1
|
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
|
2
|
Uslu F. GSM-Net: A global sequence modelling network for the segmentation of short axis CINE MRI images. Comput Med Imaging Graph 2023; 108:102266. [PMID: 37385047 DOI: 10.1016/j.compmedimag.2023.102266] [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: 01/09/2023] [Revised: 05/04/2023] [Accepted: 06/11/2023] [Indexed: 07/01/2023]
Abstract
Atrial Fibrillation (AF) is a disease where the atria fail to properly contract but quiver instead, due to the abnormal electrical activity of the atrial tissue. In AF patients, anatomical and functional parameters of the left atrium (LA) largely differ from that of healthy people due to LA remodelling, which can continue in many cases after the catheter ablation treatment. Therefore, it is important to follow up with AF patients to detect any recurrence. LA segmentation masks obtained from short-axis CINE MRI images are used as the gold standard for the quantification of LA parameters. Thick slices of CINE MRI images hinder the use of 3D networks for segmentation while 2D architectures often fail to model inter-slice dependencies. This study presents GSM-Net which approximates 3D networks with effective modelling of inter-slice similarities with two new modules: global slice sequence encoder (GSSE) and sequence dependent channel attention module (SdCAt). In contrast to previous work modelling only local inter-slice similarities, GSSE also models global spatial dependencies across slices. SdCAt generates a distribution of attention weights over MRI slices per channel, to better trace characteristic changes in the size of the LA or other structures across slices. We found that GSM-Net outperforms previous methods on LA segmentation and helps to identify AF recurrence patients. We believe that GSM-Net can be used as an automatic tool to estimate LA parameters such as ejection fraction to identify AF, and to follow up with patients after treatment to detect any recurrence.
Collapse
Affiliation(s)
- Fatmatülzehra Uslu
- Bursa Technical University, Electrical and Electronics Engineering Department, Bursa, 16310, Türkiye.
| |
Collapse
|
3
|
Kazi A, Betko S, Salvi A, Menon PG. Automatic Segmentation of the Left Atrium from Computed Tomography Angiography Images. Ann Biomed Eng 2023:10.1007/s10439-023-03170-9. [PMID: 36890303 DOI: 10.1007/s10439-023-03170-9] [Citation(s) in RCA: 1] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [Abstract] [Key Words] [Journal Information] [Subscribe] [Scholar Register] [Received: 08/01/2022] [Accepted: 02/15/2023] [Indexed: 03/10/2023]
Abstract
The left atrial appendage (LAA) causes 91% of thrombi in atrial fibrillation patients, a potential harbinger of stroke. Leveraging computed tomography angiography (CTA) images, radiologists interpret the left atrium (LA) and LAA geometries to stratify stroke risk. Nevertheless, accurate LA segmentation remains a time-consuming task with high inter-observer variability. Binary masks of the LA and their corresponding CTA images were used to train and test a 3D U-Net to automate LA segmentation. One model was trained using the entire unified-image-volume while a second model was trained on regional patch-volumes which were run for inference and then assimilated back into the full volume. The unified-image-volume U-Net achieved median DSCs of 0.92 and 0.88 for the train and test sets, respectively; the patch-volume U-Net achieved median DSCs of 0.90 and 0.89 for the train and test sets, respectively. This indicates that the unified-image-volume and patch-volume U-Net models captured up to 88 and 89% of the LA/LAA boundary's regional complexity, respectively. Additionally, the results indicate that the LA/LAA were fully captured in most of the predicted segmentations. By automating the segmentation process, our deep learning model can expedite LA/LAA shape, informing stratification of stroke risk.
Collapse
Affiliation(s)
- Amaan Kazi
- University of Pittsburgh, 302 Benedum Hall, 3700 O'Hara Street, Pittsburgh, PA, 15213, USA.,ImageRx, Pittsburgh, PA, USA
| | - Sage Betko
- Statistics & Machine Learning, Carnegie Mellon University, Pittsburgh, PA, USA.,ImageRx, Pittsburgh, PA, USA
| | - Anish Salvi
- University of Pittsburgh, 302 Benedum Hall, 3700 O'Hara Street, Pittsburgh, PA, 15213, USA.,ImageRx, Pittsburgh, PA, USA
| | - Prahlad G Menon
- University of Pittsburgh, 302 Benedum Hall, 3700 O'Hara Street, Pittsburgh, PA, 15213, USA. .,ImageRx, Pittsburgh, PA, USA.
| |
Collapse
|
4
|
Chen J, Zhang J, Debattista K, Han J. Semi-Supervised Unpaired Medical Image Segmentation Through Task-Affinity Consistency. IEEE TRANSACTIONS ON MEDICAL IMAGING 2023; 42:594-605. [PMID: 36219664 DOI: 10.1109/tmi.2022.3213372] [Citation(s) in RCA: 2] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/16/2023]
Abstract
Deep learning-based semi-supervised learning (SSL) algorithms are promising in reducing the cost of manual annotation of clinicians by using unlabelled data, when developing medical image segmentation tools. However, to date, most existing semi-supervised learning (SSL) algorithms treat the labelled images and unlabelled images separately and ignore the explicit connection between them; this disregards essential shared information and thus hinders further performance improvements. To mine the shared information between the labelled and unlabelled images, we introduce a class-specific representation extraction approach, in which a task-affinity module is specifically designed for representation extraction. We further cast the representation into two different views of feature maps; one is focusing on low-level context, while the other concentrates on structural information. The two views of feature maps are incorporated into the task-affinity module, which then extracts the class-specific representations to aid the knowledge transfer from the labelled images to the unlabelled images. In particular, a task-affinity consistency loss between the labelled images and unlabelled images based on the multi-scale class-specific representations is formulated, leading to a significant performance improvement. Experimental results on three datasets show that our method consistently outperforms existing state-of-the-art methods. Our findings highlight the potential of consistency between class-specific knowledge for semi-supervised medical image segmentation. The code and models are to be made publicly available at https://github.com/jingkunchen/TAC.
Collapse
|
5
|
Bhan A, Mangipudi PS, Goyal A. Left atrium MRI image segmentation using efficient Xception stochastic depth based generative adversarial network. INTERNATIONAL JOURNAL OF HEALTHCARE MANAGEMENT 2023. [DOI: 10.1080/20479700.2023.2166206] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/23/2023]
Affiliation(s)
- Anupama Bhan
- Department of Electronics and Communication Engineering, Amity School of Engineering and Technology, Amity University, Noida, India
| | - Partha Sarathi Mangipudi
- Department of Computer Science and Engineering, Amity School of Engineering and Technology, Amity University, Noida, India
| | - Ayush Goyal
- Department of Electrical Engineering and Computer Science, Frank H. Dotterweich College of Engineering, Texas A&M University – Kingsville, Kingsville, TX, USA
| |
Collapse
|
6
|
Peters DC, Lamy J, Sinusas AJ, Baldassarre LA. Left atrial evaluation by cardiovascular magnetic resonance: sensitive and unique biomarkers. Eur Heart J Cardiovasc Imaging 2021; 23:14-30. [PMID: 34718484 DOI: 10.1093/ehjci/jeab221] [Citation(s) in RCA: 6] [Impact Index Per Article: 2.0] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/03/2021] [Accepted: 10/12/2021] [Indexed: 12/12/2022] Open
Abstract
Left atrial (LA) imaging is still not routinely used for diagnosis and risk stratification, although recent studies have emphasized its importance as an imaging biomarker. Cardiovascular magnetic resonance is able to evaluate LA structure and function, metrics that serve as early indicators of disease, and provide prognostic information, e.g. regarding diastolic dysfunction, and atrial fibrillation (AF). MR angiography defines atrial anatomy, useful for planning ablation procedures, and also for characterizing atrial shapes and sizes that might predict cardiovascular events, e.g. stroke. Long-axis cine images can be evaluated to define minimum, maximum, and pre-atrial contraction LA volumes, and ejection fractions (EFs). More modern feature tracking of these cine images provides longitudinal LA strain through the cardiac cycle, and strain rates. Strain may be a more sensitive marker than EF and can predict post-operative AF, AF recurrence after ablation, outcomes in hypertrophic cardiomyopathy, stratification of diastolic dysfunction, and strain correlates with atrial fibrosis. Using high-resolution late gadolinium enhancement (LGE), the extent of fibrosis in the LA can be estimated and post-ablation scar can be evaluated. The LA LGE method is widely available, its reproducibility is good, and validations with voltage-mapping exist, although further scan-rescan studies are needed, and consensus regarding atrial segmentation is lacking. Using LGE, scar patterns after ablation in AF subjects can be reproducibly defined. Evaluation of 'pre-existent' atrial fibrosis may have roles in predicting AF recurrence after ablation, predicting new-onset AF and diastolic dysfunction in patients without AF. LA imaging biomarkers are ready to enter into diagnostic clinical practice.
Collapse
Affiliation(s)
- Dana C Peters
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
| | - Jérôme Lamy
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, New Haven, CT, USA
| | - Albert J Sinusas
- Department of Cardiology, Yale School of Medicine, New Haven, CT, USA
| | | |
Collapse
|
7
|
Gonzales RA, Seemann F, Lamy J, Mojibian H, Atar D, Erlinge D, Steding-Ehrenborg K, Arheden H, Hu C, Onofrey JA, Peters DC, Heiberg E. MVnet: automated time-resolved tracking of the mitral valve plane in CMR long-axis cine images with residual neural networks: a multi-center, multi-vendor study. J Cardiovasc Magn Reson 2021; 23:137. [PMID: 34857009 PMCID: PMC8638514 DOI: 10.1186/s12968-021-00824-2] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/22/2021] [Accepted: 10/20/2021] [Indexed: 11/24/2022] Open
Abstract
BACKGROUND Mitral annular plane systolic excursion (MAPSE) and left ventricular (LV) early diastolic velocity (e') are key metrics of systolic and diastolic function, but not often measured by cardiovascular magnetic resonance (CMR). Its derivation is possible with manual, precise annotation of the mitral valve (MV) insertion points along the cardiac cycle in both two and four-chamber long-axis cines, but this process is highly time-consuming, laborious, and prone to errors. A fully automated, consistent, fast, and accurate method for MV plane tracking is lacking. In this study, we propose MVnet, a deep learning approach for MV point localization and tracking capable of deriving such clinical metrics comparable to human expert-level performance, and validated it in a multi-vendor, multi-center clinical population. METHODS The proposed pipeline first performs a coarse MV point annotation in a given cine accurately enough to apply an automated linear transformation task, which standardizes the size, cropping, resolution, and heart orientation, and second, tracks the MV points with high accuracy. The model was trained and evaluated on 38,854 cine images from 703 patients with diverse cardiovascular conditions, scanned on equipment from 3 main vendors, 16 centers, and 7 countries, and manually annotated by 10 observers. Agreement was assessed by the intra-class correlation coefficient (ICC) for both clinical metrics and by the distance error in the MV plane displacement. For inter-observer variability analysis, an additional pair of observers performed manual annotations in a randomly chosen set of 50 patients. RESULTS MVnet achieved a fast segmentation (<1 s/cine) with excellent ICCs of 0.94 (MAPSE) and 0.93 (LV e') and a MV plane tracking error of -0.10 ± 0.97 mm. In a similar manner, the inter-observer variability analysis yielded ICCs of 0.95 and 0.89 and a tracking error of -0.15 ± 1.18 mm, respectively. CONCLUSION A dual-stage deep learning approach for automated annotation of MV points for systolic and diastolic evaluation in CMR long-axis cine images was developed. The method is able to carefully track these points with high accuracy and in a timely manner. This will improve the feasibility of CMR methods which rely on valve tracking and increase their utility in a clinical setting.
Collapse
Affiliation(s)
- Ricardo A. Gonzales
- Clinical Physiology, Department of Clinical Sciences, Lund University, Skåne University Hospital, Lund, Sweden
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, Yale University, New Haven, Connecticut United States of America
- Department of Electrical Engineering, Universidad de Ingeniería y Tecnología, Lima, Peru
| | - Felicia Seemann
- Clinical Physiology, Department of Clinical Sciences, Lund University, Skåne University Hospital, Lund, Sweden
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, Yale University, New Haven, Connecticut United States of America
- Department of Biomedical Engineering, Lund University, Lund, Sweden
| | - Jérôme Lamy
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, Yale University, New Haven, Connecticut United States of America
| | - Hamid Mojibian
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, Yale University, New Haven, Connecticut United States of America
| | - Dan Atar
- Department of Cardiology B, Oslo University Hospital Ullevål and Faculty of Medicine, University of Oslo, Oslo, Norway
| | - David Erlinge
- Department of Cardiology, Clinical Sciences, Lund University, Skåne University Hospital, Lund, Sweden
| | - Katarina Steding-Ehrenborg
- Clinical Physiology, Department of Clinical Sciences, Lund University, Skåne University Hospital, Lund, Sweden
| | - Håkan Arheden
- Clinical Physiology, Department of Clinical Sciences, Lund University, Skåne University Hospital, Lund, Sweden
| | - Chenxi Hu
- School of Biomedical Engineering, Shanghai Jiao Tong University, Shanghai, China
| | - John A. Onofrey
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, Yale University, New Haven, Connecticut United States of America
- Department of Urology, Yale School of Medicine, Yale University, New Haven, Connecticut United States of America
- Department of Biomedical Engineering, Yale University, New Haven, Connecticut United States of America
| | - Dana C. Peters
- Department of Radiology and Biomedical Imaging, Yale School of Medicine, Yale University, New Haven, Connecticut United States of America
| | - Einar Heiberg
- Clinical Physiology, Department of Clinical Sciences, Lund University, Skåne University Hospital, Lund, Sweden
- Department of Biomedical Engineering, Lund University, Lund, Sweden
- Wallenberg Center for Molecular Medicine, Lund University, Lund, Sweden
| |
Collapse
|