TY - JOUR
T1 - Fully automated myocardial strain estimation from cardiovascular MRI–Tagged images using a deep learning framework in the UK biobank
AU - Ferdian, Edward
AU - Suinesiaputra, Avan
AU - Fung, Kenneth
AU - Aung, Nay
AU - Lukaschuk, Elena
AU - Barutcu, Ahmet
AU - Maclean, Edd
AU - Paiva, Jose
AU - Piechnik, Stefan K.
AU - Neubauer, Stefan
AU - Petersen, Steffen E.
AU - Young, Alistair A.
N1 - Funding Information:
was provided by the British Heart Foundation and the National Institutes of Health. S.N. received funding from the NIHR Oxford Biomedical Research Centre based at The Oxford University Hospitals Trust at the University of Oxford and the British Heart Foundation Centre of Research Excellence. A.Y. received funding from the Health Research Council of New Zealand. A.L. and S.E.P. received support from the NIHR Barts Biomedical Research Centre and from the ?SmartHeart? EPSRC program grant. N.A. is supported by a Wellcome Trust Research Training Fellowship. This project was enabled through access to the MRC eMedLab Medical Bioinformatics infrastructure, supported by the Medical Research Council. K.F. is supported by The Medical College of Saint Bartholomew?s Hospital Trust, an independent registered charity that promotes and advances medical and dental education and research at Barts and The London School of Medicine and Dentistry. The UK Biobank was established by the Wellcome Trust medical charity, Medical Research Council, Department of Health, Scottish Government, and the Northwest Regional Development Agency. It has also received funding from the Welsh Assembly Government and the British Heart Foundation.
Funding Information:
This research has been conducted using the UK Biobank Resource under application 2964. Funding was provided by the British Heart Foundation and the National Institutes of Health. S.N. received funding from the NIHR Oxford Biomedical Research Centre based at The Oxford University Hospitals Trust at the University of Oxford and the British Heart Foundation Centre of Research Excellence. A.Y. received funding from the Health Research Council of New Zealand. A.L. and S.E.P. received support from the NIHR Barts Biomedical Research Centre and from the “SmartHeart” EPSRC program grant. N.A. is supported by a Wellcome Trust Research Training Fellowship. This project was enabled through access to the MRC eMedLab Medical Bioinformatics infrastructure, supported by the Medical Research Council. K.F. is supported by The Medical College of Saint Bartholomew’s Hospital Trust, an independent registered charity that promotes and advances medical and dental education and research at Barts and The London School of Medicine and Dentistry. The UK Biobank was established by the Wellcome Trust medical charity, Medical Research Council, Department of Health, Scottish Government, and the Northwest Regional Development Agency. It has also received funding from the Welsh Assembly Government and the British Heart Foundation.
Publisher Copyright:
© Published under a CC BY 4.0 license.
Copyright:
Copyright 2021 Elsevier B.V., All rights reserved.
PY - 2020/2
Y1 - 2020/2
N2 - Purpose: To demonstrate the feasibility and performance of a fully automated deep learning framework to estimate myocardial strain from short-axis cardiac MRI–tagged images. Materials and Methods: In this retrospective cross-sectional study, 4508 cases from the U.K. Biobank were split randomly into 3244 training cases, 812 validation cases, and 452 test cases. Ground truth myocardial landmarks were defined and tracked by manual initialization and correction of deformable image registration using previously validated software with five readers. The fully automatic framework consisted of (a) a convolutional neural network (CNN) for localization and (b) a combination of a recurrent neural network (RNN) and a CNN to detect and track the myocardial landmarks through the image sequence for each slice. Radial and circumferential strain were then calculated from the motion of the landmarks and averaged on a slice basis. Results: Within the test set, myocardial end-systolic circumferential Green strain errors were 20.001 ± 0.025, 20.001 ± 0.021, and 0.004 ± 0.035 in the basal, mid-, and apical slices, respectively (mean ± standard deviation of differences between predicted and manual strain). The framework reproduced significant reductions in circumferential strain in participants with diabetes, hypertensive participants, and participants with a previous heart attack. Typical processing time was approximately 260 frames (approximately 13 slices) per second on a GPU with 12 GB RAM compared with 6–8 minutes per slice for the manual analysis. Conclusion: The fully automated combined RNN and CNN framework for analysis of myocardial strain enabled unbiased strain evaluation in a high-throughput workflow, with similar ability to distinguish impairment due to diabetes, hypertension, and previous heart attack.
AB - Purpose: To demonstrate the feasibility and performance of a fully automated deep learning framework to estimate myocardial strain from short-axis cardiac MRI–tagged images. Materials and Methods: In this retrospective cross-sectional study, 4508 cases from the U.K. Biobank were split randomly into 3244 training cases, 812 validation cases, and 452 test cases. Ground truth myocardial landmarks were defined and tracked by manual initialization and correction of deformable image registration using previously validated software with five readers. The fully automatic framework consisted of (a) a convolutional neural network (CNN) for localization and (b) a combination of a recurrent neural network (RNN) and a CNN to detect and track the myocardial landmarks through the image sequence for each slice. Radial and circumferential strain were then calculated from the motion of the landmarks and averaged on a slice basis. Results: Within the test set, myocardial end-systolic circumferential Green strain errors were 20.001 ± 0.025, 20.001 ± 0.021, and 0.004 ± 0.035 in the basal, mid-, and apical slices, respectively (mean ± standard deviation of differences between predicted and manual strain). The framework reproduced significant reductions in circumferential strain in participants with diabetes, hypertensive participants, and participants with a previous heart attack. Typical processing time was approximately 260 frames (approximately 13 slices) per second on a GPU with 12 GB RAM compared with 6–8 minutes per slice for the manual analysis. Conclusion: The fully automated combined RNN and CNN framework for analysis of myocardial strain enabled unbiased strain evaluation in a high-throughput workflow, with similar ability to distinguish impairment due to diabetes, hypertension, and previous heart attack.
UR - http://www.scopus.com/inward/record.url?scp=85092693789&partnerID=8YFLogxK
U2 - 10.1148/ryct.2020190032
DO - 10.1148/ryct.2020190032
M3 - Article
AN - SCOPUS:85092693789
SN - 2638-6135
VL - 2
JO - Radiology: Cardiothoracic Imaging
JF - Radiology: Cardiothoracic Imaging
IS - 1
M1 - e190032
ER -