1
|
Jaspers TJM, Martens B, Crawley R, Jada L, Amirrajab S, Breeuwer M, Holtackers RJ, Chiribiri A, Scannell CM. Deep Learning Synthesis of White-Blood From Dark-Blood Late Gadolinium Enhancement Cardiac Magnetic Resonance. Invest Radiol 2024:00004424-990000000-00213. [PMID: 38687025 DOI: 10.1097/rli.0000000000001086] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 05/02/2024]
Abstract
OBJECTIVES Dark-blood late gadolinium enhancement (DB-LGE) cardiac magnetic resonance has been proposed as an alternative to standard white-blood LGE (WB-LGE) imaging protocols to enhance scar-to-blood contrast without compromising scar-to-myocardium contrast. In practice, both DB and WB contrasts may have clinical utility, but acquiring both has the drawback of additional acquisition time. The aim of this study was to develop and evaluate a deep learning method to generate synthetic WB-LGE images from DB-LGE, allowing the assessment of both contrasts without additional scan time. MATERIALS AND METHODS DB-LGE and WB-LGE data from 215 patients were used to train 2 types of unpaired image-to-image translation deep learning models, cycle-consistent generative adversarial network (CycleGAN) and contrastive unpaired translation, with 5 different loss function hyperparameter settings each. Initially, the best hyperparameter setting was determined for each model type based on the Fréchet inception distance and the visual assessment of expert readers. Then, the CycleGAN and contrastive unpaired translation models with the optimal hyperparameters were directly compared. Finally, with the best model chosen, the quantification of scar based on the synthetic WB-LGE images was compared with the truly acquired WB-LGE. RESULTS The CycleGAN architecture for unpaired image-to-image translation was found to provide the most realistic synthetic WB-LGE images from DB-LGE images. The results showed that it was difficult for visual readers to distinguish if an image was true or synthetic (55% correctly classified). In addition, scar burden quantification with the synthetic data was highly correlated with the analysis of the truly acquired images. Bland-Altman analysis found a mean bias in percentage scar burden between the quantification of the real WB and synthetic white-blood images of 0.44% with limits of agreement from -10.85% to 11.74%. The mean image quality of the real WB images (3.53/5) was scored higher than the synthetic white-blood images (3.03), P = 0.009. CONCLUSIONS This study proposed a CycleGAN model to generate synthetic WB-LGE from DB-LGE images to allow assessment of both image contrasts without additional scan time. This work represents a clinically focused assessment of synthetic medical images generated by artificial intelligence, a topic with significant potential for a multitude of applications. However, further evaluation is warranted before clinical adoption.
Collapse
Affiliation(s)
- Tim J M Jaspers
- From the Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands (T.J.M.J., S.A., M.B., C.M.S.); School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom (T.J.M.J., R.C., L.J., R.J.H., A.C., C.M.S.); Department of Electrical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands (T.J.M.J.); Cardiovascular Research Institute Maastricht, Maastricht University, Maastricht, the Netherlands (B.M., R.J.H.); and Department of Radiology and Nuclear Medicine, Maastricht University Medical Centre, Maastricht, the Netherlands (B.M., R.J.H.)
| | | | | | | | | | | | | | | | | |
Collapse
|
2
|
Alskaf E, Crawley R, Scannell CM, Suinesiaputra A, Young A, Masci PG, Perera D, Chiribiri A. Hybrid artificial intelligence outcome prediction using features extraction from stress perfusion cardiac magnetic resonance images and electronic health records. J Med Artif Intell 2024; 7:3. [PMID: 38584766 PMCID: PMC7615812 DOI: 10.21037/jmai-24-1] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 04/09/2024]
Abstract
Background Prediction of clinical outcomes in coronary artery disease (CAD) has been conventionally achieved using clinical risk factors. The relationship between imaging features and outcome is still not well understood. This study aims to use artificial intelligence to link image features with mortality outcome. Methods A retrospective study was performed on patients who had stress perfusion cardiac magnetic resonance (SP-CMR) between 2011 and 2021. The endpoint was all-cause mortality. Convolutional neural network (CNN) was used to extract features from stress perfusion images, and multilayer perceptron (MLP) to extract features from electronic health records (EHRs), both networks were concatenated in a hybrid neural network (HNN) to predict study endpoint. Image CNN was trained to predict study endpoint directly from images. HNN and image CNN were compared with a linear clinical model using area under the curve (AUC), F1 scores, and McNemar's test. Results Total of 1,286 cases were identified, with 201 death events (16%). The clinical model had good performance (AUC =80%, F1 score =37%). Best Image CNN model showed AUC =72% and F1 score =38%. HNN outperformed the other two models (AUC =82%, F1 score =43%). McNemar's test showed statistical difference between image CNN and both clinical model (P<0.01) and HNN (P<0.01). There was no significant difference between HNN and clinical model (P=0.15). Conclusions Death in patients with suspected or known CAD can be predicted directly from stress perfusion images without clinical knowledge. Prediction can be improved by HNN that combines clinical and SP-CMR images.
Collapse
Affiliation(s)
- Ebraham Alskaf
- School of Biomedical Engineering & Imaging Sciences, King’s College London, St Thomas’ Hospital, London, UK
| | - Richard Crawley
- School of Biomedical Engineering & Imaging Sciences, King’s College London, St Thomas’ Hospital, London, UK
| | - Cian M. Scannell
- School of Biomedical Engineering & Imaging Sciences, King’s College London, St Thomas’ Hospital, London, UK
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
| | - Avan Suinesiaputra
- School of Biomedical Engineering & Imaging Sciences, King’s College London, St Thomas’ Hospital, London, UK
| | - Alistair Young
- School of Biomedical Engineering & Imaging Sciences, King’s College London, St Thomas’ Hospital, London, UK
| | - Pier-Giorgio Masci
- School of Biomedical Engineering & Imaging Sciences, King’s College London, St Thomas’ Hospital, London, UK
| | - Divaka Perera
- School of Biomedical Engineering & Imaging Sciences, King’s College London, St Thomas’ Hospital, London, UK
| | - Amedeo Chiribiri
- School of Biomedical Engineering & Imaging Sciences, King’s College London, St Thomas’ Hospital, London, UK
| |
Collapse
|
3
|
Crawley R, Kunze KP, Milidonis X, Highton J, McElroy S, Frey SM, Hoefler D, Karamanli C, Wong NCK, Backhaus SJ, Alskaf E, Neji R, Scannell CM, Plein S, Chiribiri A. High-Resolution Free-Breathing Automated Quantitative Myocardial Perfusion by Cardiovascular Magnetic Resonance for the Detection of Functionally Significant Coronary Artery Disease. Eur Heart J Cardiovasc Imaging 2024:jeae084. [PMID: 38525948 DOI: 10.1093/ehjci/jeae084] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 12/12/2023] [Revised: 03/15/2024] [Accepted: 03/17/2024] [Indexed: 03/26/2024] Open
Abstract
AIMS Current assessment of myocardial ischaemia from stress perfusion cardiovascular magnetic resonance (SP-CMR) largely relies on visual interpretation. This study investigated the use of high-resolution free-breathing SP-CMR with automated quantitative mapping in the diagnosis of coronary artery disease (CAD). Diagnostic performance was evaluated against invasive coronary angiography (ICA) with fractional flow reserve (FFR) measurement. METHODS & RESULTS Seven-hundred and three patients were recruited for SP-CMR using the research sequence at 3 Tesla. Of those receiving ICA within 6 months, 80 patients either had FFR measurement, or identification of a chronic total occlusion (CTO) with inducible perfusion defects seen on SP-CMR. Myocardial blood flow (MBF) maps were automatically generated in-line on the scanner following image acquisition at hyperaemic stress and rest, allowing myocardial perfusion reserve (MPR) calculation. 75 coronary vessels assessed by FFR, and 28 vessels with CTO were evaluated at both segmental and coronary territory level. Coronary territory stress MBF and MPR were reduced in FFR-positive (≤ 0.80) regions (median stress MBF: 1.74 [0.90-2.17] ml/min/g; MPR: 1.67 [1.10-1.89]) compared with FFR-negative regions (stress MBF: 2.50 [2.15-2.95] ml/min/g; MPR 2.35 [2.06-2.54] p < 0.001 for both). Stress MBF ≤ 1.94 ml/min/g and MPR ≤ 1.97 accurately detected FFR-positive CAD on a per-vessel basis (area under the curve: 0.85 and 0.96 respectively; p < 0.001 for both). CONCLUSIONS A novel scanner-integrated high-resolution free-breathing SP-CMR sequence with automated in-line perfusion mapping is presented which accurately detects functionally significant CAD.
Collapse
Affiliation(s)
- R Crawley
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
| | - K P Kunze
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
- Magnetic Resonance Research Collaborations, Siemens Healthcare Limited, Camberley, United Kingdom
| | - X Milidonis
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
- DeepCamera MRG, CYENS Centre of Excellence, Nicosia, Cyprus
| | - J Highton
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
- Aival, London, United Kingdom
| | - S McElroy
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
- Magnetic Resonance Research Collaborations, Siemens Healthcare Limited, Camberley, United Kingdom
| | - S M Frey
- Department of Cardiology, University Hospital Basel, Basel, Switzerland
| | - D Hoefler
- University of Erlangen, Erlangen, Germany
| | - C Karamanli
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
| | - N C K Wong
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
| | - S J Backhaus
- Department of Cardiology, Campus Kerckhoff of the Justus-Liebig-University Giessen, Kerckhoff-Clinic, Bad Nauheim, Germany
| | - E Alskaf
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
| | - R Neji
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
| | - C M Scannell
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - S Plein
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
- Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Leeds, United Kingdom
| | - A Chiribiri
- School of Biomedical Engineering & Imaging Sciences, King's College London, United Kingdom
| |
Collapse
|
4
|
Xie C, Zhang R, Mensink S, Gandharva R, Awni M, Lim H, Kachel SE, Cheung E, Crawley R, Churilov L, Bettencourt N, Chiribiri A, Scannell CM, Lim RP. Automated inversion time selection for late gadolinium-enhanced cardiac magnetic resonance imaging. Eur Radiol 2024:10.1007/s00330-024-10630-w. [PMID: 38337070 DOI: 10.1007/s00330-024-10630-w] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 09/19/2023] [Revised: 01/16/2024] [Accepted: 01/18/2024] [Indexed: 02/12/2024]
Abstract
OBJECTIVES To develop and share a deep learning method that can accurately identify optimal inversion time (TI) from multi-vendor, multi-institutional and multi-field strength inversion scout (TI scout) sequences for late gadolinium enhancement cardiac MRI. MATERIALS AND METHODS Retrospective multicentre study conducted on 1136 1.5-T and 3-T cardiac MRI examinations from four centres and three scanner vendors. Deep learning models, comprising a convolutional neural network (CNN) that provides input to a long short-term memory (LSTM) network, were trained on TI scout pixel data from centres 1 to 3 to identify optimal TI, using ground truth annotations by two readers. Accuracy within 50 ms, mean absolute error (MAE), Lin's concordance coefficient (LCCC) and reduced major axis regression (RMAR) were used to select the best model from validation results, and applied to holdout test data. Robustness of the best-performing model was also tested on imaging data from centre 4. RESULTS The best model (SE-ResNet18-LSTM) produced accuracy of 96.1%, MAE 22.9 ms and LCCC 0.47 compared to ground truth on the holdout test set and accuracy of 97.3%, MAE 15.2 ms and LCCC 0.64 when tested on unseen external (centre 4) data. Differences in vendor performance were observed, with greatest accuracy for the most commonly represented vendor in the training data. CONCLUSION A deep learning model was developed that can identify optimal inversion time from TI scout images on multi-vendor data with high accuracy, including on previously unseen external data. We make this model available to the scientific community for further assessment or development. CLINICAL RELEVANCE STATEMENT A robust automated inversion time selection tool for late gadolinium-enhanced imaging allows for reproducible and efficient cross-vendor inversion time selection. KEY POINTS • A model comprising convolutional and recurrent neural networks was developed to extract optimal TI from TI scout images. • Model accuracy within 50 ms of ground truth on multi-vendor holdout and external data of 96.1% and 97.3% respectively was achieved. • This model could improve workflow efficiency and standardise optimal TI selection for consistent LGE imaging.
Collapse
Affiliation(s)
- Cheng Xie
- Melbourne Bioinnovation Student Initiative (MBSI), Parkville, VIC, Australia
- Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia
| | - Rory Zhang
- Melbourne Bioinnovation Student Initiative (MBSI), Parkville, VIC, Australia
- Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia
| | - Sebastian Mensink
- Melbourne Bioinnovation Student Initiative (MBSI), Parkville, VIC, Australia
- Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia
| | - Rahul Gandharva
- Melbourne Bioinnovation Student Initiative (MBSI), Parkville, VIC, Australia
- Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia
| | - Mustafa Awni
- Melbourne Bioinnovation Student Initiative (MBSI), Parkville, VIC, Australia
- Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia
| | - Hester Lim
- Melbourne Bioinnovation Student Initiative (MBSI), Parkville, VIC, Australia
- Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia
| | - Stefan E Kachel
- Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia
- Melbourne Medical School, The University of Melbourne, Parkville, VIC, Australia
| | - Ernest Cheung
- Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia
| | | | - Leonid Churilov
- Melbourne Medical School, The University of Melbourne, Parkville, VIC, Australia
| | | | | | - Cian M Scannell
- King's College London, Strand, London, UK
- Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Ruth P Lim
- Department of Radiology, Artificial Intelligence in Radiology Laboratory, Austin Health, 145 Studley Rd, Heidelberg, VIC, 3084, Australia.
- Melbourne Medical School, The University of Melbourne, Parkville, VIC, Australia.
| |
Collapse
|
5
|
Scannell CM, Crawley R, Alskaf E, Breeuwer M, Plein S, Chiribiri A. High-resolution quantification of stress perfusion defects by cardiac magnetic resonance. Eur Heart J Imaging Methods Pract 2024; 2:qyae001. [PMID: 38283662 PMCID: PMC10810243 DOI: 10.1093/ehjimp/qyae001] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 11/15/2023] [Accepted: 01/04/2024] [Indexed: 01/30/2024]
Abstract
Aims Quantitative stress perfusion cardiac magnetic resonance (CMR) is becoming more widely available, but it is still unclear how to integrate this information into clinical decision-making. Typically, pixel-wise perfusion maps are generated, but diagnostic and prognostic studies have summarized perfusion as just one value per patient or in 16 myocardial segments. In this study, the reporting of quantitative perfusion maps is extended from the standard 16 segments to a high-resolution bullseye. Cut-off thresholds are established for the high-resolution bullseye, and the identified perfusion defects are compared with visual assessment. Methods and results Thirty-four patients with known or suspected coronary artery disease were retrospectively analysed. Visual perfusion defects were contoured on the CMR images and pixel-wise quantitative perfusion maps were generated. Cut-off values were established on the high-resolution bullseye consisting of 1800 points and compared with the per-segment, per-coronary, and per-patient resolution thresholds. Quantitative stress perfusion was significantly lower in visually abnormal pixels, 1.11 (0.75-1.57) vs. 2.35 (1.82-2.9) mL/min/g (Mann-Whitney U test P < 0.001), with an optimal cut-off of 1.72 mL/min/g. This was lower than the segment-wise optimal threshold of 1.92 mL/min/g. The Bland-Altman analysis showed that visual assessment underestimated large perfusion defects compared with the quantification with good agreement for smaller defect burdens. A Dice overlap of 0.68 (0.57-0.78) was found. Conclusion This study introduces a high-resolution bullseye consisting of 1800 points, rather than 16, per patient for reporting quantitative stress perfusion, which may improve sensitivity. Using this representation, the threshold required to identify areas of reduced perfusion is lower than for segmental analysis.
Collapse
Affiliation(s)
- Cian M Scannell
- Department of Biomedical Engineering, Eindhoven University of Technology, Groene Loper 5, 5612 AEEindhoven, The Netherlands
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London SE1 7EH, UK
| | - Richard Crawley
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London SE1 7EH, UK
| | - Ebraham Alskaf
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London SE1 7EH, UK
| | - Marcel Breeuwer
- Department of Biomedical Engineering, Eindhoven University of Technology, Groene Loper 5, 5612 AEEindhoven, The Netherlands
| | - Sven Plein
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London SE1 7EH, UK
- Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Leeds LS2 9JT, UK
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London SE1 7EH, UK
| |
Collapse
|
6
|
Alskaf E, Frey SM, Scannell CM, Suinesiaputra A, Vilic D, Dinu V, Masci PG, Perera D, Young A, Chiribiri A. Machine learning outcome prediction using stress perfusion cardiac magnetic resonance reports and natural language processing of electronic health records. Inform Med Unlocked 2024; 44:101418. [PMID: 38173908 PMCID: PMC7615463 DOI: 10.1016/j.imu.2023.101418] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Key Words] [Grants] [Track Full Text] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 01/05/2024] Open
Affiliation(s)
- Ebraham Alskaf
- School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom
| | - Simon M. Frey
- School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom
- Department of Cardiology, University Hospital Basel, Basel, Switzerland
| | - Cian M. Scannell
- School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands
| | - Avan Suinesiaputra
- School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom
| | | | - Vlad Dinu
- King’s College London, United Kingdom
| | - Pier Giorgio Masci
- School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom
| | - Divaka Perera
- School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom
| | - Alistair Young
- School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom
| | - Amedeo Chiribiri
- School of Biomedical Engineering & Imaging Sciences, King’s College London, United Kingdom
| |
Collapse
|
7
|
Scannell CM, Alskaf E, Sharrack N, Razavi R, Ourselin S, Young AA, Plein S, Chiribiri A. AI-AIF: artificial intelligence-based arterial input function for quantitative stress perfusion cardiac magnetic resonance. Eur Heart J Digit Health 2023; 4:12-21. [PMID: 36743875 PMCID: PMC9890084 DOI: 10.1093/ehjdh/ztac074] [Citation(s) in RCA: 3] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Figures] [Subscribe] [Scholar Register] [Received: 08/16/2022] [Revised: 10/23/2022] [Indexed: 12/12/2022]
Abstract
Aims One of the major challenges in the quantification of myocardial blood flow (MBF) from stress perfusion cardiac magnetic resonance (CMR) is the estimation of the arterial input function (AIF). This is due to the non-linear relationship between the concentration of gadolinium and the MR signal, which leads to signal saturation. In this work, we show that a deep learning model can be trained to predict the unsaturated AIF from standard images, using the reference dual-sequence acquisition AIFs (DS-AIFs) for training. Methods and results A 1D U-Net was trained, to take the saturated AIF from the standard images as input and predict the unsaturated AIF, using the data from 201 patients from centre 1 and a test set comprised of both an independent cohort of consecutive patients from centre 1 and an external cohort of patients from centre 2 (n = 44). Fully-automated MBF was compared between the DS-AIF and AI-AIF methods using the Mann-Whitney U test and Bland-Altman analysis. There was no statistical difference between the MBF quantified with the DS-AIF [2.77 mL/min/g (1.08)] and predicted with the AI-AIF (2.79 mL/min/g (1.08), P = 0.33. Bland-Altman analysis shows minimal bias between the DS-AIF and AI-AIF methods for quantitative MBF (bias of -0.11 mL/min/g). Additionally, the MBF diagnosis classification of the AI-AIF matched the DS-AIF in 669/704 (95%) of myocardial segments. Conclusion Quantification of stress perfusion CMR is feasible with a single-sequence acquisition and a single contrast injection using an AI-based correction of the AIF.
Collapse
Affiliation(s)
- Cian M Scannell
- School of Biomedical Engineering & Imaging Sciences, King's College London, 4th Floor Lambeth Wing, St Thomas' Hospital, London SE1 7EH, UK.,Department of Biomedical Engineering, Eindhoven University of Technology, Gemini-Zuid, Groene Loper 5, 5612 Eindhoven, The Netherlands
| | - Ebraham Alskaf
- School of Biomedical Engineering & Imaging Sciences, King's College London, 4th Floor Lambeth Wing, St Thomas' Hospital, London SE1 7EH, UK
| | - Noor Sharrack
- Department of Biomedical Imaging Science, Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Clarendon Way, Leeds LS2 9JT, UK
| | - Reza Razavi
- School of Biomedical Engineering & Imaging Sciences, King's College London, 4th Floor Lambeth Wing, St Thomas' Hospital, London SE1 7EH, UK
| | - Sebastien Ourselin
- School of Biomedical Engineering & Imaging Sciences, King's College London, 4th Floor Lambeth Wing, St Thomas' Hospital, London SE1 7EH, UK
| | - Alistair A Young
- School of Biomedical Engineering & Imaging Sciences, King's College London, 4th Floor Lambeth Wing, St Thomas' Hospital, London SE1 7EH, UK
| | - Sven Plein
- School of Biomedical Engineering & Imaging Sciences, King's College London, 4th Floor Lambeth Wing, St Thomas' Hospital, London SE1 7EH, UK.,Department of Biomedical Imaging Science, Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Clarendon Way, Leeds LS2 9JT, UK
| | - Amedeo Chiribiri
- School of Biomedical Engineering & Imaging Sciences, King's College London, 4th Floor Lambeth Wing, St Thomas' Hospital, London SE1 7EH, UK
| |
Collapse
|
8
|
Alskaf E, Dutta U, Scannell CM, Chiribiri A. Deep learning applications in coronary anatomy imaging: a systematic review and meta-analysis. J Med Artif Intell 2022; 5:11. [PMID: 36861064 PMCID: PMC7614252 DOI: 10.21037/jmai-22-36] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Download PDF] [Figures] [Subscribe] [Scholar Register] [Indexed: 12/29/2022]
Abstract
Background The application of deep learning on medical imaging is growing in prevalence in the recent literature. One of the most studied areas is coronary artery disease (CAD). Imaging of coronary artery anatomy is fundamental, which has led to a high number of publications describing a variety of techniques. The aim of this systematic review is to review the evidence behind the accuracy of deep learning applications in coronary anatomy imaging. Methods The search for the relevant studies, which applied deep learning on coronary anatomy imaging, was performed in a systematic approach on MEDLINE and EMBASE databases, followed by reviewing of abstracts and full texts. The data from the final studies was retrieved using data extraction forms. A meta-analysis was performed on a subgroup of studies, which looked at fractional flow reserve (FFR) prediction. Heterogeneity was tested using tau2, I2 and Q tests. Finally, a risk of bias was performed using Quality Assessment of Diagnostic Accuracy Studies (QUADAS) approach. Results A total of 81 studies met the inclusion criteria. The most common imaging modality was coronary computed tomography angiography (CCTA) (58%) and the most common deep learning method was convolutional neural network (CNN) (52%). The majority of studies demonstrated good performance metrics. The most common outputs were focused on coronary artery segmentation, clinical outcome prediction, coronary calcium quantification and FFR prediction, and most studies reported area under the curve (AUC) of ≥80%. The pooled diagnostic odds ratio (DOR) derived from 8 studies looking at FFR prediction using CCTA was 12.5 using the Mantel-Haenszel (MH) method. There was no significant heterogeneity amongst studies according to Q test (P=0.2496). Conclusions Deep learning has been used in many applications on coronary anatomy imaging, most of which are yet to be externally validated and prepared for clinical use. The performance of deep learning, especially CNN models, proved to be powerful and some applications have already translated into medical practice, such as computed tomography (CT)-FFR. These applications have the potential to translate technology into better care of CAD patients.
Collapse
Affiliation(s)
- Ebraham Alskaf
- School of Biomedical Engineering & Imaging Sciences, King’s College London, London, UK
| | - Utkarsh Dutta
- GKT School of Medical Education, King’s College London, London, UK
| | - Cian M. Scannell
- School of Biomedical Engineering & Imaging Sciences, King’s College London, London, UK,Medical Image Analysis Group, Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, The Netherlands
| | - Amedeo Chiribiri
- School of Biomedical Engineering & Imaging Sciences, King’s College London, London, UK
| |
Collapse
|
9
|
Lustermans DRPRM, Amirrajab S, Veta M, Breeuwer M, Scannell CM. Optimized automated cardiac MR scar quantification with GAN-based data augmentation. Comput Methods Programs Biomed 2022; 226:107116. [PMID: 36148718 DOI: 10.1016/j.cmpb.2022.107116] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [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
|
10
|
Scannell CM, Alskaf E, Sharrack N, Plein S, Chribiri A. AI-AIF: artificial intelligence-based arterial input function correction for quantitative stress perfusion cardiac MRI. Eur Heart J Cardiovasc Imaging 2022. [DOI: 10.1093/ehjci/jeac141.013] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/12/2022] Open
Abstract
Abstract
Funding Acknowledgements
Type of funding sources: Public grant(s) – National budget only. Main funding source(s): Wellcome Trust
Background
The quantification of myocardial blood flow (MBF) from stress perfusion cardiac magnetic resonance (CMR) has the potential to facilitate the widespread clinical adoption of stress perfusion CMR. However, one of the major challenges of MBF quantification is the estimation of the arterial input function (AIF) as required for the tracer-kinetic modelling. Since high concentrations of contrast agent are recorded at the peak of the AIF, the non-linear relationship between the concentration of gadolinium and the measured MR signal leads to signal saturation. Current solutions include the use of dual-bolus or dual-sequence acquisitions but both have limited clinical adoption. Therefore, there is a clear unmet need for an AIF estimation approach that is both widely available and easy to integrate in clinical routine, with the ideal acquisition being with a single-bolus and single-saturation sequence.
Purpose
In this work, we propose the artificial intelligence-based AIF (AI-AIF). In particular, we show that a deep learning model can be trained to predict the unsaturated AIF from a saturated single-bolus, single-sequence AIF, using the reference standard dual-sequence AIFs (DS-AIFs) for training.
Methods
This was a multicentre retrospective study, including data from two UK centres with institutional ethical approval. The training dataset was a retrospective sample of patients exclusively from centre 1 (n=218), and a test set was comprised of both an independent cohort of consecutive patients from centre 1 and an external cohort of patients from centre 2 (n=44) to test the generalisation of the model. A 1D U-Net convolutional network was used with 5 resolution steps of two 1D convolutional blocks with batch normalisation, ReLU activations, and dropout (probability=0.2). 1D max-pooling and transposed convolutions are used for down and upsampling respectively. The model was trained for 200,000 iterations (including data augmentation), with a batch size of 10 using the ADAM optimization algorithm (learning rate, 0.001) to minimise the mean squared error between the predicted and reference standard unsaturated AIFs. MBF was quantified in a fully-automated manner (1,2) and compared between the DS-AIF and AI-AIF methods using the Mann-Whitney U test and Bland-Altman analysis.
Results
There was no statistical difference between the median MBF quantified with the DS-AIF (2.77 ml/min/g (1.08)) and quantified with the AI-AIF (2.79 ml/min/g (1.08), p = 0.33. Figure 1 shows an example patient’s predicted AI-AIF compared with the DS-AIF (a) and pixelwise MBF maps with both the DS-AIF and AI-AIF (b). Additionally, the Bland-Altman analysis (shown in Figure 2) shows minimal bias between the DS-AIF and AI-AIF methods for quantitative MBF with a mean bias of -0.11 ml/min/g.
Conclusion
Quantification of stress perfusion CMR is feasible with a single-sequence acquisition and a single contrast injection using an AI-based correction of the AIF.
Collapse
Affiliation(s)
- C M Scannell
- King's College London , London , United Kingdom of Great Britain & Northern Ireland
| | - E Alskaf
- King's College London , London , United Kingdom of Great Britain & Northern Ireland
| | - N Sharrack
- University of Leeds , Leeds , United Kingdom of Great Britain & Northern Ireland
| | - S Plein
- University of Leeds , Leeds , United Kingdom of Great Britain & Northern Ireland
| | - A Chribiri
- King's College London , London , United Kingdom of Great Britain & Northern Ireland
| |
Collapse
|
11
|
Doeblin P, Steinbeis F, Scannell CM, Goetze C, Al-Tabatabaee S, Erley J, Faragli A, Pröpper F, Witzenrath M, Zoller T, Stehning C, Gerhardt H, Sánchez-González J, Alskaf E, Kühne T, Pieske B, Tschöpe C, Chiribiri A, Kelle S. Brief Research Report: Quantitative Analysis of Potential Coronary Microvascular Disease in Suspected Long-COVID Syndrome. Front Cardiovasc Med 2022; 9:877416. [PMID: 35711381 PMCID: PMC9197432 DOI: 10.3389/fcvm.2022.877416] [Citation(s) in RCA: 8] [Impact Index Per Article: 4.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/16/2022] [Accepted: 04/22/2022] [Indexed: 12/02/2022] Open
Abstract
Background Case series have reported persistent cardiopulmonary symptoms, often termed long-COVID or post-COVID syndrome, in more than half of patients recovering from Coronavirus Disease 19 (COVID-19). Recently, alterations in microvascular perfusion have been proposed as a possible pathomechanism in long-COVID syndrome. We examined whether microvascular perfusion, measured by quantitative stress perfusion cardiac magnetic resonance (CMR), is impaired in patients with persistent cardiac symptoms post-COVID-19. Methods Our population consisted of 33 patients post-COVID-19 examined in Berlin and London, 11 (33%) of which complained of persistent chest pain and 13 (39%) of dyspnea. The scan protocol included standard cardiac imaging and dual-sequence quantitative stress perfusion. Standard parameters were compared to 17 healthy controls from our institution. Quantitative perfusion was compared to published values of healthy controls. Results The stress myocardial blood flow (MBF) was significantly lower [31.8 ± 5.1 vs. 37.8 ± 6.0 (μl/g/beat), P < 0.001] and the T2 relaxation time was significantly higher (46.2 ± 3.6 vs. 42.7 ± 2.8 ms, P = 0.002) post-COVID-19 compared to healthy controls. Stress MBF and T1 and T2 relaxation times were not correlated to the COVID-19 severity (Spearman r = −0.302, −0.070, and −0.297, respectively) or the presence of symptoms. The stress MBF showed a U-shaped relation to time from PCR to CMR, no correlation to T1 relaxation time, and a negative correlation to T2 relaxation time (Pearson r = −0.446, P = 0.029). Conclusion While we found a significantly reduced microvascular perfusion post-COVID-19 compared to healthy controls, this reduction was not related to symptoms or COVID-19 severity.
Collapse
Affiliation(s)
- Patrick Doeblin
- Department of Internal Medicine and Cardiology, German Heart Center Berlin, Berlin, Germany
- German Centre for Cardiovascular Research (DZHK), Berlin, Germany
- *Correspondence: Patrick Doeblin,
| | - Fridolin Steinbeis
- Department of Infectious Diseases and Respiratory Medicine, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Cian M. Scannell
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom
| | - Collin Goetze
- Department of Internal Medicine and Cardiology, German Heart Center Berlin, Berlin, Germany
| | - Sarah Al-Tabatabaee
- Department of Internal Medicine and Cardiology, German Heart Center Berlin, Berlin, Germany
| | - Jennifer Erley
- Department of Internal Medicine and Cardiology, German Heart Center Berlin, Berlin, Germany
| | - Alessandro Faragli
- Department of Internal Medicine and Cardiology, German Heart Center Berlin, Berlin, Germany
| | - Felix Pröpper
- Department of Internal Medicine and Cardiology, German Heart Center Berlin, Berlin, Germany
| | - Martin Witzenrath
- Department of Infectious Diseases and Respiratory Medicine, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Thomas Zoller
- Department of Infectious Diseases and Respiratory Medicine, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
- Swiss Tropical and Public Health Institute, Basel, Switzerland
| | | | - Holger Gerhardt
- German Centre for Cardiovascular Research (DZHK), Berlin, Germany
- Integrative Vascular Biology Laboratory, Max-Delbrück Center for Molecular Medicine in the Helmholtz Association (MDC), Berlin, Germany
| | | | - Ebraham Alskaf
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom
| | - Titus Kühne
- German Centre for Cardiovascular Research (DZHK), Berlin, Germany
- Department of Congenital Heart Disease, German Heart Center Berlin, Berlin, Germany
| | - Burkert Pieske
- Department of Internal Medicine and Cardiology, German Heart Center Berlin, Berlin, Germany
- German Centre for Cardiovascular Research (DZHK), Berlin, Germany
- Department of Cardiology, Campus Virchow Klinikum, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| | - Carsten Tschöpe
- German Centre for Cardiovascular Research (DZHK), Berlin, Germany
- Department of Cardiology, Campus Virchow Klinikum, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
- BIH Center for Regenerative Therapies (BCRT), Berlin Institute of Health at Charite (BIH), Universitätsmedizin Berlin, Berlin, Germany
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, United Kingdom
| | - Sebastian Kelle
- Department of Internal Medicine and Cardiology, German Heart Center Berlin, Berlin, Germany
- German Centre for Cardiovascular Research (DZHK), Berlin, Germany
- Department of Cardiology, Campus Virchow Klinikum, Charité – Universitätsmedizin Berlin, Corporate Member of Freie Universität Berlin, Humboldt-Universität zu Berlin, Berlin, Germany
| |
Collapse
|
12
|
van Herten RLM, Chiribiri A, Breeuwer M, Veta M, Scannell CM. Physics-informed neural networks for myocardial perfusion MRI quantification. Med Image Anal 2022; 78:102399. [PMID: 35299005 PMCID: PMC9051528 DOI: 10.1016/j.media.2022.102399] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.5] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/26/2020] [Revised: 01/07/2022] [Accepted: 02/18/2022] [Indexed: 11/19/2022]
Abstract
Tracer-kinetic models allow for the quantification of kinetic parameters such as blood flow from dynamic contrast-enhanced magnetic resonance (MR) images. Fitting the observed data with multi-compartment exchange models is desirable, as they are physiologically plausible and resolve directly for blood flow and microvascular function. However, the reliability of model fitting is limited by the low signal-to-noise ratio, temporal resolution, and acquisition length. This may result in inaccurate parameter estimates. This study introduces physics-informed neural networks (PINNs) as a means to perform myocardial perfusion MR quantification, which provides a versatile scheme for the inference of kinetic parameters. These neural networks can be trained to fit the observed perfusion MR data while respecting the underlying physical conservation laws described by a multi-compartment exchange model. Here, we provide a framework for the implementation of PINNs in myocardial perfusion MR. The approach is validated both in silico and in vivo. In the in silico study, an overall decrease in mean-squared error with the ground-truth parameters was observed compared to a standard non-linear least squares fitting approach. The in vivo study demonstrates that the method produces parameter values comparable to those previously found in literature, as well as providing parameter maps which match the clinical diagnosis of patients.
Collapse
Affiliation(s)
- Rudolf L M van Herten
- Department of Biomedical Engineering, Medical Image Analysis group, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom
| | - Marcel Breeuwer
- Department of Biomedical Engineering, Medical Image Analysis group, Eindhoven University of Technology, Eindhoven, the Netherlands; Philips Healthcare, Best, the Netherlands
| | - Mitko Veta
- Department of Biomedical Engineering, Medical Image Analysis group, Eindhoven University of Technology, Eindhoven, the Netherlands
| | - Cian M Scannell
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom.
| |
Collapse
|
13
|
Tourais J, Scannell CM, Schneider T, Alskaf E, Crawley R, Bosio F, Sanchez-Gonzalez J, Doneva M, Schülke C, Meineke J, Keupp J, Smink J, Breeuwer M, Chiribiri A, Henningsson M, Correia T. High-Resolution Free-Breathing Quantitative First-Pass Perfusion Cardiac MR Using Dual-Echo Dixon With Spatio-Temporal Acceleration. Front Cardiovasc Med 2022; 9:884221. [PMID: 35571164 PMCID: PMC9099052 DOI: 10.3389/fcvm.2022.884221] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 02/25/2022] [Accepted: 04/04/2022] [Indexed: 11/21/2022] Open
Abstract
Introduction To develop and test the feasibility of free-breathing (FB), high-resolution quantitative first-pass perfusion cardiac MR (FPP-CMR) using dual-echo Dixon (FOSTERS; Fat-water separation for mOtion-corrected Spatio-TEmporally accelerated myocardial peRfuSion). Materials and Methods FOSTERS was performed in FB using a dual-saturation single-bolus acquisition with dual-echo Dixon and a dynamically variable Cartesian k-t undersampling (8-fold) approach, with low-rank and sparsity constrained reconstruction, to achieve high-resolution FPP-CMR images. FOSTERS also included automatic in-plane motion estimation and T2* correction to obtain quantitative myocardial blood flow (MBF) maps. High-resolution (1.6 x 1.6 mm2) FB FOSTERS was evaluated in eleven patients, during rest, against standard-resolution (2.6 x 2.6 mm2) 2-fold SENSE-accelerated breath-hold (BH) FPP-CMR. In addition, MBF was computed for FOSTERS and spatial wavelet-based compressed sensing (CS) reconstruction. Two cardiologists scored the image quality (IQ) of FOSTERS, CS, and standard BH FPP-CMR images using a 4-point scale (1–4, non-diagnostic – fully diagnostic). Results FOSTERS produced high-quality images without dark-rim and with reduced motion-related artifacts, using an 8x accelerated FB acquisition. FOSTERS and standard BH FPP-CMR exhibited excellent IQ with an average score of 3.5 ± 0.6 and 3.4 ± 0.6 (no statistical difference, p > 0.05), respectively. CS images exhibited severe artifacts and high levels of noise, resulting in an average IQ score of 2.9 ± 0.5. MBF values obtained with FOSTERS presented a lower variance than those obtained with CS. Discussion FOSTERS enabled high-resolution FB FPP-CMR with MBF quantification. Combining motion correction with a low-rank and sparsity-constrained reconstruction results in excellent image quality.
Collapse
Affiliation(s)
- Joao Tourais
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands
- Department of MR R&D – Clinical Science, Philips Healthcare, Best, Netherlands
- Department of Imaging Physics, Magnetic Resonance Systems Lab, Delft University of Technology, Delft, Netherlands
| | - Cian M. Scannell
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | | | - Ebraham Alskaf
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Richard Crawley
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Filippo Bosio
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | | | | | | | | | | | - Jouke Smink
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands
| | - Marcel Breeuwer
- Department of Biomedical Engineering, Eindhoven University of Technology, Eindhoven, Netherlands
- Department of MR R&D – Clinical Science, Philips Healthcare, Best, Netherlands
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Markus Henningsson
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Division of Cardiovascular Medicine, Department of Medical and Health Sciences, Linkoping University, Linkoping, Sweden
- Center for Medical Image Science and Visualization (CMIV), Linkoping University, Linkoping, Sweden
| | - Teresa Correia
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
- Centre for Marine Sciences (CCMAR), Faro, Portugal
- *Correspondence: Teresa Correia
| |
Collapse
|
14
|
Demir OM, Scannell CM, Chiribiri A, Plein S, Perera D. Cardiac magnetic resonance perfusion abnormality due to anaemia. Eur Heart J Cardiovasc Imaging 2022; 23:e164. [PMID: 34849675 PMCID: PMC8944308 DOI: 10.1093/ehjci/jeab250] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 10/07/2021] [Accepted: 11/12/2021] [Indexed: 11/14/2022] Open
Affiliation(s)
- Ozan M Demir
- NIHR Biomedical Research Centre and British Heart Foundation Centre of Excellence, School of Cardiovascular Medicine and Sciences, King’s College London, London, UK
| | - Cian M Scannell
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, UK
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King’s College London, London, UK
| | - Sven Plein
- Department of Biomedical Imaging Science, Leeds Institute of Cardiovascular and Metabolic Medicine, University of Leeds, Leeds, UK
| | - Divaka Perera
- NIHR Biomedical Research Centre and British Heart Foundation Centre of Excellence, School of Cardiovascular Medicine and Sciences, King’s College London, London, UK
| |
Collapse
|
15
|
Campello VM, Gkontra P, Izquierdo C, Martin-Isla C, Sojoudi A, Full PM, Maier-Hein K, Zhang Y, He Z, Ma J, Parreno M, Albiol A, Kong F, Shadden SC, Acero JC, Sundaresan V, Saber M, Elattar M, Li H, Menze B, Khader F, Haarburger C, Scannell CM, Veta M, Carscadden A, Punithakumar K, Liu X, Tsaftaris SA, Huang X, Yang X, Li L, Zhuang X, Vilades D, Descalzo ML, Guala A, Mura LL, Friedrich MG, Garg R, Lebel J, Henriques F, Karakas M, Cavus E, Petersen SE, Escalera S, Segui S, Rodriguez-Palomares JF, Lekadir K. Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation: The M&Ms Challenge. IEEE Trans Med Imaging 2021; 40:3543-3554. [PMID: 34138702 DOI: 10.1109/tmi.2021.3090082] [Citation(s) in RCA: 82] [Impact Index Per Article: 27.3] [Reference Citation Analysis] [What about the content of this article? (0)] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 06/12/2023]
Abstract
The emergence of deep learning has considerably advanced the state-of-the-art in cardiac magnetic resonance (CMR) segmentation. Many techniques have been proposed over the last few years, bringing the accuracy of automated segmentation close to human performance. However, these models have been all too often trained and validated using cardiac imaging samples from single clinical centres or homogeneous imaging protocols. This has prevented the development and validation of models that are generalizable across different clinical centres, imaging conditions or scanner vendors. To promote further research and scientific benchmarking in the field of generalizable deep learning for cardiac segmentation, this paper presents the results of the Multi-Centre, Multi-Vendor and Multi-Disease Cardiac Segmentation (M&Ms) Challenge, which was recently organized as part of the MICCAI 2020 Conference. A total of 14 teams submitted different solutions to the problem, combining various baseline models, data augmentation strategies, and domain adaptation techniques. The obtained results indicate the importance of intensity-driven data augmentation, as well as the need for further research to improve generalizability towards unseen scanner vendors or new imaging protocols. Furthermore, we present a new resource of 375 heterogeneous CMR datasets acquired by using four different scanner vendors in six hospitals and three different countries (Spain, Canada and Germany), which we provide as open-access for the community to enable future research in the field.
Collapse
|
16
|
Doeblin P, Goetze C, Al-Tabatabaee S, Berger A, Steinbeis F, Witzenrath M, Faragli A, Stehning C, Chiribiri A, Scannell CM, Alskaf E, Pieske B, Kelle S. Stress myocardial blood flow reduced after severe COVID-19, not related to symptoms. Eur Heart J 2021. [DOI: 10.1093/eurheartj/ehab724.0213] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Indexed: 11/13/2022] Open
Abstract
Abstract
Introduction
Persistent cardiopulmonary symptoms after COVID-19 are reported in a large number of patients and the underlying pathology is still poorly understood. (1) Histopathologic studies revealed myocardial macrophage infiltrates in deceased patients, likely an unspecific finding of severe illness, and increased prevalence of micro- and macrovascular thrombi. (2) We examined whether microvascular perfusion, measured by quantitative cardiac magnetic resonance under vasodilator stress, was altered post COVID-19.
Methods
Our population consisted of 12 patients from the Pa-COVID-19-Study of the Charité Berlin, which received a cardiac MRI as part of a systematic follow up post discharge, 10 patients that presented at the German Heart Center Berlin with persistent cardiac symptoms post COVID-19 and 12 patients from the Kings College London referred for stress MRI and previous COVID-19.
The scan protocol included standard functional, edema and scar imaging and quantitative stress and rest perfusion to assess both macro- and microvascular coronary artery disease. The pharmacological stress agent was regadenosone in 20 and adenosine in 13 of the patients. To control for the higher heart rate increase under regadenosone compared to adenosine, we calculated the myocardial blood flow per heartbeat (MBF_HRi) under stress.
Results
The median time between first positive PCR for COVID-19 and the CMR exam was 2 months (Range 0 to 12). None of the 33 patients exhibited signs of myocardial edema. One patient with a previous history of myocarditis had focal fibrosis. Three patients with known coronary artery disease showed ischemic Late Enhancement. Five patients had a small pericardial effusion; one of these four patients showed slight focal pericardial edema and LGE, consistent with mild focal pericarditis. Five Patients had a stress-induced focal perfusion deficit.
Mean Stress MBF_HRi was 32.5±6.5 μl/beat/g. Stress MBF_HRi was negatively correlated with COVID-19 severity (rho=−0.361, P=0.039) and age (r=−0.452, P=0.009). The correlation with COVID-19 severity remained significant after controlling for age (rho=−0.390, P=0.027). There was no apparent difference in stress MBF_HRi between patients with and without persistent chest pain (34.5 vs. 31.5 μl/beat/g, P=0.229)
Conclusion
While vasodilator-stress myocardial blood flow after COVID-19 was negatively correlated to COVID-19 severity, it was not correlated to the presence of chest pain. The etiology of persistent cardiac symptoms after COVID-19 remains unclear.
Funding Acknowledgement
Type of funding sources: Private company. Main funding source(s): Philips Figure 1. A) Quantitative regadenosone stress myocardial blood flow (MBF) map, medial short axis slice, in a patient with persistent cardiac symptoms after COVID-19. B) Boxplot of stress MBF per heart beat by COVID-19 severity, showing decreasing MBF with increasing COVID-19 severity.
Collapse
Affiliation(s)
- P Doeblin
- Deutsches Herzzentrum Berlin, Berlin, Germany
| | - C Goetze
- Deutsches Herzzentrum Berlin, Berlin, Germany
| | | | - A Berger
- Deutsches Herzzentrum Berlin, Berlin, Germany
| | - F Steinbeis
- Charite - Campus Mitte (CCM), Department of Infectious Diseases and Respiratory Medicine, Berlin, Germany
| | - M Witzenrath
- Charite - Campus Mitte (CCM), Department of Infectious Diseases and Respiratory Medicine, Berlin, Germany
| | - A Faragli
- Deutsches Herzzentrum Berlin, Berlin, Germany
| | | | - A Chiribiri
- King's College London, Division of Imaging Sciences, London, United Kingdom
| | - C M Scannell
- King's College London, Division of Imaging Sciences, London, United Kingdom
| | - E Alskaf
- King's College London, Division of Imaging Sciences, London, United Kingdom
| | - B Pieske
- Deutsches Herzzentrum Berlin, Berlin, Germany
| | - S Kelle
- Deutsches Herzzentrum Berlin, Berlin, Germany
| |
Collapse
|
17
|
Scannell CM, Hasaneen H, Greil G, Hussain T, Razavi R, Lee J, Pushparajah K, Duong P, Chiribiri A. Automated Quantitative Stress Perfusion Cardiac Magnetic Resonance in Pediatric Patients. Front Pediatr 2021; 9:699497. [PMID: 34540764 PMCID: PMC8446614 DOI: 10.3389/fped.2021.699497] [Citation(s) in RCA: 5] [Impact Index Per Article: 1.7] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 04/23/2021] [Accepted: 08/05/2021] [Indexed: 11/13/2022] Open
Abstract
Background: Myocardial ischemia occurs in pediatrics, as a result of both congenital and acquired heart diseases, and can lead to further adverse cardiac events if untreated. The aim of this work is to assess the feasibility of fully automated, high resolution, quantitative stress myocardial perfusion cardiac magnetic resonance (CMR) in a cohort of pediatric patients and to evaluate its agreement with the coronary anatomical status of the patients. Methods: Fourteen pediatric patients, with 16 scans, who underwent dual-bolus stress perfusion CMR were retrospectively analyzed. All patients also had anatomical coronary assessment with either CMR, CT, or X-ray angiography. The perfusion CMR images were automatically processed and quantified using an analysis pipeline previously developed in adults. Results: Automated perfusion quantification was successful in 15/16 cases. The coronary perfusion territories supplied by vessels affected by a medium/large aneurysm or stenosis (according to the AHA guidelines), induced by Kawasaki disease, an anomalous origin, or interarterial course had significantly reduced myocardial blood flow (MBF) (median (interquartile range), 1.26 (1.05, 1.67) ml/min/g) as compared to territories supplied by unaffected coronaries [2.57 (2.02, 2.69) ml/min/g, p < 0.001] and territories supplied by vessels with a small aneurysm [2.52 (2.45, 2.83) ml/min/g, p = 0.002]. Conclusion: Automatic CMR-derived MBF quantification is feasible in pediatric patients, and the technology could be potentially used for objective non-invasive assessment of ischemia in children with congenital and acquired heart diseases.
Collapse
Affiliation(s)
- Cian M. Scannell
- School of Biomedical Engineering and Imaging Sciences, St Thomas' Hospital, King's College London, London, United Kingdom
| | - Hadeer Hasaneen
- School of Biomedical Engineering and Imaging Sciences, St Thomas' Hospital, King's College London, London, United Kingdom
| | - Gerald Greil
- Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, TX, United States
| | - Tarique Hussain
- Department of Pediatrics, University of Texas Southwestern Medical Center, Dallas, TX, United States
| | - Reza Razavi
- School of Biomedical Engineering and Imaging Sciences, St Thomas' Hospital, King's College London, London, United Kingdom
| | - Jack Lee
- School of Biomedical Engineering and Imaging Sciences, St Thomas' Hospital, King's College London, London, United Kingdom
| | - Kuberan Pushparajah
- School of Biomedical Engineering and Imaging Sciences, St Thomas' Hospital, King's College London, London, United Kingdom
| | - Phuoc Duong
- School of Biomedical Engineering and Imaging Sciences, St Thomas' Hospital, King's College London, London, United Kingdom
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, St Thomas' Hospital, King's College London, London, United Kingdom
| |
Collapse
|
18
|
Rahman H, Scannell CM, Demir OM, Ryan M, McConkey H, Ellis H, Masci PG, Perera D, Chiribiri A. High-Resolution Cardiac Magnetic Resonance Imaging Techniques for the Identification of Coronary Microvascular Dysfunction. JACC Cardiovasc Imaging 2020; 14:978-986. [PMID: 33248969 DOI: 10.1016/j.jcmg.2020.10.015] [Citation(s) in RCA: 52] [Impact Index Per Article: 13.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 07/07/2020] [Revised: 09/01/2020] [Accepted: 10/14/2020] [Indexed: 12/13/2022]
Abstract
OBJECTIVES This study assessed the ability to identify coronary microvascular dysfunction (CMD) in patients with angina and nonobstructive coronary artery disease (NOCAD) using high-resolution cardiac magnetic resonance (CMR) and hypothesized that quantitative perfusion techniques would have greater accuracy than visual analysis. BACKGROUND Half of all patients with angina are found to have NOCAD, while the presence of CMD portends greater morbidity and mortality, it now represents a modifiable therapeutic target. Diagnosis currently requires invasive assessment of coronary blood flow during angiography. With greater reliance on computed tomography coronary angiography as a first-line tool to investigate angina, noninvasive tests for diagnosing CMD warrant validation. METHODS Consecutive patients with angina and NOCAD were enrolled. Intracoronary pressure and flow measurements were acquired during rest and vasodilator-mediated hyperemia. CMR (3-T) was performed and analyzed by visual and quantitative techniques, including calculation of myocardial blood flow (MBF) during hyperemia (stress MBF), transmural myocardial perfusion reserve (MPR: MBFHYPEREMIA / MBFREST), and subendocardial MPR (MPRENDO). CMD was defined dichotomously as an invasive coronary flow reserve <2.5, with CMR readers blinded to this classification. RESULTS A total of 75 patients were enrolled (57 ± 10 years of age, 81% women). Among the quantitative perfusion indices, MPRENDO and MPR had the highest accuracy (area under the curve [AUC]: 0.90 and 0.88) with high sensitivity and specificity, respectively, both superior to visual assessment (both p < 0.001). Visual assessment identified CMD with 58% accuracy (41% sensitivity and 83% specificity). Quantitative stress MBF performed similarly to visual analysis (AUC: 0.64 vs. 0.60; p = 0.69). CONCLUSIONS High-resolution CMR has good accuracy at detecting CMD but only when analyzed quantitatively. Although omission of rest imaging and stress-only protocols make for quicker scans, this is at the cost of accuracy compared with integrating rest and stress perfusion. Quantitative perfusion CMR has an increasingly important role in the management of patients frequently encountered with angina and NOCAD.
Collapse
Affiliation(s)
- Haseeb Rahman
- School of Cardiovascular Medicine and Sciences, British Heart Foundation Centre of Excellence and National Institute for Health Research Biomedical Research Centre, King's College London, London, United Kingdom
| | - Cian M Scannell
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Ozan M Demir
- School of Cardiovascular Medicine and Sciences, British Heart Foundation Centre of Excellence and National Institute for Health Research Biomedical Research Centre, King's College London, London, United Kingdom
| | - Matthew Ryan
- School of Cardiovascular Medicine and Sciences, British Heart Foundation Centre of Excellence and National Institute for Health Research Biomedical Research Centre, King's College London, London, United Kingdom
| | - Hannah McConkey
- School of Cardiovascular Medicine and Sciences, British Heart Foundation Centre of Excellence and National Institute for Health Research Biomedical Research Centre, King's College London, London, United Kingdom
| | - Howard Ellis
- School of Cardiovascular Medicine and Sciences, British Heart Foundation Centre of Excellence and National Institute for Health Research Biomedical Research Centre, King's College London, London, United Kingdom
| | - Pier Giorgio Masci
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| | - Divaka Perera
- School of Cardiovascular Medicine and Sciences, British Heart Foundation Centre of Excellence and National Institute for Health Research Biomedical Research Centre, King's College London, London, United Kingdom.
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, United Kingdom
| |
Collapse
|
19
|
Scannell CM, Correia T, Villa ADM, Schneider T, Lee J, Breeuwer M, Chiribiri A, Henningsson M. Feasibility of free-breathing quantitative myocardial perfusion using multi-echo Dixon magnetic resonance imaging. Sci Rep 2020; 10:12684. [PMID: 32728198 PMCID: PMC7392760 DOI: 10.1038/s41598-020-69747-9] [Citation(s) in RCA: 4] [Impact Index Per Article: 1.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 03/19/2020] [Accepted: 07/15/2020] [Indexed: 11/08/2022] Open
Abstract
Dynamic contrast-enhanced quantitative first-pass perfusion using magnetic resonance imaging enables non-invasive objective assessment of myocardial ischemia without ionizing radiation. However, quantification of perfusion is challenging due to the non-linearity between the magnetic resonance signal intensity and contrast agent concentration. Furthermore, respiratory motion during data acquisition precludes quantification of perfusion. While motion correction techniques have been proposed, they have been hampered by the challenge of accounting for dramatic contrast changes during the bolus and long execution times. In this work we investigate the use of a novel free-breathing multi-echo Dixon technique for quantitative myocardial perfusion. The Dixon fat images, unaffected by the dynamic contrast-enhancement, are used to efficiently estimate rigid-body respiratory motion and the computed transformations are applied to the corresponding diagnostic water images. This is followed by a second non-linear correction step using the Dixon water images to remove residual motion. The proposed Dixon motion correction technique was compared to the state-of-the-art technique (spatiotemporal based registration). We demonstrate that the proposed method performs comparably to the state-of-the-art but is significantly faster to execute. Furthermore, the proposed technique can be used to correct for the decay of signal due to T2* effects to improve quantification and additionally, yields fat-free diagnostic images.
Collapse
Affiliation(s)
- Cian M Scannell
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Teresa Correia
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Adriana D M Villa
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | | | - Jack Lee
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Marcel Breeuwer
- Philips Healthcare, Best, The Netherlands
- Department of Biomedical Engineering, Medical Image Analysis Group, Eindhoven University of Technology, Eindhoven, The Netherlands
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK
| | - Markus Henningsson
- School of Biomedical Engineering and Imaging Sciences, King's College London, London, UK.
- Division of Cardiovascular Medicine, Department of Medical and Health Sciences, Linköping University, Linköping, Sweden.
- Center for Medical Image Science and Visualization (CMIV), Linköping University, Linköping, Sweden.
| |
Collapse
|
20
|
Scannell CM, Veta M, Villa AD, Sammut EC, Lee J, Breeuwer M, Chiribiri A. Deep-Learning-Based Preprocessing for Quantitative Myocardial Perfusion MRI. J Magn Reson Imaging 2020; 51:1689-1696. [PMID: 31710769 PMCID: PMC7317373 DOI: 10.1002/jmri.26983] [Citation(s) in RCA: 40] [Impact Index Per Article: 10.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 04/15/2019] [Revised: 10/11/2019] [Accepted: 10/16/2019] [Indexed: 12/21/2022] Open
Abstract
BACKGROUND Quantitative myocardial perfusion cardiac MRI can provide a fast and robust assessment of myocardial perfusion status for the noninvasive diagnosis of myocardial ischemia while being more objective than visual assessment. However, it currently has limited use in clinical practice due to the challenging postprocessing required, particularly the segmentation. PURPOSE To evaluate the efficacy of an automated deep learning (DL) pipeline for image processing prior to quantitative analysis. STUDY TYPE Retrospective. POPULATION In all, 175 (350 MRI scans; 1050 image series) clinical patients under both rest and stress conditions (135/10/30 training/validation/test). FIELD STRENGTH/SEQUENCE 3.0T/2D multislice saturation recovery T1 -weighted gradient echo sequence. ASSESSMENT Accuracy was assessed, as compared to the manual operator, through the mean square error of the distance between landmarks and the Dice similarity coefficient of the segmentation and bounding box detection. Quantitative perfusion maps obtained using the automated DL-based processing were compared to the results obtained with the manually processed images. STATISTICAL TESTS Bland-Altman plots and intraclass correlation coefficient (ICC) were used to assess the myocardial blood flow (MBF) obtained using the automated DL pipeline, as compared to values obtained by a manual operator. RESULTS The mean (SD) error in the detection of the time of peak signal enhancement in the left ventricle was 1.49 (1.4) timeframes. The mean (SD) Dice similarity coefficients for the bounding box and myocardial segmentation were 0.93 (0.03) and 0.80 (0.06), respectively. The mean (SD) error in the RV insertion point was 2.8 (1.8) mm. The Bland-Altman plots showed a bias of 2.6% of the mean MBF between the automated and manually processed MBF values on a per-myocardial segment basis. The ICC was 0.89, 95% confidence interval = [0.87, 0.90]. DATA CONCLUSION We showed high accuracy, compared to manual processing, for the DL-based processing of myocardial perfusion data leading to quantitative values that are similar to those achieved with manual processing. LEVEL OF EVIDENCE 3 Technical Efficacy Stage: 1 J. Magn. Reson. Imaging 2020;51:1689-1696.
Collapse
Affiliation(s)
- Cian M. Scannell
- School of Biomedical Engineering and Imaging SciencesKing's College LondonUK
- Alan Turing Institute LondonUK
| | - Mitko Veta
- Department of Biomedical Engineering, Medical Image Analysis groupEindhoven University of TechnologyEindhovenThe Netherlands
| | - Adriana D.M. Villa
- School of Biomedical Engineering and Imaging SciencesKing's College LondonUK
| | - Eva C. Sammut
- School of Biomedical Engineering and Imaging SciencesKing's College LondonUK
- Bristol Heart Institute and Translational Biomedical Research Centre, Faculty of Health ScienceUniversity of BristolUK
| | - Jack Lee
- School of Biomedical Engineering and Imaging SciencesKing's College LondonUK
| | - Marcel Breeuwer
- Department of Biomedical Engineering, Medical Image Analysis groupEindhoven University of TechnologyEindhovenThe Netherlands
- Philips Healthcare, BestThe Netherlands
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging SciencesKing's College LondonUK
| |
Collapse
|
21
|
Scannell CM, Chiribiri A, Villa ADM, Breeuwer M, Lee J. Hierarchical Bayesian myocardial perfusion quantification. Med Image Anal 2020; 60:101611. [PMID: 31760191 PMCID: PMC6880627 DOI: 10.1016/j.media.2019.101611] [Citation(s) in RCA: 12] [Impact Index Per Article: 3.0] [Reference Citation Analysis] [What about the content of this article? (0)] [Affiliation(s)] [Abstract] [Key Words] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/20/2018] [Revised: 11/07/2019] [Accepted: 11/08/2019] [Indexed: 01/25/2023]
Abstract
Myocardial blood flow can be quantified from dynamic contrast-enhanced magnetic resonance (MR) images through the fitting of tracer-kinetic models to the observed imaging data. The use of multi-compartment exchange models is desirable as they are physiologically motivated and resolve directly for both blood flow and microvascular function. However, the parameter estimates obtained with such models can be unreliable. This is due to the complexity of the models relative to the observed data which is limited by the low signal-to-noise ratio, the temporal resolution, the length of the acquisitions and other complex imaging artefacts. In this work, a Bayesian inference scheme is proposed which allows the reliable estimation of the parameters of the two-compartment exchange model from myocardial perfusion MR data. The Bayesian scheme allows the incorporation of prior knowledge on the physiological ranges of the model parameters and facilitates the use of the additional information that neighbouring voxels are likely to have similar kinetic parameter values. Hierarchical priors are used to avoid making a priori assumptions on the health of the patients. We provide both a theoretical introduction to Bayesian inference for tracer-kinetic modelling and specific implementation details for this application. This approach is validated in both in silico and in vivo settings. In silico, there was a significant reduction in mean-squared error with the ground-truth parameters using Bayesian inference as compared to using the standard non-linear least squares fitting. When applied to patient data the Bayesian inference scheme returns parameter values that are in-line with those previously reported in the literature, as well as giving parameter maps that match the independant clinical diagnosis of those patients.
Collapse
Affiliation(s)
- Cian M Scannell
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom; The Alan Turing Institute London, United Kingdom.
| | - Amedeo Chiribiri
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom.
| | - Adriana D M Villa
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom.
| | - Marcel Breeuwer
- Philips Healthcare, Best, the Netherlands; Department of Biomedical Engineering, Medical Image Analysis group, Eindhoven University of Technology, Eindhoven, the Netherlands.
| | - Jack Lee
- School of Biomedical Engineering and Imaging Sciences, King's College London, United Kingdom.
| |
Collapse
|
22
|
Abstract
Kinetic parameter values, such as myocardial perfusion, can be quantified from dynamic contrast-enhanced magnetic resonance imaging data using tracer-kinetic modeling. However, respiratory motion affects the accuracy of this process. Motion compensation of the image series is difficult due to the rapid local signal enhancement caused by the passing of the gadolinium-based contrast agent. This contrast enhancement invalidates the assumptions of the (global) cost functions traditionally used in intensity-based registrations. The algorithms are unable to distinguish whether the differences in signal intensity between frames are caused by the spatial motion artifacts or the local contrast enhancement. In order to address this problem, a fully automated motion compensation scheme is proposed, which consists of two stages. The first of which uses robust principal component analysis (PCA) to separate the local signal enhancement from the baseline signal, before a refinement stage which uses the traditional PCA to construct a synthetic reference series that is free from motion but preserves the signal enhancement. Validation is performed on 18 subjects acquired in free-breathing and 5 clinical subjects acquired with a breath-hold. The validation assesses the visual quality, the temporal smoothness of tissue curves, and the clinically relevant quantitative perfusion values. The expert observers score the visual quality increased by a mean of 1.58/5 after motion compensation and improvement over the previously published methods. The proposed motion compensation scheme also leads to the improved quantitative performance of motion compensated free-breathing image series [30% reduction in the coefficient of variation across quantitative perfusion maps and 53% reduction in temporal variations (p < 0.001)].
Collapse
|