - Giuseppe Muscogiuri
- Department of Diagnostic and Interventional Radiology, Papa Giovanni XXIII Hospital, Piazza OMS, 1, Bergamo BG 24127, Italy. https://twitter.com/GiuseppeMuscog
| | - Gabrielle Gershon
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA. https://twitter.com/gabbygershon
| | - Luca Saba
- Department of Radiology, Azienda Ospedaliero Universitaria (A.O.U.), di Cagliari-Polo di Monserrato, SS 554 km 4,500 Monserrato, Cagliari 09042, Italy. https://twitter.com/lucasabaITA
| | - Carlo N De Cecco
- Translational Laboratory for Cardiothoracic Imaging and Artificial Intelligence, Department of Radiology and Imaging Sciences, Emory University, 100 Woodruff Circle, Atlanta, GA 30322, USA; Division of Cardiothoracic Imaging, Department of Radiology and Imaging Sciences, Emory University, Emory University Hospital, 1365 Clifton Road Northeast, Suite AT503, Atlanta, GA 30322, USA.
| |
Collapse
|
5
|
Corral Acero J, Lamata P, Eitel I, Zacur E, Evertz R, Lange T, Backhaus SJ, Stiermaier T, Thiele H, Bueno-Orovio A, Schuster A, Grau V. Comprehensive characterization of cardiac contraction for improved post-infarction risk assessment. Sci Rep 2024; 14:8951. [PMID: 38637609 PMCID: PMC11026383 DOI: 10.1038/s41598-024-59114-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/30/2023] [Accepted: 04/08/2024] [Indexed: 04/20/2024] Open
Abstract
This study aims at identifying risk-related patterns of left ventricular contraction dynamics via novel volume transient characterization. A multicenter cohort of AMI survivors (n = 1021) who underwent Cardiac Magnetic Resonance (CMR) after infarction was considered for the study. The clinical endpoint was the 12-month rate of major adverse cardiac events (MACE, n = 73), consisting of all-cause death, reinfarction, and new congestive heart failure. Cardiac function was characterized from CMR in 3 potential directions: by (1) volume temporal transients (i.e. contraction dynamics); (2) feature tracking strain analysis (i.e. bulk tissue peak contraction); and (3) 3D shape analysis (i.e. 3D contraction morphology). A fully automated pipeline was developed to extract conventional and novel artificial-intelligence-derived metrics of cardiac contraction, and their relationship with MACE was investigated. Any of the 3 proposed directions demonstrated its additional prognostic value on top of established CMR indexes, myocardial injury markers, basic characteristics, and cardiovascular risk factors (P < 0.001). The combination of these 3 directions of enhancement towards a final CMR risk model improved MACE prediction by 13% compared to clinical baseline (0.774 (0.771-0.777) vs. 0.683 (0.681-0.685) cross-validated AUC, P < 0.001). The study evidences the contribution of the novel contraction characterization, enabled by a fully automated pipeline, to post-infarction assessment.
Collapse
Affiliation(s)
- Jorge Corral Acero
- Department of Engineering Science, Institute of Biomedical Engineering, University of Oxford, Oxford, UK.
| | - Pablo Lamata
- Department of Digital Twins for Healthcare, School of Biomedical Engineering and Imaging Sciences, King's College London, 4th Floor North Wing, St Thomas' Hospital, London, SE1 7EH, UK.
| | - Ingo Eitel
- Medical Clinic II, Cardiology, Angiology and Intensive Care Medicine, University Heart Centre Lübeck, Lübeck, Germany
- University Hospital Schleswig-Holstein, Lübeck, Germany
- German Centre for Cardiovascular Research (DZHK), Partner Site Hamburg/Kiel/Lübeck, Lübeck, Germany
| | - Ernesto Zacur
- Department of Engineering Science, Institute of Biomedical Engineering, University of Oxford, Oxford, UK
| | - Ruben Evertz
- Department of Cardiology and Pneumology, University Medical Centre Göttingen, Georg-August University, Göttingen, Germany
- German Centre for Cardiovascular Research (DZHK), Partner Site Lower Saxony, Göttingen, Germany
| | - Torben Lange
- Department of Cardiology and Pneumology, University Medical Centre Göttingen, Georg-August University, Göttingen, Germany
- German Centre for Cardiovascular Research (DZHK), Partner Site Lower Saxony, Göttingen, Germany
| | - Sören J Backhaus
- Department of Cardiology, Campus Kerckhoff of the Justus-Liebig-University Giessen, Kerckhoff-Clinic, Bad Nauheim, Germany
- German Center for Cardiovascular Research (DZHK), Partner Site Rhine-Main, Bad Nauheim, Germany
| | - Thomas Stiermaier
- Medical Clinic II, Cardiology, Angiology and Intensive Care Medicine, University Heart Centre Lübeck, Lübeck, Germany
- University Hospital Schleswig-Holstein, Lübeck, Germany
- German Centre for Cardiovascular Research (DZHK), Partner Site Hamburg/Kiel/Lübeck, Lübeck, Germany
| | - Holger Thiele
- Department of Internal Medicine/Cardiology and Leipzig Heart Science, Heart Centre Leipzig at University of Leipzig, Leipzig, Germany
| | | | - Andreas Schuster
- Department of Cardiology and Pneumology, University Medical Centre Göttingen, Georg-August University, Göttingen, Germany
- German Centre for Cardiovascular Research (DZHK), Partner Site Lower Saxony, Göttingen, Germany
| | - Vicente Grau
- Department of Engineering Science, Institute of Biomedical Engineering, University of Oxford, Oxford, UK
| |
Collapse
|
6
|
Zaman S, Vimalesvaran K, Chappell D, Varela M, Peters NS, Shiwani H, Knott KD, Davies RH, Moon JC, Bharath AA, Linton NW, Francis DP, Cole GD, Howard JP. Quality assurance of late gadolinium enhancement cardiac magnetic resonance images: a deep learning classifier for confidence in the presence or absence of abnormality with potential to prompt real-time image optimization. J Cardiovasc Magn Reson 2024; 26:101040. [PMID: 38522522 PMCID: PMC11129090 DOI: 10.1016/j.jocmr.2024.101040] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 12/06/2023] [Revised: 03/10/2024] [Accepted: 03/19/2024] [Indexed: 03/26/2024] Open
Abstract
BACKGROUND Late gadolinium enhancement (LGE) of the myocardium has significant diagnostic and prognostic implications, with even small areas of enhancement being important. Distinguishing between definitely normal and definitely abnormal LGE images is usually straightforward, but diagnostic uncertainty arises when reporters are not sure whether the observed LGE is genuine or not. This uncertainty might be resolved by repetition (to remove artifact) or further acquisition of intersecting images, but this must take place before the scan finishes. Real-time quality assurance by humans is a complex task requiring training and experience, so being able to identify which images have an intermediate likelihood of LGE while the scan is ongoing, without the presence of an expert is of high value. This decision-support could prompt immediate image optimization or acquisition of supplementary images to confirm or refute the presence of genuine LGE. This could reduce ambiguity in reports. METHODS Short-axis, phase-sensitive inversion recovery late gadolinium images were extracted from our clinical cardiac magnetic resonance (CMR) database and shuffled. Two, independent, blinded experts scored each individual slice for "LGE likelihood" on a visual analog scale, from 0 (absolute certainty of no LGE) to 100 (absolute certainty of LGE), with 50 representing clinical equipoise. The scored images were split into two classes-either "high certainty" of whether LGE was present or not, or "low certainty." The dataset was split into training, validation, and test sets (70:15:15). A deep learning binary classifier based on the EfficientNetV2 convolutional neural network architecture was trained to distinguish between these categories. Classifier performance on the test set was evaluated by calculating the accuracy, precision, recall, F1-score, and area under the receiver operating characteristics curve (ROC AUC). Performance was also evaluated on an external test set of images from a different center. RESULTS One thousand six hundred and forty-five images (from 272 patients) were labeled and split at the patient level into training (1151 images), validation (247 images), and test (247 images) sets for the deep learning binary classifier. Of these, 1208 images were "high certainty" (255 for LGE, 953 for no LGE), and 437 were "low certainty". An external test comprising 247 images from 41 patients from another center was also employed. After 100 epochs, the performance on the internal test set was accuracy = 0.94, recall = 0.80, precision = 0.97, F1-score = 0.87, and ROC AUC = 0.94. The classifier also performed robustly on the external test set (accuracy = 0.91, recall = 0.73, precision = 0.93, F1-score = 0.82, and ROC AUC = 0.91). These results were benchmarked against a reference inter-expert accuracy of 0.86. CONCLUSION Deep learning shows potential to automate quality control of late gadolinium imaging in CMR. The ability to identify short-axis images with intermediate LGE likelihood in real-time may serve as a useful decision-support tool. This approach has the potential to guide immediate further imaging while the patient is still in the scanner, thereby reducing the frequency of recalls and inconclusive reports due to diagnostic indecision.
Collapse
Affiliation(s)
- Sameer Zaman
- National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK; Imperial College Healthcare NHS Trust, London W12 0HS, UK; AI for Healthcare Centre for Doctoral Training, Imperial College London, London SW7 2AZ, UK
| | - Kavitha Vimalesvaran
- National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK; AI for Healthcare Centre for Doctoral Training, Imperial College London, London SW7 2AZ, UK
| | - Digby Chappell
- AI for Healthcare Centre for Doctoral Training, Imperial College London, London SW7 2AZ, UK
| | - Marta Varela
- National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK
| | - Nicholas S Peters
- National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK; Imperial College Healthcare NHS Trust, London W12 0HS, UK
| | - Hunain Shiwani
- Institute of Cardiovascular Science, University College London, London WC1E 6DD, UK; Barts Health Centre, St. Bartholomew's Hospital, London EC1A 7BE, UK
| | - Kristopher D Knott
- Institute of Cardiovascular Science, University College London, London WC1E 6DD, UK; St. George's University Hospitals NHS Foundation Trust, London SW17 0QT, UK
| | - Rhodri H Davies
- Institute of Cardiovascular Science, University College London, London WC1E 6DD, UK; Barts Health Centre, St. Bartholomew's Hospital, London EC1A 7BE, UK
| | - James C Moon
- Institute of Cardiovascular Science, University College London, London WC1E 6DD, UK; Barts Health Centre, St. Bartholomew's Hospital, London EC1A 7BE, UK
| | - Anil A Bharath
- Department of Bioengineering, Imperial College London, London SW7 2AZ, UK
| | - Nick Wf Linton
- Imperial College Healthcare NHS Trust, London W12 0HS, UK; Department of Bioengineering, Imperial College London, London SW7 2AZ, UK.
| | - Darrel P Francis
- National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK; Imperial College Healthcare NHS Trust, London W12 0HS, UK
| | - Graham D Cole
- National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK; Imperial College Healthcare NHS Trust, London W12 0HS, UK
| | - James P Howard
- National Heart and Lung Institute, Imperial College London, London SW7 2AZ, UK; Imperial College Healthcare NHS Trust, London W12 0HS, UK
| |
Collapse
|
7
|
Machado I, Puyol-Anton E, Hammernik K, Cruz G, Ugurlu D, Olakorede I, Oksuz I, Ruijsink B, Castelo-Branco M, Young A, Prieto C, Schnabel J, King A. A Deep Learning-Based Integrated Framework for Quality-Aware Undersampled Cine Cardiac MRI Reconstruction and Analysis. IEEE Trans Biomed Eng 2024; 71:855-865. [PMID: 37782583 DOI: 10.1109/tbme.2023.3321431] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 10/04/2023]
Abstract
Cine cardiac magnetic resonance (CMR) imaging is considered the gold standard for cardiac function evaluation. However, cine CMR acquisition is inherently slow and in recent decades considerable effort has been put into accelerating scan times without compromising image quality or the accuracy of derived results. In this article, we present a fully-automated, quality-controlled integrated framework for reconstruction, segmentation and downstream analysis of undersampled cine CMR data. The framework produces high quality reconstructions and segmentations, leading to undersampling factors that are optimised on a scan-by-scan basis. This results in reduced scan times and automated analysis, enabling robust and accurate estimation of functional biomarkers. To demonstrate the feasibility of the proposed approach, we perform simulations of radial k-space acquisitions using in-vivo cine CMR data from 270 subjects from the UK Biobank (with synthetic phase) and in-vivo cine CMR data from 16 healthy subjects (with real phase). The results demonstrate that the optimal undersampling factor varies for different subjects by approximately 1 to 2 seconds per slice. We show that our method can produce quality-controlled images in a mean scan time reduced from 12 to 4 seconds per slice, and that image quality is sufficient to allow clinically relevant parameters to be automatically estimated to lie within 5% mean absolute difference.
Collapse
|
8
|
Schilling M, Unterberg-Buchwald C, Lotz J, Uecker M. Assessment of deep learning segmentation for real-time free-breathing cardiac magnetic resonance imaging at rest and under exercise stress. Sci Rep 2024; 14:3754. [PMID: 38355969 PMCID: PMC10866998 DOI: 10.1038/s41598-024-54164-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/29/2023] [Accepted: 02/09/2024] [Indexed: 02/16/2024] Open
Abstract
In recent years, a variety of deep learning networks for cardiac MRI (CMR) segmentation have been developed and analyzed. However, nearly all of them are focused on cine CMR under breathold. In this work, accuracy of deep learning methods is assessed for volumetric analysis (via segmentation) of the left ventricle in real-time free-breathing CMR at rest and under exercise stress. Data from healthy volunteers (n = 15) for cine and real-time free-breathing CMR at rest and under exercise stress were analyzed retrospectively. Exercise stress was performed using an ergometer in the supine position. Segmentations of two deep learning methods, a commercially available technique (comDL) and an openly available network (nnU-Net), were compared to a reference model created via the manual correction of segmentations obtained with comDL. Segmentations of left ventricular endocardium (LV), left ventricular myocardium (MYO), and right ventricle (RV) are compared for both end-systolic and end-diastolic phases and analyzed with Dice's coefficient. The volumetric analysis includes the cardiac function parameters LV end-diastolic volume (EDV), LV end-systolic volume (ESV), and LV ejection fraction (EF), evaluated with respect to both absolute and relative differences. For cine CMR, nnU-Net and comDL achieve Dice's coefficients above 0.95 for LV and 0.9 for MYO, and RV. For real-time CMR, the accuracy of nnU-Net exceeds that of comDL overall. For real-time CMR at rest, nnU-Net achieves Dice's coefficients of 0.94 for LV, 0.89 for MYO, and 0.90 for RV and the mean absolute differences between nnU-Net and the reference are 2.9 mL for EDV, 3.5 mL for ESV, and 2.6% for EF. For real-time CMR under exercise stress, nnU-Net achieves Dice's coefficients of 0.92 for LV, 0.85 for MYO, and 0.83 for RV and the mean absolute differences between nnU-Net and reference are 11.4 mL for EDV, 2.9 mL for ESV, and 3.6% for EF. Deep learning methods designed or trained for cine CMR segmentation can perform well on real-time CMR. For real-time free-breathing CMR at rest, the performance of deep learning methods is comparable to inter-observer variability in cine CMR and is usable for fully automatic segmentation. For real-time CMR under exercise stress, the performance of nnU-Net could promise a higher degree of automation in the future.
Collapse
Affiliation(s)
- Martin Schilling
- Institute for Diagnostic and Interventional Radiology, Universitätsmedizin Göttingen, Göttingen, Germany
| | - Christina Unterberg-Buchwald
- Institute for Diagnostic and Interventional Radiology, Universitätsmedizin Göttingen, Göttingen, Germany
- German Centre for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, Germany
- Clinic of Cardiology and Pneumology, Universitätsmedizin Göttingen, Göttingen, Germany
| | - Joachim Lotz
- Institute for Diagnostic and Interventional Radiology, Universitätsmedizin Göttingen, Göttingen, Germany
| | - Martin Uecker
- Institute for Diagnostic and Interventional Radiology, Universitätsmedizin Göttingen, Göttingen, Germany.
- German Centre for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, Germany.
- Institute of Biomedical Imaging, Graz University of Technology, Graz, Austria.
| |
Collapse
|
9
|
Priya S, Dhruba DD, Perry SS, Aher PY, Gupta A, Nagpal P, Jacob M. Optimizing Deep Learning for Cardiac MRI Segmentation: The Impact of Automated Slice Range Classification. Acad Radiol 2024; 31:503-513. [PMID: 37541826 DOI: 10.1016/j.acra.2023.07.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/10/2023] [Revised: 07/07/2023] [Accepted: 07/09/2023] [Indexed: 08/06/2023]
Abstract
RATIONALE AND OBJECTIVES Cardiac magnetic resonance imaging is crucial for diagnosing cardiovascular diseases, but lengthy postprocessing and manual segmentation can lead to observer bias. Deep learning (DL) has been proposed for automated cardiac segmentation; however, its effectiveness is limited by the slice range selection from base to apex. MATERIALS AND METHODS In this study, we integrated an automated slice range classification step to identify basal to apical short-axis slices before DL-based segmentation. We employed publicly available Multi-Disease, Multi-View & Multi-Center Right Ventricular Segmentation in Cardiac MRI data set with short-axis cine data from 160 training, 40 validation, and 160 testing cases. Three classification and seven segmentation DL models were studied. The top-performing segmentation model was assessed with and without the classification model. Model validation to compare automated and manual segmentation was performed using Dice score and Hausdorff distance and clinical indices (correlation score and Bland-Altman plots). RESULTS The combined classification (CBAM-integrated 2D-CNN) and segmentation model (2D-UNet with dilated convolution block) demonstrated superior performance, achieving Dice scores of 0.952 for left ventricle (LV), 0.933 for right ventricle (RV), and 0.875 for myocardium, compared to the stand-alone segmentation model (0.949 for LV, 0.925 for RV, and 0.867 for myocardium). Combined classification and segmentation model showed high correlation (0.92-0.99) with manual segmentation for biventricular volumes, ejection fraction, and myocardial mass. The mean absolute difference (2.8-8.3 mL) for clinical parameters between automated and manual segmentation was within the interobserver variability range, indicating comparable performance to manual annotation. CONCLUSION Integrating an initial automated slice range classification step into the segmentation process improves the performance of DL-based cardiac chamber segmentation.
Collapse
Affiliation(s)
- Sarv Priya
- Department of Radiology, University of Iowa Carver College of Medicine, Iowa City, Iowa (S.P.).
| | - Durjoy D Dhruba
- Department of Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa (D.D.D., M.J.)
| | - Sarah S Perry
- Department of Biostatistics, University of Iowa, Iowa City, Iowa (S.S.P.)
| | - Pritish Y Aher
- Department of Radiology, University of Miami, Miller School of Medicine, Miami, Florida (P.Y.A.)
| | - Amit Gupta
- Department of Radiology, University Hospital Cleveland Medical Center, Cleveland, Ohio (A.G.)
| | - Prashant Nagpal
- Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, Wisconsin (P.N.)
| | - Mathews Jacob
- Department of Electrical and Computer Engineering, University of Iowa, Iowa City, Iowa (D.D.D., M.J.)
| |
Collapse
|
10
|
Gröschel J, Kuhnt J, Viezzer D, Hadler T, Hormes S, Barckow P, Schulz-Menger J, Blaszczyk E. Comparison of manual and artificial intelligence based quantification of myocardial strain by feature tracking-a cardiovascular MR study in health and disease. Eur Radiol 2024; 34:1003-1015. [PMID: 37594523 PMCID: PMC10853310 DOI: 10.1007/s00330-023-10127-y] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/28/2023] [Revised: 06/27/2023] [Accepted: 07/04/2023] [Indexed: 08/19/2023]
Abstract
OBJECTIVES The analysis of myocardial deformation using feature tracking in cardiovascular MR allows for the assessment of global and segmental strain values. The aim of this study was to compare strain values derived from artificial intelligence (AI)-based contours with manually derived strain values in healthy volunteers and patients with cardiac pathologies. MATERIALS AND METHODS A cohort of 136 subjects (60 healthy volunteers and 76 patients; of those including 46 cases with left ventricular hypertrophy (LVH) of varying etiology and 30 cases with chronic myocardial infarction) was analyzed. Comparisons were based on quantitative strain analysis and on a geometric level by the Dice similarity coefficient (DSC) of the segmentations. Strain quantification was performed in 3 long-axis slices and short-axis (SAX) stack with epi- and endocardial contours in end-diastole. AI contours were checked for plausibility and potential errors in the tracking algorithm. RESULTS AI-derived strain values overestimated radial strain (+ 1.8 ± 1.7% (mean difference ± standard deviation); p = 0.03) and underestimated circumferential (- 0.8 ± 0.8%; p = 0.02) and longitudinal strain (- 0.1 ± 0.8%; p = 0.54). Pairwise group comparisons revealed no significant differences for global strain. The DSC showed good agreement for healthy volunteers (85.3 ± 10.3% for SAX) and patients (80.8 ± 9.6% for SAX). In 27 cases (27/76; 35.5%), a tracking error was found, predominantly (24/27; 88.9%) in the LVH group and 22 of those (22/27; 81.5%) at the insertion of the papillary muscle in lateral segments. CONCLUSIONS Strain analysis based on AI-segmented images shows good results in healthy volunteers and in most of the patient groups. Hypertrophied ventricles remain a challenge for contouring and feature tracking. CLINICAL RELEVANCE STATEMENT AI-based segmentations can help to streamline and standardize strain analysis by feature tracking. KEY POINTS • Assessment of strain in cardiovascular magnetic resonance by feature tracking can generate global and segmental strain values. • Commercially available artificial intelligence algorithms provide segmentation for strain analysis comparable to manual segmentation. • Hypertrophied ventricles are challenging in regards of strain analysis by feature tracking.
Collapse
Affiliation(s)
- Jan Gröschel
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Zu Berlin, Berlin, Germany.
- Working Group On Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, a joint cooperation between the Charité Medical Faculty and the Max-Delbrück Center for Molecular Medicine and HELIOS Hospital Berlin-Buch, Department of Cardiology and Nephrology, Berlin, Germany.
- DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany.
| | - Johanna Kuhnt
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Zu Berlin, Berlin, Germany
- Working Group On Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, a joint cooperation between the Charité Medical Faculty and the Max-Delbrück Center for Molecular Medicine and HELIOS Hospital Berlin-Buch, Department of Cardiology and Nephrology, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany
| | - Darian Viezzer
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Zu Berlin, Berlin, Germany
- Working Group On Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, a joint cooperation between the Charité Medical Faculty and the Max-Delbrück Center for Molecular Medicine and HELIOS Hospital Berlin-Buch, Department of Cardiology and Nephrology, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany
| | - Thomas Hadler
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Zu Berlin, Berlin, Germany
- Working Group On Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, a joint cooperation between the Charité Medical Faculty and the Max-Delbrück Center for Molecular Medicine and HELIOS Hospital Berlin-Buch, Department of Cardiology and Nephrology, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany
| | - Sophie Hormes
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Zu Berlin, Berlin, Germany
- Working Group On Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, a joint cooperation between the Charité Medical Faculty and the Max-Delbrück Center for Molecular Medicine and HELIOS Hospital Berlin-Buch, Department of Cardiology and Nephrology, Berlin, Germany
| | | | - Jeanette Schulz-Menger
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Zu Berlin, Berlin, Germany
- Working Group On Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, a joint cooperation between the Charité Medical Faculty and the Max-Delbrück Center for Molecular Medicine and HELIOS Hospital Berlin-Buch, Department of Cardiology and Nephrology, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany
| | - Edyta Blaszczyk
- Charité - Universitätsmedizin Berlin, corporate member of Freie Universität Berlin and Humboldt-Universität Zu Berlin, Berlin, Germany.
- Working Group On Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, a joint cooperation between the Charité Medical Faculty and the Max-Delbrück Center for Molecular Medicine and HELIOS Hospital Berlin-Buch, Department of Cardiology and Nephrology, Berlin, Germany.
- DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany.
| |
Collapse
|
11
|
Korosoglou G, Sagris M, André F, Steen H, Montenbruck M, Frey N, Kelle S. Systematic review and meta-analysis for the value of cardiac magnetic resonance strain to predict cardiac outcomes. Sci Rep 2024; 14:1094. [PMID: 38212323 PMCID: PMC10784294 DOI: 10.1038/s41598-023-50835-5] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/02/2023] [Accepted: 12/26/2023] [Indexed: 01/13/2024] Open
Abstract
Cardiac magnetic resonance (CMR) is the gold standard for the diagnostic classification and risk stratification in most patients with cardiac disorders. The aim of the present study was to investigate the ability of Strain-encoded MR (SENC) for the prediction of major adverse cardiovascular events (MACE). A systematic review and meta-analysis was performed according to the PRISMA Guidelines, including patients with or without cardiovascular disease and asymptomatic individuals. Myocardial strain by HARP were used as pulse sequences in 1.5 T scanners. Published literature in MEDLINE (PubMed) and Cochrane's databases were explored before February 2023 for studies assessing the clinical utility of myocardial strain by Harmonic Phase Magnetic Resonance Imaging (HARP), Strain-encoded MR (SENC) or fast-SENC. In total, 8 clinical trials (4 studies conducted in asymptomatic individuals and 4 in patients with suspected or known cardiac disease) were included in this systematic review, while 3 studies were used for our meta-analysis, based on individual patient level data. Kaplan-Meier analysis and Cox proportional hazard models were used, testing the ability of myocardial strain by HARP and SENC/fast-SENC for the prediction of MACE. Strain enabled risk stratification in asymptomatic individuals, predicting MACE and the development of incident heart failure. Of 1332 patients who underwent clinically indicated CMR, including SENC or fast-SENC acquisitions, 19 patients died, 28 experienced non-fatal infarctions, 52 underwent coronary revascularization and 86 were hospitalized due to heart failure during median 22.4 (17.2-28.5) months of follow-up. SENC/fast-SENC, predicted both all-cause mortality and MACE with high accuracy (HR = 3.0, 95% CI = 1.2-7.6, p = 0.02 and HR = 4.1, 95% CI = 3.0-5.5, respectively, p < 0.001). Using hierarchical Cox-proportional hazard regression models, SENC/fast-SENC exhibited incremental value to clinical data and conventional CMR parameters. Reduced myocardial strain predicts of all-cause mortality and cardiac outcomes in symptomatic patients with a wide range of ischemic or non-ischemic cardiac diseases, whereas in asymptomatic individuals, reduced strain was a precursor of incident heart failure.
Collapse
Affiliation(s)
- Grigorios Korosoglou
- Departments of Cardiology, Vascular Medicine and Pneumology, GRN Academic Teaching Hospital Weinheim, Roentgenstrasse 1, 69469, Weinheim, Germany.
- Cardiac Imaging Center Weinheim, Hector Foundations, Weinheim, Germany.
| | - Marios Sagris
- Hippokration General Hospital, National and Kapodistrian University of Athens, School of Medicine, Athens, Greece
| | - Florian André
- Departments of Cardiology, Angiology and Pneumology, Heidelberg University, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim, Heidelberg, Germany
| | - Henning Steen
- Departments of Cardiology, Angiology and Pneumology, Heidelberg University, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim, Heidelberg, Germany
| | | | - Norbert Frey
- Departments of Cardiology, Angiology and Pneumology, Heidelberg University, Heidelberg, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Heidelberg/Mannheim, Heidelberg, Germany
| | - Sebastian Kelle
- Department of Cardiology, Angiology and Intensive Care Medicine, Deutsches Herzzentrum der Charité, Berlin, Germany
- DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany
| |
Collapse
|
12
|
Li Y, Chan E, Puyol-Antón E, Ruijsink B, Cecelja M, King AP, Razavi R, Chowienczyk P. Hemodynamic Determinants of Elevated Blood Pressure and Hypertension in the Middle to Older-Age UK Population: A UK Biobank Imaging Study. Hypertension 2023; 80:2473-2484. [PMID: 37675583 PMCID: PMC10876164 DOI: 10.1161/hypertensionaha.122.20969] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/23/2023] [Accepted: 08/01/2023] [Indexed: 09/08/2023]
Abstract
BACKGROUND Increased systemic vascular resistance and, in older people, reduced aortic distensibility, are thought to be the hemodynamic determinants of primary hypertension but cardiac output could also be important. We examined the hemodynamics of elevated blood pressure and hypertension in the middle to older-aged UK population participating in the UK Biobank imaging studies. METHODS Cardiac output, systemic vascular resistance, and aortic distensibility were measured from cardiac magnetic resonance imaging in 31 112 (distensibility in 21 178) participants (46.3% male, mean age±SD 63±7 years). Body composition including visceral adipose tissue volume and abdominal subcutaneous adipose tissue volume were measured in 19 645 participants. RESULTS Participants with higher blood pressure had higher cardiac output (higher by 17.9±26.6% in hypertensive compared with those with optimal blood pressure) and higher systemic vascular resistance (higher by 11.4±27.9% in hypertensive compared with those with optimal blood pressure). These differences were little changed after adjustment for body size and adiposity. The contribution of cardiac output relative to systemic vascular resistance was more marked in younger compared with older subjects. Aortic distensibility decreased with age and was lower in participants with higher compared with lower blood pressure but with a greater difference in younger compared with older subjects. CONCLUSIONS In the middle to older-aged UK population, cardiac output plays an important role in contributing to elevated mean arterial blood pressure, particularly in younger compared with older subjects. Reduced aortic distensibility contributes to a rise in pulse pressure and systolic blood pressure at all ages.
Collapse
Affiliation(s)
- Ye Li
- Department of Clinical Pharmacology, King’s College London British Heart Foundation Centre, St. Thomas’ Hospital, United Kingdom (Y.L., M.C., P.C.)
| | - Emily Chan
- School of Bioengineering and Imaging Science, King’s College London, United Kingdom (E.C., E.P.-A., B.R., A.P.K., R.R.)
| | - Esther Puyol-Antón
- School of Bioengineering and Imaging Science, King’s College London, United Kingdom (E.C., E.P.-A., B.R., A.P.K., R.R.)
| | - Bram Ruijsink
- School of Bioengineering and Imaging Science, King’s College London, United Kingdom (E.C., E.P.-A., B.R., A.P.K., R.R.)
| | - Marina Cecelja
- Department of Clinical Pharmacology, King’s College London British Heart Foundation Centre, St. Thomas’ Hospital, United Kingdom (Y.L., M.C., P.C.)
| | - Andrew P. King
- School of Bioengineering and Imaging Science, King’s College London, United Kingdom (E.C., E.P.-A., B.R., A.P.K., R.R.)
| | - Reza Razavi
- School of Bioengineering and Imaging Science, King’s College London, United Kingdom (E.C., E.P.-A., B.R., A.P.K., R.R.)
| | - Phil Chowienczyk
- Department of Clinical Pharmacology, King’s College London British Heart Foundation Centre, St. Thomas’ Hospital, United Kingdom (Y.L., M.C., P.C.)
| |
Collapse
|
13
|
Mariscal-Harana J, Asher C, Vergani V, Rizvi M, Keehn L, Kim RJ, Judd RM, Petersen SE, Razavi R, King AP, Ruijsink B, Puyol-Antón E. An artificial intelligence tool for automated analysis of large-scale unstructured clinical cine cardiac magnetic resonance databases. EUROPEAN HEART JOURNAL. DIGITAL HEALTH 2023; 4:370-383. [PMID: 37794871 PMCID: PMC10545512 DOI: 10.1093/ehjdh/ztad044] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 04/13/2023] [Revised: 06/05/2023] [Accepted: 07/12/2023] [Indexed: 10/06/2023]
Abstract
Aims Artificial intelligence (AI) techniques have been proposed for automating analysis of short-axis (SAX) cine cardiac magnetic resonance (CMR), but no CMR analysis tool exists to automatically analyse large (unstructured) clinical CMR datasets. We develop and validate a robust AI tool for start-to-end automatic quantification of cardiac function from SAX cine CMR in large clinical databases. Methods and results Our pipeline for processing and analysing CMR databases includes automated steps to identify the correct data, robust image pre-processing, an AI algorithm for biventricular segmentation of SAX CMR and estimation of functional biomarkers, and automated post-analysis quality control to detect and correct errors. The segmentation algorithm was trained on 2793 CMR scans from two NHS hospitals and validated on additional cases from this dataset (n = 414) and five external datasets (n = 6888), including scans of patients with a range of diseases acquired at 12 different centres using CMR scanners from all major vendors. Median absolute errors in cardiac biomarkers were within the range of inter-observer variability: <8.4 mL (left ventricle volume), <9.2 mL (right ventricle volume), <13.3 g (left ventricular mass), and <5.9% (ejection fraction) across all datasets. Stratification of cases according to phenotypes of cardiac disease and scanner vendors showed good performance across all groups. Conclusion We show that our proposed tool, which combines image pre-processing steps, a domain-generalizable AI algorithm trained on a large-scale multi-domain CMR dataset and quality control steps, allows robust analysis of (clinical or research) databases from multiple centres, vendors, and cardiac diseases. This enables translation of our tool for use in fully automated processing of large multi-centre databases.
Collapse
Affiliation(s)
- Jorge Mariscal-Harana
- School of Biomedical Engineering & Imaging Sciences Rayne Institute, 4th Floor, Lambeth Wing St. Thomas' Hospital Westminster Bridge Road London SE1 7EH
| | - Clint Asher
- School of Biomedical Engineering & Imaging Sciences Rayne Institute, 4th Floor, Lambeth Wing St. Thomas' Hospital Westminster Bridge Road London SE1 7EH
- Department of Adult and Paediatric Cardiology, Guy’s and St Thomas’ NHS Foundation Trust, Westminster Bridge Road, London SE1 7EH, London, UK
| | - Vittoria Vergani
- School of Biomedical Engineering & Imaging Sciences Rayne Institute, 4th Floor, Lambeth Wing St. Thomas' Hospital Westminster Bridge Road London SE1 7EH
| | - Maleeha Rizvi
- School of Biomedical Engineering & Imaging Sciences Rayne Institute, 4th Floor, Lambeth Wing St. Thomas' Hospital Westminster Bridge Road London SE1 7EH
- Department of Adult and Paediatric Cardiology, Guy’s and St Thomas’ NHS Foundation Trust, Westminster Bridge Road, London SE1 7EH, London, UK
| | - Louise Keehn
- Department of Clinical Pharmacology, King’s College London British Heart Foundation Centre, St Thomas’ Hospital, London, Westminster Bridge Road, London SE1 7EH, UK
| | - Raymond J Kim
- Division of Cardiology, Department of Medicine, Duke University, 40 Duke Medicine Circle, Durham, NC 27710, USA
| | - Robert M Judd
- Division of Cardiology, Department of Medicine, Duke University, 40 Duke Medicine Circle, Durham, NC 27710, USA
| | - Steffen E Petersen
- William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London, Charterhouse Square, London EC1M 6BQ, UK
- Barts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust, W Smithfield, London EC1A 7BE, UK
- Health Data Research UK, Gibbs Building, 215 Euston Rd., London NW1 2BE, UK
- Alan Turing Institute, 96 Euston Rd., London NW1 2DB, UK
| | - Reza Razavi
- School of Biomedical Engineering & Imaging Sciences Rayne Institute, 4th Floor, Lambeth Wing St. Thomas' Hospital Westminster Bridge Road London SE1 7EH
- Department of Adult and Paediatric Cardiology, Guy’s and St Thomas’ NHS Foundation Trust, Westminster Bridge Road, London SE1 7EH, London, UK
| | - Andrew P King
- School of Biomedical Engineering & Imaging Sciences Rayne Institute, 4th Floor, Lambeth Wing St. Thomas' Hospital Westminster Bridge Road London SE1 7EH
| | - Bram Ruijsink
- School of Biomedical Engineering & Imaging Sciences Rayne Institute, 4th Floor, Lambeth Wing St. Thomas' Hospital Westminster Bridge Road London SE1 7EH
- Department of Adult and Paediatric Cardiology, Guy’s and St Thomas’ NHS Foundation Trust, Westminster Bridge Road, London SE1 7EH, London, UK
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, 3584 CX Utrecht, the Netherlands
| | - Esther Puyol-Antón
- School of Biomedical Engineering & Imaging Sciences Rayne Institute, 4th Floor, Lambeth Wing St. Thomas' Hospital Westminster Bridge Road London SE1 7EH
| |
Collapse
|
14
|
Fang Q, Huang K, Yao X, Peng Y, Kan A, Song Y, Wang X, Xiao X, Gong L. The application of radiology for dilated cardiomyopathy diagnosis, treatment, and prognosis prediction: a bibliometric analysis. Quant Imaging Med Surg 2023; 13:7012-7028. [PMID: 37869323 PMCID: PMC10585513 DOI: 10.21037/qims-23-34] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/07/2023] [Accepted: 08/11/2023] [Indexed: 10/24/2023]
Abstract
Background Radiology plays a highly crucial role in the diagnosis, treatment, and prognosis prediction of dilated cardiomyopathy (DCM). Related research has increased rapidly over the past few years, but systematic analyses are lacking. This study thus aimed to provide a reference for further research by analyzing the knowledge field, development trends, and research hotspots of radiology in DCM using bibliometric methods. Methods Articles on the radiology of DCM published between 2002 and 2021 in the Web of Science Core Collection database (WoSCCd) were searched and analyzed. Data were retrieved and analyzed using CiteSpace V, VOSviewer, and Scimago Graphic software, and included the name, research institution, and nationality of authors; journals of publication; and the number of citations. Results A total of 4,257 articles were identified on radiology of DCM from WoSCCd. The number of articles published in this field has grown steadily from 2002 to 2021 and is expected to reach 392 annually by 2024. According to subfields, the number of papers published in cardiac magnetic resonance field increased steadily. The authors from the United States published the most (1,364 articles, 32.04%) articles. The author with the most articles published was Bax JJ (54 articles, 1.27%) from Leiden University Medical Center. The most cited article was titled "2016 ESC Guidelines for the diagnosis and treatment of acute and chronic heart failure", with 138 citations. Citation-based clustering showed that arrhythmogenic cardiomyopathy, T1 mapping, and endomyocardial biopsy are the current hots pots for research in DCM radiology. The most frequently occurring keyword was "dilated cardiomyopathy". The keyword-based clusters mainly included "late gadolinium enhancement", "congestive heart failure", "cardiovascular magnetic resonance", "sudden cardiac death", "ventricular arrhythmia", and "cardiac resynchronization therapy". Conclusions The United States and Northern Europe are the most influential countries in research on DCM radiology, with many leading distinguished research institutions. The current research hots pots are myocardial fibrosis, risk stratification of ventricular arrhythmia, the prognosis of cardiac resynchronization therapy (CRT) treatment, and subtype classification of DCM.
Collapse
Affiliation(s)
- Qimin Fang
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Kaiyao Huang
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Xinyu Yao
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Yun Peng
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Ao Kan
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Yipei Song
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Xiwen Wang
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Xuan Xiao
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| | - Lianggeng Gong
- Department of Radiology, The Second Affiliated Hospital of Nanchang University, Nanchang, China
| |
Collapse
|
15
|
Niskanen JE, Ohlsson Å, Ljungvall I, Drögemüller M, Ernst RF, Dooijes D, van Deutekom HWM, van Tintelen JP, Snijders Blok CJB, van Vugt M, van Setten J, Asselbergs FW, Petrič AD, Salonen M, Hundi S, Hörtenhuber M, Kere J, Pyle WG, Donner J, Postma AV, Leeb T, Andersson G, Hytönen MK, Häggström J, Wiberg M, Friederich J, Eberhard J, Harakalova M, van Steenbeek FG, Wess G, Lohi H. Identification of novel genetic risk factors of dilated cardiomyopathy: from canine to human. Genome Med 2023; 15:73. [PMID: 37723491 PMCID: PMC10506233 DOI: 10.1186/s13073-023-01221-3] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 08/17/2023] [Indexed: 09/20/2023] Open
Abstract
BACKGROUND Dilated cardiomyopathy (DCM) is a life-threatening heart disease and a common cause of heart failure due to systolic dysfunction and subsequent left or biventricular dilatation. A significant number of cases have a genetic etiology; however, as a complex disease, the exact genetic risk factors are largely unknown, and many patients remain without a molecular diagnosis. METHODS We performed GWAS followed by whole-genome, transcriptome, and immunohistochemical analyses in a spontaneously occurring canine model of DCM. Canine gene discovery was followed up in three human DCM cohorts. RESULTS Our results revealed two independent additive loci associated with the typical DCM phenotype comprising left ventricular systolic dysfunction and dilatation. We highlight two novel candidate genes, RNF207 and PRKAA2, known for their involvement in cardiac action potentials, energy homeostasis, and morphology. We further illustrate the distinct genetic etiologies underlying the typical DCM phenotype and ventricular premature contractions. Finally, we followed up on the canine discoveries in human DCM patients and discovered candidate variants in our two novel genes. CONCLUSIONS Collectively, our study yields insight into the molecular pathophysiology of DCM and provides a large animal model for preclinical studies.
Collapse
Affiliation(s)
- Julia E Niskanen
- Department of Medical and Clinical Genetics, University of Helsinki, Haartmaninkatu 8, 00290, Helsinki, Finland
- Department of Veterinary Biosciences, University of Helsinki, Agnes Sjöbergin katu 2, 00790, Helsinki, Finland
- Folkhälsan Research Center, Haartmaninkatu 8, P.O.Box 63, 00290, Helsinki, Finland
| | - Åsa Ohlsson
- Department of Animal Breeding and Genetics, Swedish University of Agricultural Sciences, Uppsala, Sweden
| | - Ingrid Ljungvall
- Department of Clinical Sciences, Swedish University of Agricultural Sciences, Uppsala, Sweden
| | - Michaela Drögemüller
- Institute of Genetics, Vetsuisse Faculty, University of Bern, Bern, 3001, Switzerland
| | - Robert F Ernst
- Department of Genetics, University Medical Centre Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Dennis Dooijes
- Department of Genetics, University Medical Centre Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Hanneke W M van Deutekom
- Department of Genetics, University Medical Centre Utrecht, Utrecht University, Utrecht, The Netherlands
| | - J Peter van Tintelen
- Department of Genetics, University Medical Centre Utrecht, Utrecht University, Utrecht, The Netherlands
| | - Christian J B Snijders Blok
- Department of Cardiology, Division Heart & Lungs, University Medical Center Utrecht (UMCU), Utrecht, The Netherlands
- Regenerative Medicine Centre Utrecht, University of Utrecht, Utrecht, The Netherlands
| | - Marion van Vugt
- Department of Cardiology, Division Heart & Lungs, University Medical Center Utrecht (UMCU), Utrecht, The Netherlands
| | - Jessica van Setten
- Department of Cardiology, Division Heart & Lungs, University Medical Center Utrecht (UMCU), Utrecht, The Netherlands
| | - Folkert W Asselbergs
- Amsterdam University Medical Centers, Department of Cardiology, University of Amsterdam, Amsterdam, The Netherlands
- Health Data Research UK and Institute of Health Informatics, University College London, London, UK
| | | | - Milla Salonen
- Department of Medical and Clinical Genetics, University of Helsinki, Haartmaninkatu 8, 00290, Helsinki, Finland
- Department of Veterinary Biosciences, University of Helsinki, Agnes Sjöbergin katu 2, 00790, Helsinki, Finland
- Folkhälsan Research Center, Haartmaninkatu 8, P.O.Box 63, 00290, Helsinki, Finland
| | - Sruthi Hundi
- Department of Medical and Clinical Genetics, University of Helsinki, Haartmaninkatu 8, 00290, Helsinki, Finland
- Department of Veterinary Biosciences, University of Helsinki, Agnes Sjöbergin katu 2, 00790, Helsinki, Finland
- Folkhälsan Research Center, Haartmaninkatu 8, P.O.Box 63, 00290, Helsinki, Finland
| | - Matthias Hörtenhuber
- Department of Biosciences and Nutrition, Karolinska Institutet, Huddinge, Sweden
| | - Juha Kere
- Folkhälsan Research Center, Haartmaninkatu 8, P.O.Box 63, 00290, Helsinki, Finland
- Department of Biosciences and Nutrition, Karolinska Institutet, Huddinge, Sweden
- Research Programs Unit, Stem Cells and Metabolism Research Program, University of Helsinki, Helsinki, Finland
| | - W Glen Pyle
- Department of Biomedical Sciences, University of Guelph, Guelph, ON, Canada
- IMPART Investigator Team Canada, Dalhousie Medicine, Saint John, NB, Canada
| | - Jonas Donner
- Wisdom Panel Research Team, Wisdom Panel, Kinship, Helsinki, Finland
| | - Alex V Postma
- Department of Human Genetics, Amsterdam University Medical Center, Amsterdam, The Netherlands
- Department of Medical Biology, Amsterdam University Medical Center, Amsterdam, The Netherlands
| | - Tosso Leeb
- Institute of Genetics, Vetsuisse Faculty, University of Bern, Bern, 3001, Switzerland
| | - Göran Andersson
- Department of Animal Breeding and Genetics, Swedish University of Agricultural Sciences, Uppsala, Sweden
| | - Marjo K Hytönen
- Department of Medical and Clinical Genetics, University of Helsinki, Haartmaninkatu 8, 00290, Helsinki, Finland
- Department of Veterinary Biosciences, University of Helsinki, Agnes Sjöbergin katu 2, 00790, Helsinki, Finland
- Folkhälsan Research Center, Haartmaninkatu 8, P.O.Box 63, 00290, Helsinki, Finland
| | - Jens Häggström
- Department of Clinical Sciences, Swedish University of Agricultural Sciences, Uppsala, Sweden
| | - Maria Wiberg
- Department of Equine and Small Animal Medicine, University of Helsinki, Helsinki, Finland
| | - Jana Friederich
- LMU Small Animal Clinic, Ludwig Maximilians University of Munich, Munich, Germany
| | - Jenny Eberhard
- LMU Small Animal Clinic, Ludwig Maximilians University of Munich, Munich, Germany
| | - Magdalena Harakalova
- Department of Cardiology, Division Heart & Lungs, University Medical Center Utrecht (UMCU), Utrecht, The Netherlands
- Regenerative Medicine Centre Utrecht, University of Utrecht, Utrecht, The Netherlands
| | - Frank G van Steenbeek
- Department of Cardiology, Division Heart & Lungs, University Medical Center Utrecht (UMCU), Utrecht, The Netherlands
- Regenerative Medicine Centre Utrecht, University of Utrecht, Utrecht, The Netherlands
- Department of Clinical Sciences, Faculty of Veterinary Medicine, Utrecht University, Yalelaan 108, Utrecht, 3584 CM, The Netherlands
| | - Gerhard Wess
- LMU Small Animal Clinic, Ludwig Maximilians University of Munich, Munich, Germany
| | - Hannes Lohi
- Department of Medical and Clinical Genetics, University of Helsinki, Haartmaninkatu 8, 00290, Helsinki, Finland.
- Department of Veterinary Biosciences, University of Helsinki, Agnes Sjöbergin katu 2, 00790, Helsinki, Finland.
- Folkhälsan Research Center, Haartmaninkatu 8, P.O.Box 63, 00290, Helsinki, Finland.
| |
Collapse
|
16
|
Gonzales RA, Ibáñez DH, Hann E, Popescu IA, Burrage MK, Lee YP, Altun İ, Weintraub WS, Kwong RY, Kramer CM, Neubauer S, Ferreira VM, Zhang Q, Piechnik SK. Quality control-driven deep ensemble for accountable automated segmentation of cardiac magnetic resonance LGE and VNE images. Front Cardiovasc Med 2023; 10:1213290. [PMID: 37753166 PMCID: PMC10518404 DOI: 10.3389/fcvm.2023.1213290] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/27/2023] [Accepted: 08/16/2023] [Indexed: 09/28/2023] Open
Abstract
Background Late gadolinium enhancement (LGE) cardiovascular magnetic resonance (CMR) imaging is the gold standard for non-invasive myocardial tissue characterisation. However, accurate segmentation of the left ventricular (LV) myocardium remains a challenge due to limited training data and lack of quality control. This study addresses these issues by leveraging generative adversarial networks (GAN)-generated virtual native enhancement (VNE) images to expand the training set and incorporating an automated quality control-driven (QCD) framework to improve segmentation reliability. Methods A dataset comprising 4,716 LGE images (from 1,363 patients with hypertrophic cardiomyopathy and myocardial infarction) was used for development. To generate additional clinically validated data, LGE data were augmented with a GAN-based generator to produce VNE images. LV was contoured on these images manually by clinical observers. To create diverse candidate segmentations, the QCD framework involved multiple U-Nets, which were combined using statistical rank filters. The framework predicted the Dice Similarity Coefficient (DSC) for each candidate segmentation, with the highest predicted DSC indicating the most accurate and reliable result. The performance of the QCD ensemble framework was evaluated on both LGE and VNE test datasets (309 LGE/VNE images from 103 patients), assessing segmentation accuracy (DSC) and quality prediction (mean absolute error (MAE) and binary classification accuracy). Results The QCD framework effectively and rapidly segmented the LV myocardium (<1 s per image) on both LGE and VNE images, demonstrating robust performance on both test datasets with similar mean DSC (LGE: 0.845 ± 0.075 ; VNE: 0.845 ± 0.071 ; p = n s ). Incorporating GAN-generated VNE data into the training process consistently led to enhanced performance for both individual models and the overall framework. The quality control mechanism yielded a high performance (MAE = 0.043 , accuracy = 0.951 ) emphasising the accuracy of the quality control-driven strategy in predicting segmentation quality in clinical settings. Overall, no statistical difference (p = n s ) was found when comparing the LGE and VNE test sets across all experiments. Conclusions The QCD ensemble framework, leveraging GAN-generated VNE data and an automated quality control mechanism, significantly improved the accuracy and reliability of LGE segmentation, paving the way for enhanced and accountable diagnostic imaging in routine clinical use.
Collapse
Affiliation(s)
- Ricardo A. Gonzales
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
| | - Daniel H. Ibáñez
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
- Artificio, Cambridge, MA, United States
| | - Evan Hann
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
| | - Iulia A. Popescu
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
| | - Matthew K. Burrage
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
- Faculty of Medicine, University of Queensland, Brisbane, QLD, Australia
| | - Yung P. Lee
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
| | - İbrahim Altun
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
| | - William S. Weintraub
- MedStar Health Research Institute, Georgetown University, Washington, DC, United States
| | - Raymond Y. Kwong
- Cardiovascular Division, Department of Medicine, Brigham and Women’s Hospital, Harvard Medical School, Boston, MA, United States
| | - Christopher M. Kramer
- Department of Medicine, University of Virginia Health System, Charlottesville, VA, United States
| | - Stefan Neubauer
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
| | | | | | - Vanessa M. Ferreira
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
| | - Qiang Zhang
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
| | - Stefan K. Piechnik
- Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Division of Cardiovascular Medicine, Radcliffe Department of Medicine, John Radcliffe Hospital, University of Oxford, Oxford, United Kingdom
| |
Collapse
|
17
|
Ng M, Guo F, Biswas L, Petersen SE, Piechnik SK, Neubauer S, Wright G. Estimating Uncertainty in Neural Networks for Cardiac MRI Segmentation: A Benchmark Study. IEEE Trans Biomed Eng 2023; 70:1955-1966. [PMID: 37015623 DOI: 10.1109/tbme.2022.3232730] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/31/2022]
Abstract
OBJECTIVE Convolutional neural networks (CNNs) have demonstrated promise in automated cardiac magnetic resonance image segmentation. However, when using CNNs in a large real-world dataset, it is important to quantify segmentation uncertainty and identify segmentations which could be problematic. In this work, we performed a systematic study of Bayesian and non-Bayesian methods for estimating uncertainty in segmentation neural networks. METHODS We evaluated Bayes by Backprop, Monte Carlo Dropout, Deep Ensembles, and Stochastic Segmentation Networks in terms of segmentation accuracy, probability calibration, uncertainty on out-of-distribution images, and segmentation quality control. RESULTS We observed that Deep Ensembles outperformed the other methods except for images with heavy noise and blurring distortions. We showed that Bayes by Backprop is more robust to noise distortions while Stochastic Segmentation Networks are more resistant to blurring distortions. For segmentation quality control, we showed that segmentation uncertainty is correlated with segmentation accuracy for all the methods. With the incorporation of uncertainty estimates, we were able to reduce the percentage of poor segmentation to 5% by flagging 31-48% of the most uncertain segmentations for manual review, substantially lower than random review without using neural network uncertainty (reviewing 75-78% of all images). CONCLUSION This work provides a comprehensive evaluation of uncertainty estimation methods and showed that Deep Ensembles outperformed other methods in most cases. SIGNIFICANCE Neural network uncertainty measures can help identify potentially inaccurate segmentations and alert users for manual review.
Collapse
|
18
|
Schmidt AF, Bourfiss M, Alasiri A, Puyol-Anton E, Chopade S, van Vugt M, van der Laan SW, Gross C, Clarkson C, Henry A, Lumbers TR, van der Harst P, Franceschini N, Bis JC, Velthuis BK, te Riele AS, Hingorani AD, Ruijsink B, Asselbergs FW, van Setten J, Finan C. Druggable proteins influencing cardiac structure and function: Implications for heart failure therapies and cancer cardiotoxicity. SCIENCE ADVANCES 2023; 9:eadd4984. [PMID: 37126556 PMCID: PMC10132758 DOI: 10.1126/sciadv.add4984] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 06/15/2022] [Accepted: 03/24/2023] [Indexed: 05/03/2023]
Abstract
Dysfunction of either the right or left ventricle can lead to heart failure (HF) and subsequent morbidity and mortality. We performed a genome-wide association study (GWAS) of 16 cardiac magnetic resonance (CMR) imaging measurements of biventricular function and structure. Cis-Mendelian randomization (MR) was used to identify plasma proteins associating with CMR traits as well as with any of the following cardiac outcomes: HF, non-ischemic cardiomyopathy, dilated cardiomyopathy (DCM), atrial fibrillation, or coronary heart disease. In total, 33 plasma proteins were prioritized, including repurposing candidates for DCM and/or HF: IL18R (providing indirect evidence for IL18), I17RA, GPC5, LAMC2, PA2GA, CD33, and SLAF7. In addition, 13 of the 25 druggable proteins (52%; 95% confidence interval, 0.31 to 0.72) could be mapped to compounds with known oncological indications or side effects. These findings provide leads to facilitate drug development for cardiac disease and suggest that cardiotoxicities of several cancer treatments might represent mechanism-based adverse effects.
Collapse
Affiliation(s)
- Amand F. Schmidt
- Institute of Cardiovascular Science, Faculty of Population Health, University College London, London, UK
- UCL BHF Research Accelerator Centre, London, UK
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
- Department of Cardiology, Amsterdam Cardiovascular Sciences, Amsterdam University Medical Centre, University of Amsterdam, Amsterdam, Netherlands
| | - Mimount Bourfiss
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| | - Abdulrahman Alasiri
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
- Medical Genomics Research Department, King Abdullah International Medical Research Center, King Saud Bin Abdulaziz University for Health Sciences, Ministry of National Guard Health Affairs, Riyadh, Saudi Arabia
| | - Esther Puyol-Anton
- Department of Biomedical Engineering, School of Biomedical Engineering and Imaging Sciences, King's College London, King's Health Partners, London, UK
| | - Sandesh Chopade
- Institute of Cardiovascular Science, Faculty of Population Health, University College London, London, UK
- UCL BHF Research Accelerator Centre, London, UK
| | - Marion van Vugt
- Institute of Cardiovascular Science, Faculty of Population Health, University College London, London, UK
- UCL BHF Research Accelerator Centre, London, UK
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
- Department of Cardiology, Amsterdam Cardiovascular Sciences, Amsterdam University Medical Centre, University of Amsterdam, Amsterdam, Netherlands
| | - Sander W. van der Laan
- Central Diagnostics Laboratory, Division Laboratory, Pharmacy, and Biomedical Genetics, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| | - Christian Gross
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| | - Chris Clarkson
- Institute of Cardiovascular Science, Faculty of Population Health, University College London, London, UK
- UCL BHF Research Accelerator Centre, London, UK
| | - Albert Henry
- Institute of Cardiovascular Science, Faculty of Population Health, University College London, London, UK
- UCL BHF Research Accelerator Centre, London, UK
- Institute of Health Informatics, Faculty of Population Health, University College London, London, UK
| | - Tom R. Lumbers
- UCL BHF Research Accelerator Centre, London, UK
- Institute of Health Informatics, Faculty of Population Health, University College London, London, UK
| | - Pim van der Harst
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| | - Nora Franceschini
- Department of Epidemiology, Gillings School of Global Public Health, University of North Carolina, Chapel Hill, NC, USA
| | - Joshua C. Bis
- Cardiovascular Health Research Unit, Department of Medicine, University of Washington, Seattle, WA, USA
| | - Birgitta K. Velthuis
- Department of Radiology, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| | - Anneline S. J. M. te Riele
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
- Netherlands Heart Institute, Utrecht, Netherlands
- Member of the European Reference Network for rare, low prevalence, and complex diseases of the heart (ERN GUARD HEART; http://guardheart.ern-net.eu)
| | - Aroon D. Hingorani
- Institute of Cardiovascular Science, Faculty of Population Health, University College London, London, UK
- UCL BHF Research Accelerator Centre, London, UK
| | - Bram Ruijsink
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
- Department of Biomedical Engineering, School of Biomedical Engineering and Imaging Sciences, King's College London, King's Health Partners, London, UK
| | - Folkert W. Asselbergs
- Institute of Cardiovascular Science, Faculty of Population Health, University College London, London, UK
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
- Department of Cardiology, Amsterdam Cardiovascular Sciences, Amsterdam University Medical Centre, University of Amsterdam, Amsterdam, Netherlands
- Institute of Health Informatics, Faculty of Population Health, University College London, London, UK
- Member of the European Reference Network for rare, low prevalence, and complex diseases of the heart (ERN GUARD HEART; http://guardheart.ern-net.eu)
| | - Jessica van Setten
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| | - Chris Finan
- Institute of Cardiovascular Science, Faculty of Population Health, University College London, London, UK
- UCL BHF Research Accelerator Centre, London, UK
- Department of Cardiology, Division Heart and Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, Netherlands
| |
Collapse
|
19
|
Shimoyama T, Gaj S, Nakamura K, Kovi S, Man S, Uchino K. Quantitative CTA vascular calcification, atherosclerosis burden, and stroke mechanism in patients with ischemic stroke. J Neurol Sci 2023; 449:120667. [PMID: 37148773 DOI: 10.1016/j.jns.2023.120667] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/05/2022] [Revised: 04/23/2023] [Accepted: 04/27/2023] [Indexed: 05/08/2023]
Abstract
BACKGROUND Vascular calcification is recognized as the advanced stage of atherosclerosis burden. We hypothesized that vascular calcium quantification in CT angiography (CTA) would be helpful to differentiate large artery atherosclerosis (LAA) from other stroke etiology in patients with ischemic stroke. METHODS We studied 375 acute ischemic stroke patients (200 males, mean age 69.9 years) who underwent complete CTA images of the aortic arch, neck, and head. The automatic artery and calcification segmentation method measured calcification volumes in the intracranial internal carotid artery (ICA), cervical carotid artery, and aortic arch using deep-learning U-net model and region-grow algorithms. We investigated the correlations and patterns of vascular calcification in the different vessel beds among stroke etiology by age category (young: <65 years, intermediate: 65-74 years, older ≥75 years). RESULTS Ninety-five (25.3%) were diagnosed with LAA according to TOAST criteria. Median calcification volumes were higher by increasing the age category in each vessel bed. One-way ANOVA with Bonferroni correction showed calcification volumes in all vessel beds were significantly higher in LAA compared with other stroke subtypes in the younger subgroup. Calcification volumes were independently associated with LAA in intracranial ICA (OR; 2.89, 95% CI 1.56-5.34, P = .001), cervical carotid artery (OR; 3.40, 95% CI 1.94-5.94, P < .001) and aorta (OR; 1.69, 95%CI 1.01-2.80, P = .044) in younger subsets. By contrast, the intermediate and older subsets did not show a significant relationship between calcification volumes and stroke subtypes. CONCLUSION Atherosclerosis calcium volumes in major vessels were significantly higher in LAA compared to non-LAA stroke in younger age.
Collapse
Affiliation(s)
- Takashi Shimoyama
- Cerebrovascular Center, Neurological Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Sibaji Gaj
- Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Kunio Nakamura
- Department of Biomedical Engineering, Lerner Research Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Shivakrishna Kovi
- Cerebrovascular Center, Neurological Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Shumei Man
- Cerebrovascular Center, Neurological Institute, Cleveland Clinic, Cleveland, OH, USA
| | - Ken Uchino
- Cerebrovascular Center, Neurological Institute, Cleveland Clinic, Cleveland, OH, USA.
| |
Collapse
|
20
|
Ferreira VM, Plein S, Wong TC, Tao Q, Raisi-Estabragh Z, Jain SS, Han Y, Ojha V, Bluemke DA, Hanneman K, Weinsaft J, Vidula MK, Ntusi NAB, Schulz-Menger J, Kim J. Cardiovascular magnetic resonance for evaluation of cardiac involvement in COVID-19: recommendations by the Society for Cardiovascular Magnetic Resonance. J Cardiovasc Magn Reson 2023; 25:21. [PMID: 36973744 PMCID: PMC10041524 DOI: 10.1186/s12968-023-00933-0] [Citation(s) in RCA: 10] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/09/2023] [Accepted: 03/14/2023] [Indexed: 03/29/2023] Open
Abstract
Coronavirus disease 2019 (COVID-19) is an ongoing global pandemic that has affected nearly 600 million people to date across the world. While COVID-19 is primarily a respiratory illness, cardiac injury is also known to occur. Cardiovascular magnetic resonance (CMR) imaging is uniquely capable of characterizing myocardial tissue properties in-vivo, enabling insights into the pattern and degree of cardiac injury. The reported prevalence of myocardial involvement identified by CMR in the context of COVID-19 infection among previously hospitalized patients ranges from 26 to 60%. Variations in the reported prevalence of myocardial involvement may result from differing patient populations (e.g. differences in severity of illness) and the varying intervals between acute infection and CMR evaluation. Standardized methodologies in image acquisition, analysis, interpretation, and reporting of CMR abnormalities across would likely improve concordance between studies. This consensus document by the Society for Cardiovascular Magnetic Resonance (SCMR) provides recommendations on CMR imaging and reporting metrics towards the goal of improved standardization and uniform data acquisition and analytic approaches when performing CMR in patients with COVID-19 infection.
Collapse
Affiliation(s)
- Vanessa M Ferreira
- University of Oxford Centre for Clinical Magnetic Resonance Research (OCMR), Oxford British Heart Foundation Centre of Research Excellence, The National Institute for Health Research Oxford Biomedical Research Centre at the Oxford University Hospitals NHS Foundation Trust, Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, UK
| | - Sven Plein
- Department of Biomedical Imaging Science, University of Leeds, Leeds, UK
| | - Timothy C Wong
- Division of Cardiology, Department of Medicine, University of Pittsburgh School of Medicine, Pittsburgh, USA
| | - Qian Tao
- Department of Imaging Physics, Delft University of Technology, Delft, The Netherlands
| | - Zahra Raisi-Estabragh
- William Harvey Research Institute, NIHR Barts Biomedical Research Centre, Queen Mary University of London, Charterhouse Square, London, EC1M 6BQ, UK
| | - Supriya S Jain
- Division of Pediatric Cardiology, Department of Pediatrics, Maria Fareri Children's Hospital at Westchester Medical Center, New York Medical College, New York, USA
| | - Yuchi Han
- Cardiovascular Medicine, Wexner Medical Center, The Ohio State University, Columbus, USA
| | - Vineeta Ojha
- Department of Cardiovascular Radiology and Endovascular Interventions, All India Institute of Medical Sciences, New Delhi, India
| | - David A Bluemke
- Department of Radiology, University of Wisconsin School of Medicine and Public Health, Madison, USA
| | - Kate Hanneman
- Department of Medical Imaging, Toronto General Hospital, University of Toronto, Toronto, Canada
| | - Jonathan Weinsaft
- Department of Medicine, Division of Cardiology, Weill Cornell Medicine/New York Presbyterian Hospital, Weill Cornell Medical College, New York, USA
| | - Mahesh K Vidula
- Division of Cardiovascular Medicine, University of Pennsylvania, Philadelphia, USA
| | - Ntobeko A B Ntusi
- Division of Cardiology, Department of Medicine, University of Cape Town and Groote Schuur Hospital; Cape Heart Institute, University of Cape Town, South African Medical Research Council Extramural Unit On Intersection of Noncommunicable Diseases and Infectious Diseases, Cape Town, South Africa
| | - Jeanette Schulz-Menger
- Working Group on Cardiovascular Magnetic Resonance, Experimental and Clinical Research Center, a joint cooperation between Charité and MDC, Charité University Medicine, Berlin, Germany
- Department of Cardiology and Nephrology, Helios Hospital Berlin-Buch, Berlin, Germany
| | - Jiwon Kim
- Department of Medicine, Division of Cardiology, Weill Cornell Medicine/New York Presbyterian Hospital, Weill Cornell Medical College, New York, USA.
| |
Collapse
|
21
|
Kikano SD, Weingarten A, Sunthankar SD, McEachern W, George-Durett K, Parra DA, Soslow JH, Chew JD. Association of cardiovascular magnetic resonance diastolic indices with arrhythmia in repaired Tetralogy of Fallot. J Cardiovasc Magn Reson 2023; 25:17. [PMID: 36907898 PMCID: PMC10009941 DOI: 10.1186/s12968-023-00928-x] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/07/2022] [Accepted: 02/23/2023] [Indexed: 03/14/2023] Open
Abstract
BACKGROUND Patients with repaired Tetralogy of Fallot (rTOF) experience a high burden of long-term morbidity, particularly arrhythmias. Cardiovascular magnetic resonance (CMR) is routinely used to assess ventricular characteristics but the relationship between CMR diastolic function and arrhythmia has not been evaluated. We hypothesized in rTOF, left ventricular (LV) diastolic dysfunction on CMR would correlate with arrhythmias and mortality. METHODS Adolescents and adults with rTOF who underwent CMR were compared to healthy controls (n = 58). Standard ventricular parameters were assessed and manual planimetry was performed to generate filling curves and indices of diastolic function. Chart review was performed to collect outcomes. Univariate and multivariable logistic regression was performed to identify outcome associations. RESULTS One-hundred sixty-seven subjects with rTOF (mean age 32 years) and 58 healthy control subjects underwent CMR. Patients with rTOF had decreased LV volumes and increased right ventricular (RV) volumes, lower RV ejection fraction (RVEF), lower peak ejection rate (PER), peak filling rate (PFR) and PFR indexed to end-diastolic volume (PFR/EDV) compared to healthy controls. Eighty-three subjects with rTOF had arrhythmia (63 atrial, 47 ventricular) and 11 died. Left atrial (LA) volumes, time to peak filling rate (tPFR), and PFR/EDV were associated with arrhythmia on univariate analysis. PER/EDV was associated with ventricular (Odds ratio, OR 0.43 [0.24-0.80], p = 0.007) and total arrhythmia (OR 0.56 [0.37-0.92], p = 0.021) burden. A multivariable predictive model including diastolic covariates showed improved prediction for arrhythmia compared to clinical and conventional CMR measures (area under curve (AUC) 0.749 v. 0.685 for overall arrhythmia). PFR/EDV was decreased and tPFR was increased in rTOF subjects with mortality as compared to those without mortality. CONCLUSIONS Subjects with rTOF have abnormal LV diastolic function compared to healthy controls. Indices of LV diastolic function were associated with arrhythmia and mortality. CMR diastolic indices may be helpful in risk stratification for arrhythmia.
Collapse
Affiliation(s)
- Sandra D Kikano
- Thomas P. Graham Division of Pediatric Cardiology Monroe Carell Jr Children's Hospital at Vanderbilt University, 2200 Children's Way Suite 5230, Doctors' Office Tower, Nashville, TN, 37232-9119, USA.
| | - Angela Weingarten
- Thomas P. Graham Division of Pediatric Cardiology Monroe Carell Jr Children's Hospital at Vanderbilt University, 2200 Children's Way Suite 5230, Doctors' Office Tower, Nashville, TN, 37232-9119, USA
| | - Sudeep D Sunthankar
- Thomas P. Graham Division of Pediatric Cardiology Monroe Carell Jr Children's Hospital at Vanderbilt University, 2200 Children's Way Suite 5230, Doctors' Office Tower, Nashville, TN, 37232-9119, USA
| | - William McEachern
- Thomas P. Graham Division of Pediatric Cardiology Monroe Carell Jr Children's Hospital at Vanderbilt University, 2200 Children's Way Suite 5230, Doctors' Office Tower, Nashville, TN, 37232-9119, USA
| | - Kristen George-Durett
- Thomas P. Graham Division of Pediatric Cardiology Monroe Carell Jr Children's Hospital at Vanderbilt University, 2200 Children's Way Suite 5230, Doctors' Office Tower, Nashville, TN, 37232-9119, USA
| | - David A Parra
- Thomas P. Graham Division of Pediatric Cardiology Monroe Carell Jr Children's Hospital at Vanderbilt University, 2200 Children's Way Suite 5230, Doctors' Office Tower, Nashville, TN, 37232-9119, USA
| | - Jonathan H Soslow
- Thomas P. Graham Division of Pediatric Cardiology Monroe Carell Jr Children's Hospital at Vanderbilt University, 2200 Children's Way Suite 5230, Doctors' Office Tower, Nashville, TN, 37232-9119, USA
| | - Joshua D Chew
- Thomas P. Graham Division of Pediatric Cardiology Monroe Carell Jr Children's Hospital at Vanderbilt University, 2200 Children's Way Suite 5230, Doctors' Office Tower, Nashville, TN, 37232-9119, USA
| |
Collapse
|
22
|
Riazy L, Däuber S, Lange S, Viezzer DS, Ott S, Wiesemann S, Blaszczyk E, Mühlberg F, Zange L, Schulz-Menger J. Translating principles of quality control to cardiovascular magnetic resonance: assessing quantitative parameters of the left ventricle in a large cohort. Sci Rep 2023; 13:2205. [PMID: 36750647 PMCID: PMC9905535 DOI: 10.1038/s41598-023-29028-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/14/2022] [Accepted: 01/30/2023] [Indexed: 02/09/2023] Open
Abstract
Cardiac magnetic resonance (CMR) examinations require standardization to achieve reproducible results. Therefore, quality control as known as in other industries such as in-vitro diagnostics, could be of essential value. One such method is the statistical detection of long-time drifts of clinically relevant measurements. Starting in 2010, reports from all CMR examinations of a high-volume center were stored in a hospital information system. Quantitative parameters of the left ventricle were analyzed over time with moving averages of different window sizes. Influencing factors on the acquisition and on the downstream analysis were captured. 26,902 patient examinations were exported from the clinical information system. The moving median was compared to predefined tolerance ranges, which revealed an overall of 50 potential quality relevant changes ("alerts") in SV, EDV and LVM. Potential causes such as change of staff, scanner relocation and software changes were found not to be causal of the alerts. No other influencing factors were identified retrospectively. Statistical quality assurance systems based on moving average control charts may provide an important step towards reliability of quantitative CMR. A prospective evaluation is needed for the effective root cause analysis of quality relevant alerts.
Collapse
Affiliation(s)
- Leili Riazy
- Experimental and Clinical Research Center (ECRC), Charité Universitätsmedizin Berlin-Buch, Berlin, Germany.,DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany
| | | | - Steffen Lange
- Department of Computer Science, Darmstadt University of Applied Sciences, Darmstadt, Germany
| | - Darian Steven Viezzer
- Experimental and Clinical Research Center (ECRC), Charité Universitätsmedizin Berlin-Buch, Berlin, Germany.,DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany
| | - Steffen Ott
- HELIOS Hospital Berlin-Buch, Berlin, Germany
| | - Stephanie Wiesemann
- Experimental and Clinical Research Center (ECRC), Charité Universitätsmedizin Berlin-Buch, Berlin, Germany.,DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany
| | - Edyta Blaszczyk
- Experimental and Clinical Research Center (ECRC), Charité Universitätsmedizin Berlin-Buch, Berlin, Germany.,DZHK (German Centre for Cardiovascular Research), Partner Site Berlin, Berlin, Germany
| | - Fabian Mühlberg
- Experimental and Clinical Research Center (ECRC), Charité Universitätsmedizin Berlin-Buch, Berlin, Germany.,HELIOS Hospital Berlin-Buch, Berlin, Germany
| | - Leonora Zange
- Experimental and Clinical Research Center (ECRC), Charité Universitätsmedizin Berlin-Buch, Berlin, Germany.,HELIOS Hospital Berlin-Buch, Berlin, Germany
| | - Jeanette Schulz-Menger
- Experimental and Clinical Research Center (ECRC), Charité Universitätsmedizin Berlin-Buch, Berlin, Germany. .,HELIOS Hospital Berlin-Buch, Berlin, Germany.
| |
Collapse
|
23
|
Papetti DM, Van Abeelen K, Davies R, Menè R, Heilbron F, Perelli FP, Artico J, Seraphim A, Moon JC, Parati G, Xue H, Kellman P, Badano LP, Besozzi D, Nobile MS, Torlasco C. An accurate and time-efficient deep learning-based system for automated segmentation and reporting of cardiac magnetic resonance-detected ischemic scar. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2023; 229:107321. [PMID: 36586175 PMCID: PMC10331164 DOI: 10.1016/j.cmpb.2022.107321] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Received: 08/22/2022] [Revised: 11/21/2022] [Accepted: 12/19/2022] [Indexed: 06/17/2023]
Abstract
BACKGROUND AND OBJECTIVES Myocardial infarction scar (MIS) assessment by cardiac magnetic resonance provides prognostic information and guides patients' clinical management. However, MIS segmentation is time-consuming and not performed routinely. This study presents a deep-learning-based computational workflow for the segmentation of left ventricular (LV) MIS, for the first time performed on state-of-the-art dark-blood late gadolinium enhancement (DB-LGE) images, and the computation of MIS transmurality and extent. METHODS DB-LGE short-axis images of consecutive patients with myocardial infarction were acquired at 1.5T in two centres between Jan 1, 2019, and June 1, 2021. Two convolutional neural network (CNN) models based on the U-Net architecture were trained to sequentially segment the LV and MIS, by processing an incoming series of DB-LGE images. A 5-fold cross-validation was performed to assess the performance of the models. Model outputs were compared respectively with manual (LV endo- and epicardial border) and semi-automated (MIS, 4-Standard Deviation technique) ground truth to assess the accuracy of the segmentation. An automated post-processing and reporting tool was developed, computing MIS extent (expressed as relative infarcted mass) and transmurality. RESULTS The dataset included 1355 DB-LGE short-axis images from 144 patients (MIS in 942 images). High performance (> 0.85) as measured by the Intersection over Union metric was obtained for both the LV and MIS segmentations on the training sets. The performance for both LV and MIS segmentations was 0.83 on the test sets. Compared to the 4-Standard Deviation segmentation technique, our system was five times quicker (<1 min versus 7 ± 3 min), and required minimal user interaction. CONCLUSIONS Our solution successfully addresses different issues related to automatic MIS segmentation, including accuracy, time-effectiveness, and the automatic generation of a clinical report.
Collapse
Affiliation(s)
- Daniele M Papetti
- Department of Informatics, Systems and Communication, University of Milano-Bicocca, Viale Sarca 336, Milano 20126, Italy
| | - Kirsten Van Abeelen
- Department of Medicine and Surgery, University of Milano-Bicocca, Milan 20126, Italy
| | - Rhodri Davies
- Institute of Cardiovascular Science, University College London, London WC1E 6DD, UK; Barts Heart Centre, St Bartholomew's Hospital, West Smithfield, London EC1A 7BE, UK; MRC Unit for Lifelong Health and Ageing, University College London, London WC1E 6DD, UK
| | - Roberto Menè
- Department of Medicine and Surgery, University of Milano-Bicocca, Milan 20126, Italy; Department of Cardiology, IRCCS Istituto Auxologico Italiano, Via Magnasco 2, Milan 20145, Italy
| | - Francesca Heilbron
- Department of Cardiology, IRCCS Istituto Auxologico Italiano, Via Magnasco 2, Milan 20145, Italy
| | - Francesco P Perelli
- Department of Medicine and Surgery, University of Milano-Bicocca, Milan 20126, Italy; Department of Cardiology, IRCCS Istituto Auxologico Italiano, Via Magnasco 2, Milan 20145, Italy
| | - Jessica Artico
- Institute of Cardiovascular Science, University College London, London WC1E 6DD, UK; Barts Heart Centre, St Bartholomew's Hospital, West Smithfield, London EC1A 7BE, UK
| | - Andreas Seraphim
- Institute of Cardiovascular Science, University College London, London WC1E 6DD, UK; Department of Cardiac Electrophysiology, Barts Heart Centre, Barts Health NHS Trust, London EC1A 7BE, UK
| | - James C Moon
- Institute of Cardiovascular Science, University College London, London WC1E 6DD, UK; Barts Heart Centre, St Bartholomew's Hospital, West Smithfield, London EC1A 7BE, UK
| | - Gianfranco Parati
- Department of Cardiology, IRCCS Istituto Auxologico Italiano, Via Magnasco 2, Milan 20145, Italy
| | - Hui Xue
- National Heart, Lung, and Blood Institute, National Institutes of Health, DHHS, Bethesda, MD, USA.
| | - Peter Kellman
- Bicocca Bioinformatics Biostatistics and Bioimaging Centre (B4), University of Milano-Bicocca, Vedano al Lambro 20854, Italy
| | - Luigi P Badano
- Department of Medicine and Surgery, University of Milano-Bicocca, Milan 20126, Italy; Department of Cardiology, IRCCS Istituto Auxologico Italiano, Via Magnasco 2, Milan 20145, Italy
| | - Daniela Besozzi
- Department of Informatics, Systems and Communication, University of Milano-Bicocca, Viale Sarca 336, Milano 20126, Italy; Bicocca Bioinformatics Biostatistics and Bioimaging Centre (B4), University of Milano-Bicocca, Vedano al Lambro 20854, Italy.
| | - Marco S Nobile
- Bicocca Bioinformatics Biostatistics and Bioimaging Centre (B4), University of Milano-Bicocca, Vedano al Lambro 20854, Italy; Department of Environmental Sciences, Informatics and Statistics, Ca' Foscari University of Venice, Via Torino 155, Mestre, Venice 30172, Italy.
| | - Camilla Torlasco
- Department of Cardiology, IRCCS Istituto Auxologico Italiano, Via Magnasco 2, Milan 20145, Italy.
| |
Collapse
|
24
|
Zhao D, Ferdian E, Maso Talou GD, Quill GM, Gilbert K, Wang VY, Babarenda Gamage TP, Pedrosa J, D’hooge J, Sutton TM, Lowe BS, Legget ME, Ruygrok PN, Doughty RN, Camara O, Young AA, Nash MP. MITEA: A dataset for machine learning segmentation of the left ventricle in 3D echocardiography using subject-specific labels from cardiac magnetic resonance imaging. Front Cardiovasc Med 2023; 9:1016703. [PMID: 36704465 PMCID: PMC9871929 DOI: 10.3389/fcvm.2022.1016703] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/11/2022] [Accepted: 12/06/2022] [Indexed: 01/11/2023] Open
Abstract
Segmentation of the left ventricle (LV) in echocardiography is an important task for the quantification of volume and mass in heart disease. Continuing advances in echocardiography have extended imaging capabilities into the 3D domain, subsequently overcoming the geometric assumptions associated with conventional 2D acquisitions. Nevertheless, the analysis of 3D echocardiography (3DE) poses several challenges associated with limited spatial resolution, poor contrast-to-noise ratio, complex noise characteristics, and image anisotropy. To develop automated methods for 3DE analysis, a sufficiently large, labeled dataset is typically required. However, ground truth segmentations have historically been difficult to obtain due to the high inter-observer variability associated with manual analysis. We address this lack of expert consensus by registering labels derived from higher-resolution subject-specific cardiac magnetic resonance (CMR) images, producing 536 annotated 3DE images from 143 human subjects (10 of which were excluded). This heterogeneous population consists of healthy controls and patients with cardiac disease, across a range of demographics. To demonstrate the utility of such a dataset, a state-of-the-art, self-configuring deep learning network for semantic segmentation was employed for automated 3DE analysis. Using the proposed dataset for training, the network produced measurement biases of -9 ± 16 ml, -1 ± 10 ml, -2 ± 5 %, and 5 ± 23 g, for end-diastolic volume, end-systolic volume, ejection fraction, and mass, respectively, outperforming an expert human observer in terms of accuracy as well as scan-rescan reproducibility. As part of the Cardiac Atlas Project, we present here a large, publicly available 3DE dataset with ground truth labels that leverage the higher resolution and contrast of CMR, to provide a new benchmark for automated 3DE analysis. Such an approach not only reduces the effect of observer-specific bias present in manual 3DE annotations, but also enables the development of analysis techniques which exhibit better agreement with CMR compared to conventional methods. This represents an important step for enabling more efficient and accurate diagnostic and prognostic information to be obtained from echocardiography.
Collapse
Affiliation(s)
- Debbie Zhao
- Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand
| | - Edward Ferdian
- Department of Anatomy and Medical Imaging, University of Auckland, Auckland, New Zealand
| | | | - Gina M. Quill
- Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand
| | - Kathleen Gilbert
- Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand
| | - Vicky Y. Wang
- Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand
| | | | - João Pedrosa
- Institute for Systems and Computer Engineering, Technology and Science (INESC TEC), Porto, Portugal
| | - Jan D’hooge
- Department of Cardiovascular Sciences, KU Leuven, Leuven, Belgium
| | - Timothy M. Sutton
- Counties Manukau Health Cardiology, Middlemore Hospital, Auckland, New Zealand
| | - Boris S. Lowe
- Green Lane Cardiovascular Service, Auckland City Hospital, Auckland, New Zealand
| | - Malcolm E. Legget
- Department of Medicine, University of Auckland, Auckland, New Zealand
| | - Peter N. Ruygrok
- Green Lane Cardiovascular Service, Auckland City Hospital, Auckland, New Zealand
- Department of Medicine, University of Auckland, Auckland, New Zealand
| | - Robert N. Doughty
- Green Lane Cardiovascular Service, Auckland City Hospital, Auckland, New Zealand
- Department of Medicine, University of Auckland, Auckland, New Zealand
| | - Oscar Camara
- Department of Information and Communication Technologies, Universitat Pompeu Fabra, Barcelona, Spain
| | - Alistair A. Young
- Department of Anatomy and Medical Imaging, University of Auckland, Auckland, New Zealand
- Department of Biomedical Engineering, King’s College London, London, United Kingdom
| | - Martyn P. Nash
- Auckland Bioengineering Institute, University of Auckland, Auckland, New Zealand
- Department of Engineering Science, University of Auckland, Auckland, New Zealand
| |
Collapse
|
25
|
Byrne N, Clough JR, Valverde I, Montana G, King AP. A Persistent Homology-Based Topological Loss for CNN-Based Multiclass Segmentation of CMR. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:3-14. [PMID: 36044487 PMCID: PMC7614102 DOI: 10.1109/tmi.2022.3203309] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/10/2023]
Abstract
Multi-class segmentation of cardiac magnetic resonance (CMR) images seeks a separation of data into anatomical components with known structure and configuration. The most popular CNN-based methods are optimised using pixel wise loss functions, ignorant of the spatially extended features that characterise anatomy. Therefore, whilst sharing a high spatial overlap with the ground truth, inferred CNN-based segmentations can lack coherence, including spurious connected components, holes and voids. Such results are implausible, violating anticipated anatomical topology. In response, (single-class) persistent homology-based loss functions have been proposed to capture global anatomical features. Our work extends these approaches to the task of multi-class segmentation. Building an enriched topological description of all class labels and class label pairs, our loss functions make predictable and statistically significant improvements in segmentation topology using a CNN-based post-processing framework. We also present (and make available) a highly efficient implementation based on cubical complexes and parallel execution, enabling practical application within high resolution 3D data for the first time. We demonstrate our approach on 2D short axis and 3D whole heart CMR segmentation, advancing a detailed and faithful analysis of performance on two publicly available datasets.
Collapse
Affiliation(s)
- Nick Byrne
- School of BMEIS at KCL: London, SE1 7EH, UK. Nick Byrne and Isra Valverde are also with the Medical Physics and Paediatric Cardiology Departments respectively, both at GSTT: London, SE1 7EH, UK
| | - James R. Clough
- School of BMEIS at KCL: London, SE1 7EH, UK. Nick Byrne and Isra Valverde are also with the Medical Physics and Paediatric Cardiology Departments respectively, both at GSTT: London, SE1 7EH, UK
| | - Israel Valverde
- School of BMEIS at KCL: London, SE1 7EH, UK. Nick Byrne and Isra Valverde are also with the Medical Physics and Paediatric Cardiology Departments respectively, both at GSTT: London, SE1 7EH, UK
| | - Giovanni Montana
- Warwick Manufacturing Group at the University of Warwick: Coventry, CV4 7AL, UK
| | - Andrew P. King
- School of BMEIS at KCL: London, SE1 7EH, UK. Nick Byrne and Isra Valverde are also with the Medical Physics and Paediatric Cardiology Departments respectively, both at GSTT: London, SE1 7EH, UK
| |
Collapse
|
26
|
Cecelja M, Ruijsink B, Puyol‐Antón E, Li Y, Godwin H, King AP, Razavi R, Chowienczyk P. Aortic Distensibility Measured by Automated Analysis of Magnetic Resonance Imaging Predicts Adverse Cardiovascular Events in UK Biobank. J Am Heart Assoc 2022; 11:e026361. [PMID: 36444831 PMCID: PMC9851433 DOI: 10.1161/jaha.122.026361] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/29/2022] [Accepted: 08/04/2022] [Indexed: 11/30/2022]
Abstract
Background Automated analysis of cardiovascular magnetic resonance images provides the potential to assess aortic distensibility in large populations. The aim of this study was to compare the prediction of cardiovascular events by automated cardiovascular magnetic resonance with those of other simple measures of aortic stiffness suitable for population screening. Methods and Results Aortic distensibility was measured from automated segmentation of aortic cine cardiovascular magnetic resonance using artificial intelligence in 8435 participants. The associations of distensibility, brachial pulse pressure, and stiffness index (obtained by finger photoplethysmography) with conventional risk factors was examined by multivariable regression and incident cardiovascular events by Cox proportional-hazards regression. Mean (±SD) distensibility values for men and women were 1.77±1.15 and 2.10±1.45 (P<0.0001) 10-3 mm Hg-1, respectively. There was a good correlation between automatically and manually obtained systolic and diastolic aortic areas (r=0.980 and r=0.985, respectively). In regression analysis, distensibility associated with age, mean arterial pressure, heart rate, weight, and plasma glucose but not male sex, cholesterol or current smoking. During an average follow-up of 2.8±1.3 years, 86 participants experienced cardiovascular events 6 of whom died. Higher distensibility was associated with reduced risk of cardiovascular events (adjusted hazard ratio [HR], 0.61 per log unit of distensibility; P=0.016). There was no evidence of an association between pulse pressure (adjusted HR 1.00; P=0.715) or stiffness index (adjusted HR, 1.02; P=0.535) and risk of cardiovascular events. Conclusions Automated cardiovascular magnetic resonance-derived aortic distensibility may be incorporated into routine clinical imaging. It shows a similar association to cardiovascular risk factors as other measures of arterial stiffness and predicts new-onset cardiovascular events, making it a useful tool for the measurement of vascular aging and associated cardiovascular risk.
Collapse
Affiliation(s)
- Marina Cecelja
- King’s College London British Heart Foundation Centre, Department of Clinical PharmacologySt Thomas’ HospitalLondonUnited Kingdom
| | - Bram Ruijsink
- School of Bioengineering and Imaging SciencesKing’s College LondonLondonUnited Kingdom
| | - Esther Puyol‐Antón
- School of Bioengineering and Imaging SciencesKing’s College LondonLondonUnited Kingdom
| | - Ye Li
- King’s College London British Heart Foundation Centre, Department of Clinical PharmacologySt Thomas’ HospitalLondonUnited Kingdom
| | - Harriet Godwin
- King’s College London British Heart Foundation CentreSchool of Cardiovascular Medicine & Sciences, Department of CardiologyLondonUnited Kingdom
| | - Andrew P. King
- School of Bioengineering and Imaging SciencesKing’s College LondonLondonUnited Kingdom
| | - Reza Razavi
- School of Bioengineering and Imaging SciencesKing’s College LondonLondonUnited Kingdom
| | - Phil Chowienczyk
- King’s College London British Heart Foundation Centre, Department of Clinical PharmacologySt Thomas’ HospitalLondonUnited Kingdom
| |
Collapse
|
27
|
Bourfiss M, van Vugt M, Alasiri AI, Ruijsink B, van Setten J, Schmidt AF, Dooijes D, Puyol-Antón E, Velthuis BK, van Tintelen JP, te Riele AS, Baas AF, Asselbergs FW. Prevalence and Disease Expression of Pathogenic and Likely Pathogenic Variants Associated With Inherited Cardiomyopathies in the General Population. CIRCULATION. GENOMIC AND PRECISION MEDICINE 2022; 15:e003704. [PMID: 36264615 PMCID: PMC9770140 DOI: 10.1161/circgen.122.003704] [Citation(s) in RCA: 13] [Impact Index Per Article: 6.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
Abstract
BACKGROUND Pathogenic and likely pathogenic variants associated with arrhythmogenic right ventricular cardiomyopathy (ARVC), dilated cardiomyopathy (DCM), and hypertrophic cardiomyopathy (HCM) are recommended to be reported as secondary findings in genome sequencing studies. This provides opportunities for early diagnosis, but also fuels uncertainty in variant carriers (G+), since disease penetrance is incomplete. We assessed the prevalence and disease expression of G+ in the general population. METHODS We identified pathogenic and likely pathogenic variants associated with ARVC, DCM and/or HCM in 200 643 UK Biobank individuals, who underwent whole exome sequencing. We calculated the prevalence of G+ and analyzed the frequency of cardiomyopathy/heart failure diagnosis. In undiagnosed individuals, we analyzed early signs of disease expression using available electrocardiography and cardiac magnetic resonance imaging data. RESULTS We found a prevalence of 1:578, 1:251, and 1:149 for pathogenic and likely pathogenic variants associated with ARVC, DCM and HCM respectively. Compared with controls, cardiovascular mortality was higher in DCM G+ (odds ratio 1.67 [95% CI 1.04; 2.59], P=0.030), but similar in ARVC and HCM G+ (P≥0.100). Cardiomyopathy or heart failure diagnosis were more frequent in DCM G+ (odds ratio 3.66 [95% CI 2.24; 5.81], P=4.9×10-7) and HCM G+ (odds ratio 3.03 [95% CI 1.98; 4.56], P=5.8×10-7), but comparable in ARVC G+ (P=0.172). In contrast, ARVC G+ had more ventricular arrhythmias (P=3.3×10-4). In undiagnosed individuals, left ventricular ejection fraction was reduced in DCM G+ (P=0.009). CONCLUSIONS In the general population, pathogenic and likely pathogenic variants associated with ARVC, DCM, or HCM are not uncommon. Although G+ have increased mortality and morbidity, disease penetrance in these carriers from the general population remains low (1.2-3.1%). Follow-up decisions in case of incidental findings should not be based solely on a variant, but on multiple factors, including family history and disease expression.
Collapse
Affiliation(s)
- Mimount Bourfiss
- Dept of Cardiology, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (M.B., M.v.V., A.I.A., A.S.J.M.t.R., B.R., J.v.S., A.F.S., F.W.A.)
| | - Marion van Vugt
- Dept of Cardiology, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (M.B., M.v.V., A.I.A., A.S.J.M.t.R., B.R., J.v.S., A.F.S., F.W.A.)
| | - Abdulrahman I. Alasiri
- Dept of Cardiology, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (M.B., M.v.V., A.I.A., A.S.J.M.t.R., B.R., J.v.S., A.F.S., F.W.A.)
| | - Bram Ruijsink
- Dept of Cardiology, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (M.B., M.v.V., A.I.A., A.S.J.M.t.R., B.R., J.v.S., A.F.S., F.W.A.)
- School of Biomedical Engineering & Imaging Sciences, King’s College London, London, United Kingdom (B.R., E.P.-A.)
| | - Jessica van Setten
- Dept of Cardiology, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (M.B., M.v.V., A.I.A., A.S.J.M.t.R., B.R., J.v.S., A.F.S., F.W.A.)
| | - A. Floriaan Schmidt
- Dept of Cardiology, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (M.B., M.v.V., A.I.A., A.S.J.M.t.R., B.R., J.v.S., A.F.S., F.W.A.)
- Faculty of Population Health Sciences Institute of Cardiovascular Science, London, London, United Kingdom (A.F.S., F.W.A.)
| | - Dennis Dooijes
- Dept of Genetics, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (D.D., J.P.v.T., A.F.B.)
| | - Esther Puyol-Antón
- School of Biomedical Engineering & Imaging Sciences, King’s College London, London, United Kingdom (B.R., E.P.-A.)
| | - Birgitta K. Velthuis
- Dept of Radiology, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (B.K.V.)
| | - J. Peter van Tintelen
- Dept of Genetics, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (D.D., J.P.v.T., A.F.B.)
| | - Anneline S.J.M. te Riele
- Dept of Cardiology, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (M.B., M.v.V., A.I.A., A.S.J.M.t.R., B.R., J.v.S., A.F.S., F.W.A.)
- Netherlands Heart Institute, Utrecht, the Netherlands (A.S.J.M.t.R)
| | - Annette F. Baas
- Dept of Genetics, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (D.D., J.P.v.T., A.F.B.)
| | - Folkert W. Asselbergs
- Dept of Cardiology, Univ Medical Center Utrecht, Utrecht Univ, Utrecht, the Netherlands (M.B., M.v.V., A.I.A., A.S.J.M.t.R., B.R., J.v.S., A.F.S., F.W.A.)
- Faculty of Population Health Sciences Institute of Cardiovascular Science, London, London, United Kingdom (A.F.S., F.W.A.)
- Health Data Research UK & Institute of Health Informatics, Univ College London, London, United Kingdom (F.W.A.)
| |
Collapse
|
28
|
Kim WJC, Beqiri A, Lewandowski AJ, Puyol-Antón E, Markham DC, King AP, Leeson P, Lamata P. Beyond Simpson's Rule: Accounting for Orientation and Ellipticity Assumptions. ULTRASOUND IN MEDICINE & BIOLOGY 2022; 48:2476-2485. [PMID: 36137846 PMCID: PMC9810537 DOI: 10.1016/j.ultrasmedbio.2022.07.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 10/05/2021] [Revised: 06/21/2022] [Accepted: 07/24/2022] [Indexed: 06/16/2023]
Abstract
Simpson's biplane rule (SBR) is considered the gold standard method for left ventricle (LV) volume quantification from echocardiography but relies on a summation-of-disks approach that makes assumptions about LV orientation and cross-sectional shape. We aim to identify key limiting factors in SBR and to develop a new robust standard for volume quantification. Three methods for computing LV volume were studied: (i) SBR, (ii) addition of a truncated basal cone (TBC) to SBR and (iii) a novel method of basal-oriented disks (BODs). Three retrospective cohorts representative of the young, adult healthy and heart failure populations were used to study the impact of anatomical variations in volume computations. Results reveal how basal slanting can cause over- and underestimation of volume, with errors by SBR and TBC >10 mL for slanting angles >6°. Only the BOD method correctly accounted for basal slanting, reducing relative volume errors by SBR from -2.23 ± 2.21% to -0.70 ± 1.91% in the adult population and similar qualitative performance in the other two cohorts. In conclusion, the summation of basal oriented disks, a novel interpretation of SBR, is a more accurate and precise method for estimating LV volume.
Collapse
Affiliation(s)
- Woo-Jin Cho Kim
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Arian Beqiri
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK; Ultromics Ltd, Oxford, UK
| | - Adam J Lewandowski
- Cardiovascular Clinical Research Facility, Division of Cardiovascular Medicine, University of Oxford, Oxford, UK
| | - Esther Puyol-Antón
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | | | - Andrew P King
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Paul Leeson
- Cardiovascular Clinical Research Facility, Division of Cardiovascular Medicine, University of Oxford, Oxford, UK
| | - Pablo Lamata
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK.
| |
Collapse
|
29
|
Vandermolen S, Ricci F, Chahal CAA, Capelli C, Barakat K, Fedorowski A, Westwood M, Patel RS, Petersen SE, Gallina S, Pugliese F, Khanji MY. 'The Digital Cardiologist': How Technology Is Changing the Paradigm of Cardiology Training. Curr Probl Cardiol 2022; 47:101394. [PMID: 36100095 DOI: 10.1016/j.cpcardiol.2022.101394] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/02/2022] [Accepted: 09/07/2022] [Indexed: 11/18/2022]
Abstract
In the same way that the practice of cardiology has evolved over the years, so too has the way cardiology fellows in training (FITs) are trained. Propelled by recent advances in technology-catalyzed by COVID-19-and the requirement to adapt age-old methods of both teaching and health care delivery, many aspects, or 'domains', of learning have changed. These include the environments in which FITs work (outpatient clinics, 'on-call' inpatient service) and procedures in which they need clinical competency. Further advances in virtual reality are also changing the way FITs learn and interact. The proliferation of technology into the cardiology curriculum has led to some describing the need for FITs to develop into 'digital cardiologists', namely those who comfortably use digital tools to aid clinical practice, teaching, and training whilst, at the same time, retain the ability for human analysis and nuanced assessment so important to patient-centred training and clinical care.
Collapse
Affiliation(s)
- Sebastian Vandermolen
- Barts Heart Centre, Barts Health NHS Trust, London, West Smithfield, EC1A 7BE, UK; NIHR Barts Biomedical Research Centre, William Harvey Research Institute, Queen Mary University of London, EC1A 7BE, UK
| | - Fabrizio Ricci
- Institute of Advanced Biomedical Technologies, Department of Neuroscience, Imaging and Clinical Sciences, "G.d'Annunzio" University, Chieti, Italy; Department of Clinical Sciences, Lund University, Jan Waldenströms gata 35 - 205 02, Malmö, Sweden; Casa di Cura Villa Serena, Città Sant'Angelo, Pescara, Italy
| | - C Anwar A Chahal
- Barts Heart Centre, Barts Health NHS Trust, London, West Smithfield, EC1A 7BE, UK; Center for Inherited Cardiovascular Diseases, WellSpan Health, Lancaster, PA; Cardiac Electrophysiology, Cardiovascular Division, Hospital of the University of Pennsylvania, Philadelphia, PA; Department of Cardiovascular Medicine, Mayo Clinic, Rochester, MN
| | - Claudio Capelli
- Institute of Cardiovascular Science, University College London (London, UK)
| | - Khalid Barakat
- Barts Heart Centre, Barts Health NHS Trust, London, West Smithfield, EC1A 7BE, UK
| | - Artur Fedorowski
- Department of Clinical Sciences, Lund University, Jan Waldenströms gata 35 - 205 02, Malmö, Sweden; Department of Cardiology, Karolinska University Hospital, and Department of Medicine, Karolinska Institute, Stockholm, Sweden
| | - Mark Westwood
- NIHR Barts Biomedical Research Centre, William Harvey Research Institute, Queen Mary University of London, EC1A 7BE, UK
| | - Riyaz S Patel
- Barts Heart Centre, Barts Health NHS Trust, London, West Smithfield, EC1A 7BE, UK; Institute of Cardiovascular Science, University College London (London, UK)
| | - Steffen E Petersen
- Barts Heart Centre, Barts Health NHS Trust, London, West Smithfield, EC1A 7BE, UK; NIHR Barts Biomedical Research Centre, William Harvey Research Institute, Queen Mary University of London, EC1A 7BE, UK
| | - Sabina Gallina
- Institute of Advanced Biomedical Technologies, Department of Neuroscience, Imaging and Clinical Sciences, "G.d'Annunzio" University, Chieti, Italy
| | - Francesca Pugliese
- Barts Heart Centre, Barts Health NHS Trust, London, West Smithfield, EC1A 7BE, UK; NIHR Barts Biomedical Research Centre, William Harvey Research Institute, Queen Mary University of London, EC1A 7BE, UK
| | - Mohammed Y Khanji
- Barts Heart Centre, Barts Health NHS Trust, London, West Smithfield, EC1A 7BE, UK; NIHR Barts Biomedical Research Centre, William Harvey Research Institute, Queen Mary University of London, EC1A 7BE, UK; Newham University Hospital. Glen Road, Plaistow, Barts Health NHS Trust. London, UK.
| |
Collapse
|
30
|
Lustermans DRPRM, Amirrajab S, Veta M, Breeuwer M, Scannell CM. Optimized automated cardiac MR scar quantification with GAN-based data augmentation. COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE 2022; 226:107116. [PMID: 36148718 DOI: 10.1016/j.cmpb.2022.107116] [Citation(s) in RCA: 6] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Received: 09/28/2021] [Revised: 08/26/2022] [Accepted: 09/05/2022] [Indexed: 06/16/2023]
Abstract
BACKGROUND The clinical utility of late gadolinium enhancement (LGE) cardiac MRI is limited by the lack of standardization, and time-consuming postprocessing. In this work, we tested the hypothesis that a cascaded deep learning pipeline trained with augmentation by synthetically generated data would improve model accuracy and robustness for automated scar quantification. METHODS A cascaded pipeline consisting of three consecutive neural networks is proposed, starting with a bounding box regression network to identify a region of interest around the left ventricular (LV) myocardium. Two further nnU-Net models are then used to segment the myocardium and, if present, scar. The models were trained on the data from the EMIDEC challenge, supplemented with an extensive synthetic dataset generated with a conditional GAN. RESULTS The cascaded pipeline significantly outperformed a single nnU-Net directly segmenting both the myocardium (mean Dice similarity coefficient (DSC) (standard deviation (SD)): 0.84 (0.09) vs 0.63 (0.20), p < 0.01) and scar (DSC: 0.72 (0.34) vs 0.46 (0.39), p < 0.01) on a per-slice level. The inclusion of the synthetic data as data augmentation during training improved the scar segmentation DSC by 0.06 (p < 0.01). The mean DSC per-subject on the challenge test set, for the cascaded pipeline augmented by synthetic generated data, was 0.86 (0.03) and 0.67 (0.29) for myocardium and scar, respectively. CONCLUSION A cascaded deep learning-based pipeline trained with augmentation by synthetically generated data leads to myocardium and scar segmentations that are similar to the manual operator, and outperforms direct segmentation without the synthetic images.
Collapse
Affiliation(s)
- Didier R P R M Lustermans
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands.
| | - Sina Amirrajab
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Mitko Veta
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Marcel Breeuwer
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands; Department of MR R&D - Clinical Science, Philips Healthcare, Best, the Netherlands
| | - Cian M Scannell
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands; School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom.
| |
Collapse
|
31
|
Velasco C, Fletcher TJ, Botnar RM, Prieto C. Artificial intelligence in cardiac magnetic resonance fingerprinting. Front Cardiovasc Med 2022; 9:1009131. [PMID: 36204566 PMCID: PMC9530662 DOI: 10.3389/fcvm.2022.1009131] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Accepted: 08/30/2022] [Indexed: 11/13/2022] Open
Abstract
Magnetic resonance fingerprinting (MRF) is a fast MRI-based technique that allows for multiparametric quantitative characterization of the tissues of interest in a single acquisition. In particular, it has gained attention in the field of cardiac imaging due to its ability to provide simultaneous and co-registered myocardial T1 and T2 mapping in a single breath-held cardiac MRF scan, in addition to other parameters. Initial results in small healthy subject groups and clinical studies have demonstrated the feasibility and potential of MRF imaging. Ongoing research is being conducted to improve the accuracy, efficiency, and robustness of cardiac MRF. However, these improvements usually increase the complexity of image reconstruction and dictionary generation and introduce the need for sequence optimization. Each of these steps increase the computational demand and processing time of MRF. The latest advances in artificial intelligence (AI), including progress in deep learning and the development of neural networks for MRI, now present an opportunity to efficiently address these issues. Artificial intelligence can be used to optimize candidate sequences and reduce the memory demand and computational time required for reconstruction and post-processing. Recently, proposed machine learning-based approaches have been shown to reduce dictionary generation and reconstruction times by several orders of magnitude. Such applications of AI should help to remove these bottlenecks and speed up cardiac MRF, improving its practical utility and allowing for its potential inclusion in clinical routine. This review aims to summarize the latest developments in artificial intelligence applied to cardiac MRF. Particularly, we focus on the application of machine learning at different steps of the MRF process, such as sequence optimization, dictionary generation and image reconstruction.
Collapse
Affiliation(s)
- Carlos Velasco
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- *Correspondence: Carlos Velasco
| | - Thomas J. Fletcher
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - René M. Botnar
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Institute for Biological and Medical Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile
- Millennium Institute for Intelligent Healthcare Engineering, Santiago, Chile
| | - Claudia Prieto
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Institute for Biological and Medical Engineering, Pontificia Universidad Católica de Chile, Santiago, Chile
- Millennium Institute for Intelligent Healthcare Engineering, Santiago, Chile
| |
Collapse
|
32
|
Aikawa T, Oyama-Manabe N. Editorial for "Comparison of DeepStrain and Feature Tracking for Cardiac MRI Strain Analysis". J Magn Reson Imaging 2022; 57:1516-1517. [PMID: 36017874 DOI: 10.1002/jmri.28394] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/14/2022] [Accepted: 06/16/2022] [Indexed: 11/12/2022] Open
Affiliation(s)
- Tadao Aikawa
- Department of Radiology, Jichi Medical University Saitama Medical Center, Saitama, Japan.,Department of Cardiology, Hokkaido Cardiovascular Hospital, Sapporo, Japan
| | - Noriko Oyama-Manabe
- Department of Radiology, Jichi Medical University Saitama Medical Center, Saitama, Japan
| |
Collapse
|
33
|
Backhaus SJ, Aldehayat H, Kowallick JT, Evertz R, Lange T, Kutty S, Bigalke B, Gutberlet M, Hasenfuß G, Thiele H, Stiermaier T, Eitel I, Schuster A. Artificial intelligence fully automated myocardial strain quantification for risk stratification following acute myocardial infarction. Sci Rep 2022; 12:12220. [PMID: 35851282 PMCID: PMC9293901 DOI: 10.1038/s41598-022-16228-w] [Citation(s) in RCA: 7] [Impact Index Per Article: 3.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/15/2022] [Accepted: 07/06/2022] [Indexed: 11/09/2022] Open
Abstract
Feasibility of automated volume-derived cardiac functional evaluation has successfully been demonstrated using cardiovascular magnetic resonance (CMR) imaging. Notwithstanding, strain assessment has proven incremental value for cardiovascular risk stratification. Since introduction of deformation imaging to clinical practice has been complicated by time-consuming post-processing, we sought to investigate automation respectively. CMR data (n = 1095 patients) from two prospectively recruited acute myocardial infarction (AMI) populations with ST-elevation (STEMI) (AIDA STEMI n = 759) and non-STEMI (TATORT-NSTEMI n = 336) were analysed fully automated and manually on conventional cine sequences. LV function assessment included global longitudinal, circumferential, and radial strains (GLS/GCS/GRS). Agreements were assessed between automated and manual strain assessments. The former were assessed for major adverse cardiac event (MACE) prediction within 12 months following AMI. Manually and automated derived GLS showed the best and excellent agreement with an intraclass correlation coefficient (ICC) of 0.81. Agreement was good for GCS and poor for GRS. Amongst automated analyses, GLS (HR 1.12, 95% CI 1.08-1.16, p < 0.001) and GCS (HR 1.07, 95% CI 1.05-1.10, p < 0.001) best predicted MACE with similar diagnostic accuracy compared to manual analyses; area under the curve (AUC) for GLS (auto 0.691 vs. manual 0.693, p = 0.801) and GCS (auto 0.668 vs. manual 0.686, p = 0.425). Amongst automated functional analyses, GLS was the only independent predictor of MACE in multivariate analyses (HR 1.10, 95% CI 1.04-1.15, p < 0.001). Considering high agreement of automated GLS and equally high accuracy for risk prediction compared to the reference standard of manual analyses, automation may improve efficiency and aid in clinical routine implementation.Trial registration: ClinicalTrials.gov, NCT00712101 and NCT01612312.
Collapse
Affiliation(s)
- Sören J Backhaus
- Department of Cardiology and Pneumology, University Medical Centre, Georg-August-University Göttingen, Robert-Koch-Str. 40, 37099, Göttingen, Germany.,German Center for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, Germany
| | - Haneen Aldehayat
- Department of Cardiology and Pneumology, University Medical Centre, Georg-August-University Göttingen, Robert-Koch-Str. 40, 37099, Göttingen, Germany
| | - Johannes T Kowallick
- German Center for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, Germany.,University Medical Center Göttingen, Institute for Diagnostic and Interventional Radiology, Georg-August University, Göttingen, Germany
| | - Ruben Evertz
- Department of Cardiology and Pneumology, University Medical Centre, Georg-August-University Göttingen, Robert-Koch-Str. 40, 37099, Göttingen, Germany.,German Center for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, Germany
| | - Torben Lange
- Department of Cardiology and Pneumology, University Medical Centre, Georg-August-University Göttingen, Robert-Koch-Str. 40, 37099, Göttingen, Germany.,German Center for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, Germany
| | - Shelby Kutty
- Helen B. Taussig Heart Center, The Johns Hopkins Hospital and School of Medicine, Baltimore, MD, USA
| | - Boris Bigalke
- Department of Cardiology, Charité Campus Benjamin Franklin, University Medical Center Berlin, Berlin, Germany
| | - Matthias Gutberlet
- Institute of Diagnostic and Interventional Radiology, Heart Center Leipzig at University of Leipzig, Leipzig, Germany
| | - Gerd Hasenfuß
- Department of Cardiology and Pneumology, University Medical Centre, Georg-August-University Göttingen, Robert-Koch-Str. 40, 37099, Göttingen, Germany
| | - Holger Thiele
- Department of Internal Medicine/Cardiology, Heart Center Leipzig at University of Leipzig, Leipzig, Germany
| | - Thomas Stiermaier
- University Heart Center Lübeck, Medical Clinic II (Cardiology/Angiology/Intensive Care Medicine), University Hospital Schleswig-Holstein, Lübeck, Germany.,German Center for Cardiovascular Research (DZHK), Partner Site Hamburg/Kiel/Lübeck, Lübeck, Germany
| | - Ingo Eitel
- University Heart Center Lübeck, Medical Clinic II (Cardiology/Angiology/Intensive Care Medicine), University Hospital Schleswig-Holstein, Lübeck, Germany.,German Center for Cardiovascular Research (DZHK), Partner Site Hamburg/Kiel/Lübeck, Lübeck, Germany
| | - Andreas Schuster
- Department of Cardiology and Pneumology, University Medical Centre, Georg-August-University Göttingen, Robert-Koch-Str. 40, 37099, Göttingen, Germany. .,German Center for Cardiovascular Research (DZHK), Partner Site Göttingen, Göttingen, Germany.
| |
Collapse
|
34
|
Guo F, Ng M, Kuling G, Wright G. Cardiac MRI segmentation with sparse annotations: Ensembling deep learning uncertainty and shape priors. Med Image Anal 2022; 81:102532. [PMID: 35872359 DOI: 10.1016/j.media.2022.102532] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/30/2021] [Revised: 06/07/2022] [Accepted: 07/07/2022] [Indexed: 10/17/2022]
Abstract
The performance of deep learning for cardiac magnetic resonance imaging (MRI) segmentation is oftentimes degraded when using small datasets and sparse annotations for training or adapting a pre-trained model to previously unseen datasets. Here, we developed and evaluated an approach to addressing some of these issues to facilitate broader use of deep learning for short-axis cardiac MRI segmentation. We developed a globally optimal label fusion (GOLF) algorithm that enforced spatial smoothness to generate consensus segmentation from segmentation predictions provided by a deep learning ensemble algorithm. The GOLF consensus was entered into an uncertainty-guided coupled continuous kernel cut (ugCCKC) algorithm that employed normalized cut, image-grid continuous regularization, and "nesting" and circular shape priors of the left ventricular myocardium (LVM) and cavity (LVC). In addition, the uncertainty measurements derived from the segmentation predictions were used to constrain the similarity of GOLF and final segmentation. We optimized ugCCKC through upper bound relaxation, for which we developed an efficient coupled continuous max-flow algorithm implemented in an iterative manner. We showed that GOLF yielded average symmetric surface distance (ASSD) 0.2-0.8 mm lower than an averaging method with higher or similar Dice similarity coefficient (DSC). We also demonstrated that ugCCKC incorporating the shape priors improved DSC by 0.01-0.05 and reduced ASSD by 0.1-0.9 mm. In addition, we integrated GOLF and ugCCKC into a deep learning ensemble algorithm by refining the segmentation of an unannotated dataset and using the refined segmentation to update the trained models. With the proposed framework, we demonstrated the capability of using relatively small datasets (5-10 subjects) with sparse (5-25% slices labeled) annotations to train a deep learning algorithm, while achieving DSC of 0.871-0.893 for LVM and 0.933-0.959 for LVC on the LVQuan dataset, and these were 0.844-0.871 for LVM and 0.923-0.931 for LVC on the ACDC dataset. Furthermore, we showed that the proposed approach can be adapted to substantially alleviate the domain shift issue. Moreover, we calculated a number of commonly used LV function measurements using the derived segmentation and observed strong correlations (Pearson r=0.77-1.00, p<0.001) between algorithm and manual LV function analyses. These results suggest that the developed approaches can be used to facilitate broader application of deep learning in research and clinical cardiac MR imaging workflow.
Collapse
Affiliation(s)
- Fumin Guo
- Wuhan National Laboratory for Optoelectronics, Biomedical Engineering, Huazhong University of Science and Technology, Wuhan, China; Department of Medical Biophysics, University of Toronto, Toronto, Canada; Sunnybrook Research Institute, University of Toronto, Toronto, Canada.
| | - Matthew Ng
- Department of Medical Biophysics, University of Toronto, Toronto, Canada; Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Grey Kuling
- Department of Medical Biophysics, University of Toronto, Toronto, Canada; Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| | - Graham Wright
- Department of Medical Biophysics, University of Toronto, Toronto, Canada; Sunnybrook Research Institute, University of Toronto, Toronto, Canada
| |
Collapse
|
35
|
Abstract
In this digital era, artificial intelligence (AI) is establishing a strong foothold in commercial industry and the field of technology. These effects are trickling into the healthcare industry, especially in the clinical arena of cardiology. Machine learning (ML) algorithms are making substantial progress in various subspecialties of cardiology. This will have a positive impact on patient care and move the field towards precision medicine. In this review article, we explore the progress of ML in cardiovascular imaging, electrophysiology, heart failure, and interventional cardiology.
Collapse
|
36
|
Fernández-Llaneza D, Gondová A, Vince H, Patra A, Zurek M, Konings P, Kagelid P, Hultin L. Towards fully automated segmentation of rat cardiac MRI by leveraging deep learning frameworks. Sci Rep 2022; 12:9193. [PMID: 35654902 PMCID: PMC9163082 DOI: 10.1038/s41598-022-12378-z] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/08/2021] [Accepted: 04/26/2022] [Indexed: 11/19/2022] Open
Abstract
Automated segmentation of human cardiac magnetic resonance datasets has been steadily improving during recent years. Similar applications would be highly useful to improve and speed up the studies of cardiac function in rodents in the preclinical context. However, the transfer of such segmentation methods to the preclinical research is compounded by the limited number of datasets and lower image resolution. In this paper we present a successful application of deep architectures 3D cardiac segmentation for rats in preclinical contexts which to our knowledge has not yet been reported. We developed segmentation models that expand on the standard U-Net architecture and evaluated models separately trained for systole and diastole phases (2MSA) and a single model trained for all phases (1MSA). Furthermore, we calibrated model outputs using a Gaussian process (GP)-based prior to improve phase selection. The resulting models approach human performance in terms of left ventricular segmentation quality and ejection fraction (EF) estimation in both 1MSA and 2MSA settings (Sørensen-Dice score 0.91 ± 0.072 and 0.93 ± 0.032, respectively). 2MSA achieved a mean absolute difference between estimated and reference EF of 3.5 ± 2.5%, while 1MSA resulted in 4.1 ± 3.0%. Applying GPs to 1MSA enabled automating systole and diastole phase selection. Both segmentation approaches (1MSA and 2MSA) were statistically equivalent. Combined with a proposed cardiac phase selection strategy, our work presents an important first step towards a fully automated segmentation pipeline in the context of rat cardiac analysis.
Collapse
Affiliation(s)
- Daniel Fernández-Llaneza
- Clinical Pharmacology and Safety Sciences, Biopharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Mölndal, SE, Sweden.
| | - Andrea Gondová
- Clinical Pharmacology and Safety Sciences, Biopharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Mölndal, SE, Sweden
| | - Harris Vince
- Clinical Pharmacology and Safety Sciences, Biopharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Mölndal, SE, Sweden
| | - Arijit Patra
- Clinical Pharmacology and Safety Sciences, Biopharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Mölndal, SE, Sweden
| | - Magdalena Zurek
- Clinical Pharmacology and Safety Sciences, Biopharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Mölndal, SE, Sweden
| | - Peter Konings
- Data Sciences and Quantitative Biology, Discovery Sciences, Biopharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Mölndal, SE, Sweden
| | - Patrik Kagelid
- Clinical Pharmacology and Safety Sciences, Biopharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Mölndal, SE, Sweden
| | - Leif Hultin
- Clinical Pharmacology and Safety Sciences, Biopharmaceuticals R&D, AstraZeneca, Pepparedsleden 1, 431 83, Mölndal, SE, Sweden
| |
Collapse
|
37
|
Truong VT, Nguyen BP, Nguyen-Vo TH, Mazur W, Chung ES, Palmer C, Tretter JT, Alsaied T, Pham VT, Do HQ, Do PTN, Pham VN, Ha BN, Chau HN, Le TK. Application of machine learning in screening for congenital heart diseases using fetal echocardiography. THE INTERNATIONAL JOURNAL OF CARDIOVASCULAR IMAGING 2022; 38:1007-1015. [PMID: 35192082 DOI: 10.1007/s10554-022-02566-3] [Citation(s) in RCA: 10] [Impact Index Per Article: 5.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Subscribe] [Scholar Register] [Received: 10/11/2021] [Accepted: 02/13/2022] [Indexed: 11/05/2022]
Abstract
There is a growing body of literature supporting the utilization of machine learning (ML) to improve diagnosis and prognosis tools of cardiovascular disease. The current study was to investigate the impact that the ML framework may have on the sensitivity of predicting the presence or absence of congenital heart disease (CHD) using fetal echocardiography. A comprehensive fetal echocardiogram including 2D cardiac chamber quantification, valvar assessments, assessment of great vessel morphology, and Doppler-derived blood flow interrogation was recorded. The postnatal echocardiogram was used to ascertain the diagnosis of CHD. A random forest (RF) algorithm with a nested tenfold cross-validation was used to train models for assessing the presence of CHD. The study population was derived from a database of 3910 singleton fetuses with maternal age of 28.8 ± 5.2 years and gestational age at the time of fetal echocardiography of 22.0 weeks (IQR 21-24). The proportion of CHD was 14.1% for the studied cohort confirmed by post-natal echocardiograms. Our proposed RF-based framework provided a sensitivity of 0.85, a specificity of 0.88, a positive predictive value of 0.55 and a negative predictive value of 0.97 to detect the CHD with the mean of mean ROC curves of 0.94 and the mean of mean PR curves of 0.84. Additionally, six first features, including cardiac axis, peak velocity of blood flow across the pulmonic valve, cardiothoracic ratio, pulmonary valvar annulus diameter, right ventricular end-diastolic diameter, and aortic valvar annulus diameter, are essential features that play crucial roles in adding more predictive values to the model in detecting patients with CHD. ML using RF can provide increased sensitivity in prenatal CHD screening with very good performance. The incorporation of ML algorithms into fetal echocardiography may further standardize the assessment for CHD.
Collapse
Affiliation(s)
- Vien T Truong
- The Christ Hospital Health Network, Cincinnati, OH, USA
- The Lindner Research Center, Cincinnati, OH, USA
| | - Binh P Nguyen
- School of Mathematics and Statistics, Victoria University of Wellington, Wellington, New Zealand
| | - Thanh-Hoang Nguyen-Vo
- School of Mathematics and Statistics, Victoria University of Wellington, Wellington, New Zealand
| | | | | | | | - Justin T Tretter
- Cincinnati Children's Hospital Medical Center, University of Cincinnati, College of Medicine, Cincinnati, OH, USA
| | - Tarek Alsaied
- Cincinnati Children's Hospital Medical Center, University of Cincinnati, College of Medicine, Cincinnati, OH, USA
| | - Vy T Pham
- Washington University School of Medicine in St. Louis, St. Louis, MO, USA
| | - Huan Q Do
- Heart Institute of HCMC, Ho Chi Minh City, Vietnam
| | | | - Vinh N Pham
- Heart Center, Tam Anh General Hospital, Ho Chi Minh City, Vietnam
| | - Ban N Ha
- Heart Institute of HCMC, Ho Chi Minh City, Vietnam
| | - Hoa N Chau
- University of Medicine and Pharmacy, Ho Chi Minh City, Vietnam
| | - Tuyen K Le
- Heart Institute of HCMC, Ho Chi Minh City, Vietnam.
| |
Collapse
|
38
|
From Accuracy to Reliability and Robustness in Cardiac Magnetic Resonance Image Segmentation: A Review. APPLIED SCIENCES-BASEL 2022. [DOI: 10.3390/app12083936] [Citation(s) in RCA: 5] [Impact Index Per Article: 2.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 01/03/2023]
Abstract
Since the rise of deep learning (DL) in the mid-2010s, cardiac magnetic resonance (CMR) image segmentation has achieved state-of-the-art performance. Despite achieving inter-observer variability in terms of different accuracy performance measures, visual inspections reveal errors in most segmentation results, indicating a lack of reliability and robustness of DL segmentation models, which can be critical if a model was to be deployed into clinical practice. In this work, we aim to bring attention to reliability and robustness, two unmet needs of cardiac image segmentation methods, which are hampering their translation into practice. To this end, we first study the performance accuracy evolution of CMR segmentation, illustrate the improvements brought by DL algorithms and highlight the symptoms of performance stagnation. Afterwards, we provide formal definitions of reliability and robustness. Based on the two definitions, we identify the factors that limit the reliability and robustness of state-of-the-art deep learning CMR segmentation techniques. Finally, we give an overview of the current set of works that focus on improving the reliability and robustness of CMR segmentation, and we categorize them into two families of methods: quality control methods and model improvement techniques. The first category corresponds to simpler strategies that only aim to flag situations where a model may be incurring poor reliability or robustness. The second one, instead, directly tackles the problem by bringing improvements into different aspects of the CMR segmentation model development process. We aim to bring the attention of more researchers towards these emerging trends regarding the development of reliable and robust CMR segmentation frameworks, which can guarantee the safe use of DL in clinical routines and studies.
Collapse
|
39
|
Alandejani F, Alabed S, Garg P, Goh ZM, Karunasaagarar K, Sharkey M, Salehi M, Aldabbagh Z, Dwivedi K, Mamalakis M, Metherall P, Uthoff J, Johns C, Rothman A, Condliffe R, Hameed A, Charalampoplous A, Lu H, Plein S, Greenwood JP, Lawrie A, Wild JM, de Koning PJH, Kiely DG, Van Der Geest R, Swift AJ. Training and clinical testing of artificial intelligence derived right atrial cardiovascular magnetic resonance measurements. J Cardiovasc Magn Reson 2022; 24:25. [PMID: 35387651 PMCID: PMC8988415 DOI: 10.1186/s12968-022-00855-3] [Citation(s) in RCA: 3] [Impact Index Per Article: 1.5] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/15/2021] [Accepted: 03/19/2022] [Indexed: 12/29/2022] Open
Abstract
BACKGROUND Right atrial (RA) area predicts mortality in patients with pulmonary hypertension, and is recommended by the European Society of Cardiology/European Respiratory Society pulmonary hypertension guidelines. The advent of deep learning may allow more reliable measurement of RA areas to improve clinical assessments. The aim of this study was to automate cardiovascular magnetic resonance (CMR) RA area measurements and evaluate the clinical utility by assessing repeatability, correlation with invasive haemodynamics and prognostic value. METHODS A deep learning RA area CMR contouring model was trained in a multicentre cohort of 365 patients with pulmonary hypertension, left ventricular pathology and healthy subjects. Inter-study repeatability (intraclass correlation coefficient (ICC)) and agreement of contours (DICE similarity coefficient (DSC)) were assessed in a prospective cohort (n = 36). Clinical testing and mortality prediction was performed in n = 400 patients that were not used in the training nor prospective cohort, and the correlation of automatic and manual RA measurements with invasive haemodynamics assessed in n = 212/400. Radiologist quality control (QC) was performed in the ASPIRE registry, n = 3795 patients. The primary QC observer evaluated all the segmentations and recorded them as satisfactory, suboptimal or failure. A second QC observer analysed a random subcohort to assess QC agreement (n = 1018). RESULTS All deep learning RA measurements showed higher interstudy repeatability (ICC 0.91 to 0.95) compared to manual RA measurements (1st observer ICC 0.82 to 0.88, 2nd observer ICC 0.88 to 0.91). DSC showed high agreement comparing automatic artificial intelligence and manual CMR readers. Maximal RA area mean and standard deviation (SD) DSC metric for observer 1 vs observer 2, automatic measurements vs observer 1 and automatic measurements vs observer 2 is 92.4 ± 3.5 cm2, 91.2 ± 4.5 cm2 and 93.2 ± 3.2 cm2, respectively. Minimal RA area mean and SD DSC metric for observer 1 vs observer 2, automatic measurements vs observer 1 and automatic measurements vs observer 2 was 89.8 ± 3.9 cm2, 87.0 ± 5.8 cm2 and 91.8 ± 4.8 cm2. Automatic RA area measurements all showed moderate correlation with invasive parameters (r = 0.45 to 0.66), manual (r = 0.36 to 0.57). Maximal RA area could accurately predict elevated mean RA pressure low and high-risk thresholds (area under the receiver operating characteristic curve artificial intelligence = 0.82/0.87 vs manual = 0.78/0.83), and predicted mortality similar to manual measurements, both p < 0.01. In the QC evaluation, artificial intelligence segmentations were suboptimal at 108/3795 and a low failure rate of 16/3795. In a subcohort (n = 1018), agreement by two QC observers was excellent, kappa 0.84. CONCLUSION Automatic artificial intelligence CMR derived RA size and function are accurate, have excellent repeatability, moderate associations with invasive haemodynamics and predict mortality.
Collapse
Affiliation(s)
- Faisal Alandejani
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Samer Alabed
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
- INSIGNEO, Institute for In Silico Medicine, University of Sheffield, Sheffield, UK
| | - Pankaj Garg
- Norwich Medical School, University of East Anglia, Norwich, UK
| | - Ze Ming Goh
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Kavita Karunasaagarar
- Radiology Department, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK
| | - Michael Sharkey
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
- Radiology Department, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK
| | - Mahan Salehi
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Ziad Aldabbagh
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Krit Dwivedi
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Michail Mamalakis
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Pete Metherall
- Radiology Department, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK
| | - Johanna Uthoff
- Department of Computer Science, University of Sheffield, Sheffield, UK
| | - Chris Johns
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Alexander Rothman
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
- INSIGNEO, Institute for In Silico Medicine, University of Sheffield, Sheffield, UK
- Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK
| | - Robin Condliffe
- Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK
| | - Abdul Hameed
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
- Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK
| | - Athanasios Charalampoplous
- Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK
| | - Haiping Lu
- INSIGNEO, Institute for In Silico Medicine, University of Sheffield, Sheffield, UK
- Department of Computer Science, University of Sheffield, Sheffield, UK
| | - Sven Plein
- Multidisciplinary Cardiovascular Research Centre (MCRC) &, Biomedical Imaging Science Department, Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Clarendon Way, Leeds, UK
| | - John P Greenwood
- Multidisciplinary Cardiovascular Research Centre (MCRC) &, Biomedical Imaging Science Department, Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Clarendon Way, Leeds, UK
| | - Allan Lawrie
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
| | - Jim M Wild
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
- INSIGNEO, Institute for In Silico Medicine, University of Sheffield, Sheffield, UK
| | - Patrick J H de Koning
- Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, Netherlands
| | - David G Kiely
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK
- INSIGNEO, Institute for In Silico Medicine, University of Sheffield, Sheffield, UK
- Sheffield Pulmonary Vascular Disease Unit, Royal Hallamshire Hospital, Sheffield Teaching Hospitals NHS Foundation Trust, Sheffield, UK
| | - Rob Van Der Geest
- Division of Image Processing, Department of Radiology, Leiden University Medical Center, Leiden, Netherlands
| | - Andrew J Swift
- Department of Infection, Immunity and Cardiovascular Disease, University of Sheffield, Sheffield, UK.
- INSIGNEO, Institute for In Silico Medicine, University of Sheffield, Sheffield, UK.
| |
Collapse
|
40
|
Puyol-Antón E, Ruijsink B, Mariscal Harana J, Piechnik SK, Neubauer S, Petersen SE, Razavi R, Chowienczyk P, King AP. Fairness in Cardiac Magnetic Resonance Imaging: Assessing Sex and Racial Bias in Deep Learning-Based Segmentation. Front Cardiovasc Med 2022; 9:859310. [PMID: 35463778 PMCID: PMC9021445 DOI: 10.3389/fcvm.2022.859310] [Citation(s) in RCA: 19] [Impact Index Per Article: 9.5] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Journal Information] [Subscribe] [Scholar Register] [Received: 01/21/2022] [Accepted: 03/02/2022] [Indexed: 12/12/2022] Open
Abstract
Background Artificial intelligence (AI) techniques have been proposed for automation of cine CMR segmentation for functional quantification. However, in other applications AI models have been shown to have potential for sex and/or racial bias. The objective of this paper is to perform the first analysis of sex/racial bias in AI-based cine CMR segmentation using a large-scale database. Methods A state-of-the-art deep learning (DL) model was used for automatic segmentation of both ventricles and the myocardium from cine short-axis CMR. The dataset consisted of end-diastole and end-systole short-axis cine CMR images of 5,903 subjects from the UK Biobank database (61.5 ± 7.1 years, 52% male, 81% white). To assess sex and racial bias, we compared Dice scores and errors in measurements of biventricular volumes and function between patients grouped by race and sex. To investigate whether segmentation bias could be explained by potential confounders, a multivariate linear regression and ANCOVA were performed. Results Results on the overall population showed an excellent agreement between the manual and automatic segmentations. We found statistically significant differences in Dice scores between races (white ∼94% vs. minority ethnic groups 86-89%) as well as in absolute/relative errors in volumetric and functional measures, showing that the AI model was biased against minority racial groups, even after correction for possible confounders. The results of a multivariate linear regression analysis showed that no covariate could explain the Dice score bias between racial groups. However, for the Mixed and Black race groups, sex showed a weak positive association with the Dice score. The results of an ANCOVA analysis showed that race was the main factor that can explain the overall difference in Dice scores between racial groups. Conclusion We have shown that racial bias can exist in DL-based cine CMR segmentation models when training with a database that is sex-balanced but not race-balanced such as the UK Biobank.
Collapse
Affiliation(s)
- Esther Puyol-Antón
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom
| | - Bram Ruijsink
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom
- Department of Adult and Paediatric Cardiology, Guy’s and St Thomas’ NHS Foundation Trust, London, United Kingdom
- Division of Heart and Lungs, Department of Cardiology, University Medical Centre Utrecht, Utrecht, Netherlands
| | - Jorge Mariscal Harana
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom
| | - Stefan K. Piechnik
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, United Kingdom
| | - Stefan Neubauer
- Division of Cardiovascular Medicine, Radcliffe Department of Medicine, University of Oxford, Oxford, United Kingdom
| | - Steffen E. Petersen
- National Institute for Health Research (NIHR) Barts Biomedical Research Centre, William Harvey Research Institute, Queen Mary University London, London, United Kingdom
- Barts Heart Centre, St Bartholomew’s Hospital, Barts Health NHS Trust, London, United Kingdom
- Health Data Research UK, London, United Kingdom
- Alan Turing Institute, London, United Kingdom
| | - Reza Razavi
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom
- Department of Adult and Paediatric Cardiology, Guy’s and St Thomas’ NHS Foundation Trust, London, United Kingdom
| | - Phil Chowienczyk
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom
- British Heart Foundation Centre, King’s College London, London, United Kingdom
| | - Andrew P. King
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom
| |
Collapse
|
41
|
Ismail TF, Strugnell W, Coletti C, Božić-Iven M, Weingärtner S, Hammernik K, Correia T, Küstner T. Cardiac MR: From Theory to Practice. Front Cardiovasc Med 2022; 9:826283. [PMID: 35310962 PMCID: PMC8927633 DOI: 10.3389/fcvm.2022.826283] [Citation(s) in RCA: 12] [Impact Index Per Article: 6.0] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/30/2021] [Accepted: 01/17/2022] [Indexed: 01/10/2023] Open
Abstract
Cardiovascular disease (CVD) is the leading single cause of morbidity and mortality, causing over 17. 9 million deaths worldwide per year with associated costs of over $800 billion. Improving prevention, diagnosis, and treatment of CVD is therefore a global priority. Cardiovascular magnetic resonance (CMR) has emerged as a clinically important technique for the assessment of cardiovascular anatomy, function, perfusion, and viability. However, diversity and complexity of imaging, reconstruction and analysis methods pose some limitations to the widespread use of CMR. Especially in view of recent developments in the field of machine learning that provide novel solutions to address existing problems, it is necessary to bridge the gap between the clinical and scientific communities. This review covers five essential aspects of CMR to provide a comprehensive overview ranging from CVDs to CMR pulse sequence design, acquisition protocols, motion handling, image reconstruction and quantitative analysis of the obtained data. (1) The basic MR physics of CMR is introduced. Basic pulse sequence building blocks that are commonly used in CMR imaging are presented. Sequences containing these building blocks are formed for parametric mapping and functional imaging techniques. Commonly perceived artifacts and potential countermeasures are discussed for these methods. (2) CMR methods for identifying CVDs are illustrated. Basic anatomy and functional processes are described to understand the cardiac pathologies and how they can be captured by CMR imaging. (3) The planning and conduct of a complete CMR exam which is targeted for the respective pathology is shown. Building blocks are illustrated to create an efficient and patient-centered workflow. Further strategies to cope with challenging patients are discussed. (4) Imaging acceleration and reconstruction techniques are presented that enable acquisition of spatial, temporal, and parametric dynamics of the cardiac cycle. The handling of respiratory and cardiac motion strategies as well as their integration into the reconstruction processes is showcased. (5) Recent advances on deep learning-based reconstructions for this purpose are summarized. Furthermore, an overview of novel deep learning image segmentation and analysis methods is provided with a focus on automatic, fast and reliable extraction of biomarkers and parameters of clinical relevance.
Collapse
Affiliation(s)
- Tevfik F. Ismail
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Cardiology Department, Guy's and St Thomas' Hospital, London, United Kingdom
| | - Wendy Strugnell
- Queensland X-Ray, Mater Hospital Brisbane, Brisbane, QLD, Australia
| | - Chiara Coletti
- Magnetic Resonance Systems Lab, Delft University of Technology, Delft, Netherlands
| | - Maša Božić-Iven
- Magnetic Resonance Systems Lab, Delft University of Technology, Delft, Netherlands
- Computer Assisted Clinical Medicine, Heidelberg University, Mannheim, Germany
| | | | - Kerstin Hammernik
- Lab for AI in Medicine, Technical University of Munich, Munich, Germany
- Department of Computing, Imperial College London, London, United Kingdom
| | - Teresa Correia
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Centre of Marine Sciences, Faro, Portugal
| | - Thomas Küstner
- Medical Image and Data Analysis (MIDAS.lab), Department of Diagnostic and Interventional Radiology, University Hospital of Tübingen, Tübingen, Germany
| |
Collapse
|
42
|
Sengupta PP, Chandrashekhar Y. Imaging With Deep Learning: Sharpening the Cutting Edge. JACC Cardiovasc Imaging 2022; 15:547-549. [PMID: 35272811 DOI: 10.1016/j.jcmg.2022.02.001] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/24/2022]
|
43
|
Juarez-Orozco LE, Klén R, Niemi M, Ruijsink B, Daquarti G, van Es R, Benjamins JW, Yeung MW, van der Harst P, Knuuti J. Artificial Intelligence to Improve Risk Prediction with Nuclear Cardiac Studies. Curr Cardiol Rep 2022; 24:307-316. [PMID: 35171443 PMCID: PMC8852880 DOI: 10.1007/s11886-022-01649-w] [Citation(s) in RCA: 2] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Accepted: 12/17/2021] [Indexed: 12/28/2022]
Abstract
Purpose of Review As machine learning-based artificial intelligence (AI) continues to revolutionize the way in which we analyze data, the field of nuclear cardiology provides fertile ground for the implementation of these complex analytics. This review summarizes and discusses the principles regarding nuclear cardiology techniques and AI, and the current evidence regarding its performance and contribution to the improvement of risk prediction in cardiovascular disease. Recent Findings and Summary There is a growing body of evidence on the experimentation with and implementation of machine learning-based AI on nuclear cardiology studies both concerning SPECT and PET technology for the improvement of risk-of-disease (classification of disease) and risk-of-events (prediction of adverse events) estimations. These publications still report objective divergence in methods either utilizing statistical machine learning approaches or deep learning with varying architectures, dataset sizes, and performance. Recent efforts have been placed into bringing standardization and quality to the experimentation and application of machine learning-based AI in cardiovascular imaging to generate standards in data harmonization and analysis through AI. Machine learning-based AI offers the possibility to improve risk evaluation in cardiovascular disease through its implementation on cardiac nuclear studies. Graphical Abstract AI in improving risk evaluation in nuclear cardiology. * Based on the 2019 ESC guidelines ![]()
Collapse
Affiliation(s)
- Luis Eduardo Juarez-Orozco
- Department of Cardiology, Division Heart & Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands.,Turku PET Centre, University of Turku and Turku University Hospital, Kiinamyllynkatu 4-8, 20520, Turku, Finland.,Department of Cardiology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Riku Klén
- Turku PET Centre, University of Turku and Turku University Hospital, Kiinamyllynkatu 4-8, 20520, Turku, Finland
| | - Mikael Niemi
- Turku PET Centre, University of Turku and Turku University Hospital, Kiinamyllynkatu 4-8, 20520, Turku, Finland
| | - Bram Ruijsink
- Department of Cardiology, Division Heart & Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands.,Division of Imaging Sciences and Biomedical Engineering, King's College London, St Thomas' Hospital, London, UK
| | - Gustavo Daquarti
- Department of Artificial Intelligence, UMA-Health, Buenos Aires, Argentina
| | - Rene van Es
- Department of Cardiology, Division Heart & Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands
| | - Jan-Walter Benjamins
- Department of Cardiology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Ming Wai Yeung
- Department of Cardiology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Pim van der Harst
- Department of Cardiology, Division Heart & Lungs, University Medical Center Utrecht, Utrecht University, Utrecht, the Netherlands.,Department of Cardiology, University of Groningen, University Medical Center Groningen, Groningen, The Netherlands
| | - Juhani Knuuti
- Turku PET Centre, University of Turku and Turku University Hospital, Kiinamyllynkatu 4-8, 20520, Turku, Finland.
| |
Collapse
|
44
|
Assessment of Bi-Ventricular and Bi-Atrial Areas Using Four-Chamber Cine Cardiovascular Magnetic Resonance Imaging: Fully Automated Segmentation with a U-Net Convolutional Neural Network. INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH 2022; 19:ijerph19031401. [PMID: 35162424 PMCID: PMC8834677 DOI: 10.3390/ijerph19031401] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Received: 12/26/2021] [Revised: 01/18/2022] [Accepted: 01/26/2022] [Indexed: 02/04/2023]
Abstract
Four-chamber (4CH) cine cardiovascular magnetic resonance imaging (CMR) facilitates simultaneous evaluation of cardiac chambers; however, manual segmentation is time-consuming and subjective in practice. We evaluated deep learning based on a U-Net convolutional neural network (CNN) for fully automated segmentation of the four cardiac chambers using 4CH cine CMR. Cine CMR datasets from patients were randomly assigned for training (1400 images from 70 patients), validation (600 images from 30 patients), and testing (1000 images from 50 patients). We validated manual and automated segmentation based on the U-Net CNN using the dice similarity coefficient (DSC) and Spearman’s rank correlation coefficient (ρ); p < 0.05 was statistically significant. The overall median DSC showed high similarity (0.89). Automated segmentation correlated strongly with manual segmentation in all chambers—the left and right ventricles, and the left and right atria (end-diastolic area: ρ = 0.88, 0.76, 0.92, and 0.87; end-systolic area: ρ = 0.81, 0.81, 0.92, and 0.83, respectively; p < 0.01). The area under the curve for the left ventricle, left atrium, right ventricle, and right atrium showed high scores (0.96, 0.99, 0.88, and 0.96, respectively). Fully automated segmentation could facilitate simultaneous evaluation and detection of enlargement of the four cardiac chambers without any time-consuming analysis.
Collapse
|
45
|
Fotaki A, Puyol-Antón E, Chiribiri A, Botnar R, Pushparajah K, Prieto C. Artificial Intelligence in Cardiac MRI: Is Clinical Adoption Forthcoming? Front Cardiovasc Med 2022; 8:818765. [PMID: 35083303 PMCID: PMC8785419 DOI: 10.3389/fcvm.2021.818765] [Citation(s) in RCA: 9] [Impact Index Per Article: 4.5] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/19/2021] [Accepted: 12/15/2021] [Indexed: 12/24/2022] Open
Abstract
Artificial intelligence (AI) refers to the area of knowledge that develops computerised models to perform tasks that typically require human intelligence. These algorithms are programmed to learn and identify patterns from "training data," that can be subsequently applied to new datasets, without being explicitly programmed to do so. AI is revolutionising the field of medical imaging and in particular of Cardiovascular Magnetic Resonance (CMR) by providing deep learning solutions for image acquisition, reconstruction and analysis, ultimately supporting the clinical decision making. Numerous methods have been developed over recent years to enhance and expedite CMR data acquisition, image reconstruction, post-processing and analysis; along with the development of promising AI-based biomarkers for a wide spectrum of cardiac conditions. The exponential rise in the availability and complexity of CMR data has fostered the development of different AI models. Integration in clinical routine in a meaningful way remains a challenge. Currently, innovations in this field are still mostly presented in proof-of-concept studies with emphasis on the engineering solutions; often recruiting small patient cohorts or relying on standardised databases such as Multi-ethnic Study on atherosclerosis (MESA), UK Biobank and others. The wider incorporation of clinically valid endpoints such as symptoms, survival, need and response to treatment remains to be seen. This review briefly summarises the current principles of AI employed in CMR and explores the relevant prospective observational studies in cardiology patient cohorts. It provides an overview of clinical studies employing undersampled reconstruction techniques to speed up the scan encompassing cine imaging, whole-heart imaging, multi-parametric mapping and magnetic resonance fingerprinting along with the clinical utility of AI applications in image post-processing, and analysis. Specific focus is given to studies that have incorporated CMR-derived prediction models for prognostication in cardiac disease. It also discusses current limitations and proposes potential developments to enable multi-disciplinary collaboration for improved evidence-based medicine. AI is an extremely promising field and the timely integration of clinician's input in the ingenious technical investigator's paradigm holds promise for a bright future in the medical field.
Collapse
Affiliation(s)
- Anastasia Fotaki
- Department of Biomedical Engineering, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom
| | - Esther Puyol-Antón
- Department of Biomedical Engineering, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Amedeo Chiribiri
- Department of Biomedical Engineering, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom
| | - René Botnar
- Department of Biomedical Engineering, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Escuela de Ingeniería, Pontificia Universidad Católica de Chile, Santiago, Chile
| | - Kuberan Pushparajah
- Department of Biomedical Engineering, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Guy's and St. Thomas' NHS Foundation Trust, London, United Kingdom
| | - Claudia Prieto
- Department of Biomedical Engineering, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Escuela de Ingeniería, Pontificia Universidad Católica de Chile, Santiago, Chile
| |
Collapse
|
46
|
Taylor AM. The role of artificial intelligence in paediatric cardiovascular magnetic resonance imaging. Pediatr Radiol 2022; 52:2131-2138. [PMID: 34936019 PMCID: PMC9537201 DOI: 10.1007/s00247-021-05218-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 05/05/2021] [Revised: 08/13/2021] [Accepted: 10/05/2021] [Indexed: 11/24/2022]
Abstract
Artificial intelligence (AI) offers the potential to change many aspects of paediatric cardiac imaging. At present, there are only a few clinically validated examples of AI applications in this field. This review focuses on the use of AI in paediatric cardiovascular MRI, using examples from paediatric cardiovascular MRI, adult cardiovascular MRI and other radiologic experience.
Collapse
Affiliation(s)
- Andrew M. Taylor
- Great Ormond Street Hospital for Children, Zayed Centre for Research, 20 Guildford St., Room 3.7, London, WC1N 1DZ UK ,Cardiovascular Imaging, UCL Institute of Cardiovascular Science, London, UK
| |
Collapse
|
47
|
Asher C, Puyol-Antón E, Rizvi M, Ruijsink B, Chiribiri A, Razavi R, Carr-White G. The Role of AI in Characterizing the DCM Phenotype. Front Cardiovasc Med 2021; 8:787614. [PMID: 34993240 PMCID: PMC8724536 DOI: 10.3389/fcvm.2021.787614] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 10/01/2021] [Accepted: 12/02/2021] [Indexed: 12/13/2022] Open
Abstract
Dilated Cardiomyopathy is conventionally defined by left ventricular dilatation and dysfunction in the absence of coronary disease. Emerging evidence suggests many patients remain vulnerable to major adverse outcomes despite clear therapeutic success of modern evidence-based heart failure therapy. In this era of personalized medical care, the conventional assessment of left ventricular ejection fraction falls short in fully predicting evolution and risk of outcomes in this heterogenous group of heart muscle disease, as such, a more refined means of phenotyping this disease appears essential. Cardiac MRI (CMR) is well-placed in this respect, not only for its diagnostic utility, but the wealth of information captured in global and regional function assessment with the addition of unique tissue characterization across different disease states and patient cohorts. Advanced tools are needed to leverage these sensitive metrics and integrate with clinical, genetic and biochemical information for personalized, and more clinically useful characterization of the dilated cardiomyopathy phenotype. Recent advances in artificial intelligence offers the unique opportunity to impact clinical decision making through enhanced precision image-analysis tasks, multi-source extraction of relevant features and seamless integration to enhance understanding, improve diagnosis, and subsequently clinical outcomes. Focusing particularly on deep learning, a subfield of artificial intelligence, that has garnered significant interest in the imaging community, this paper reviews the main developments that could offer more robust disease characterization and risk stratification in the Dilated Cardiomyopathy phenotype. Given its promising utility in the non-invasive assessment of cardiac diseases, we firstly highlight the key applications in CMR, set to enable comprehensive quantitative measures of function beyond the standard of care assessment. Concurrently, we revisit the added value of tissue characterization techniques for risk stratification, showcasing the deep learning platforms that overcome limitations in current clinical workflows and discuss how they could be utilized to better differentiate at-risk subgroups of this phenotype. The final section of this paper is dedicated to the allied clinical applications to imaging, that incorporate artificial intelligence and have harnessed the comprehensive abundance of data from genetics and relevant clinical variables to facilitate better classification and enable enhanced risk prediction for relevant outcomes.
Collapse
Affiliation(s)
- Clint Asher
- Department of Cardiovascular Imaging, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Department of Cardiology, Guys and St Thomas' NHS Trust, London, United Kingdom
| | - Esther Puyol-Antón
- Department of Cardiovascular Imaging, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Maleeha Rizvi
- Department of Cardiovascular Imaging, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Department of Cardiology, Guys and St Thomas' NHS Trust, London, United Kingdom
| | - Bram Ruijsink
- Department of Cardiovascular Imaging, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Department of Cardiology, Guys and St Thomas' NHS Trust, London, United Kingdom
- Division of Heart and Lungs, Department of Cardiology, University Medical Center Utrecht, Utrecht, Netherlands
| | - Amedeo Chiribiri
- Department of Cardiovascular Imaging, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Department of Cardiology, Guys and St Thomas' NHS Trust, London, United Kingdom
| | - Reza Razavi
- Department of Cardiovascular Imaging, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Department of Cardiology, Guys and St Thomas' NHS Trust, London, United Kingdom
| | - Gerry Carr-White
- Department of Cardiovascular Imaging, School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Department of Cardiology, Guys and St Thomas' NHS Trust, London, United Kingdom
| |
Collapse
|
48
|
Infante T, Cavaliere C, Punzo B, Grimaldi V, Salvatore M, Napoli C. Radiogenomics and Artificial Intelligence Approaches Applied to Cardiac Computed Tomography Angiography and Cardiac Magnetic Resonance for Precision Medicine in Coronary Heart Disease: A Systematic Review. Circ Cardiovasc Imaging 2021; 14:1133-1146. [PMID: 34915726 DOI: 10.1161/circimaging.121.013025] [Citation(s) in RCA: 14] [Impact Index Per Article: 4.7] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 12/21/2022]
Abstract
The risk of coronary heart disease (CHD) clinical manifestations and patient management is estimated according to risk scores accounting multifactorial risk factors, thus failing to cover the individual cardiovascular risk. Technological improvements in the field of medical imaging, in particular, in cardiac computed tomography angiography and cardiac magnetic resonance protocols, laid the development of radiogenomics. Radiogenomics aims to integrate a huge number of imaging features and molecular profiles to identify optimal radiomic/biomarker signatures. In addition, supervised and unsupervised artificial intelligence algorithms have the potential to combine different layers of data (imaging parameters and features, clinical variables and biomarkers) and elaborate complex and specific CHD risk models allowing more accurate diagnosis and reliable prognosis prediction. Literature from the past 5 years was systematically collected from PubMed and Scopus databases, and 60 studies were selected. We speculated the applicability of radiogenomics and artificial intelligence through the application of machine learning algorithms to identify CHD and characterize atherosclerotic lesions and myocardial abnormalities. Radiomic features extracted by cardiac computed tomography angiography and cardiac magnetic resonance showed good diagnostic accuracy for the identification of coronary plaques and myocardium structure; on the other hand, few studies exploited radiogenomics integration, thus suggesting further research efforts in this field. Cardiac computed tomography angiography resulted the most used noninvasive imaging modality for artificial intelligence applications. Several studies provided high performance for CHD diagnosis, classification, and prognostic assessment even though several efforts are still needed to validate and standardize algorithms for CHD patient routine according to good medical practice.
Collapse
Affiliation(s)
- Teresa Infante
- Department of Advanced Medical and Surgical Sciences (DAMSS), University of Campania "Luigi Vanvitelli", Naples, Italy (T.I., C.N.)
| | | | - Bruna Punzo
- IRCCS SDN, Naples, Italy (C.C., B.P., V.G., M.S., C.N.)
| | | | | | - Claudio Napoli
- Department of Advanced Medical and Surgical Sciences (DAMSS), University of Campania "Luigi Vanvitelli", Naples, Italy (T.I., C.N.).,IRCCS SDN, Naples, Italy (C.C., B.P., V.G., M.S., C.N.)
| |
Collapse
|
49
|
Shaw LJ, Chandrashekhar Y. What Is of Recent Interest in Cardiac Imaging?: Insights From the JACC Family of Journals. J Am Coll Cardiol 2021; 78:2387-2391. [PMID: 34857099 PMCID: PMC8629342 DOI: 10.1016/j.jacc.2021.10.029] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 10/25/2022]
|
50
|
Building Confidence in AI-Interpreted CMR. JACC Cardiovasc Imaging 2021; 15:428-430. [PMID: 34922861 DOI: 10.1016/j.jcmg.2021.10.008] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/12/2021] [Accepted: 10/14/2021] [Indexed: 11/23/2022]
|