{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T16:44:11Z","timestamp":1783010651071,"version":"3.54.6"},"reference-count":28,"publisher":"MDPI AG","issue":"9","license":[{"start":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T00:00:00Z","timestamp":1630022400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100016394","name":"ANR","doi-asserted-by":"publisher","award":["ANR-10-IAHU-02"],"award-info":[{"award-number":["ANR-10-IAHU-02"]}],"id":[{"id":"10.13039\/501100016394","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Diagnostics"],"abstract":"<jats:p>The automatic classification of various types of cardiomyopathies is desirable but has never been performed using a convolutional neural network (CNN). The purpose of this study was to evaluate currently available CNN models to classify cine magnetic resonance (cine-MR) images of cardiomyopathies. Method: Diastolic and systolic frames of 1200 cine-MR sequences of three categories of subjects (395 normal, 411 hypertrophic cardiomyopathy, and 394 dilated cardiomyopathy) were selected, preprocessed, and labeled. Pretrained, fine-tuned deep learning models (VGG) were used for image classification (sixfold cross-validation and double split testing with hold-out data). The heat activation map algorithm (Grad-CAM) was applied to reveal salient pixel areas leading to the classification. Results: The diastolic\u2013systolic dual-input concatenated VGG model cross-validation accuracy was 0.982 \u00b1 0.009. Summed confusion matrices showed that, for the 1200 inputs, the VGG model led to 22 errors. The classification of a 227-input validation group, carried out by an experienced radiologist and cardiologist, led to a similar number of discrepancies. The image preparation process led to 5% accuracy improvement as compared to nonprepared images. Grad-CAM heat activation maps showed that most misclassifications occurred when extracardiac location caught the attention of the network. Conclusions: CNN networks are very well suited and are 98% accurate for the classification of cardiomyopathies, regardless of the imaging plane, when both diastolic and systolic frames are incorporated. Misclassification is in the same range as inter-observer discrepancies in experienced human readers.<\/jats:p>","DOI":"10.3390\/diagnostics11091554","type":"journal-article","created":{"date-parts":[[2021,8,27]],"date-time":"2021-08-27T09:53:23Z","timestamp":1630058003000},"page":"1554","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Classification of Cardiomyopathies from MR Cine Images Using Convolutional Neural Network with Transfer Learning"],"prefix":"10.3390","volume":"11","author":[{"given":"Philippe","family":"Germain","sequence":"first","affiliation":[{"name":"Department of Radiology, Nouvel Hopital Civil, University Hospital, 67091 Strasbourg, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Armine","family":"Vardazaryan","sequence":"additional","affiliation":[{"name":"ICube, University of Strasbourg, CNRS, 67091 Strasbourg, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Nicolas","family":"Padoy","sequence":"additional","affiliation":[{"name":"ICube, University of Strasbourg, CNRS, 67091 Strasbourg, France"},{"name":"IHU, 67091 Strasbourg, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Aissam","family":"Labani","sequence":"additional","affiliation":[{"name":"Department of Radiology, Nouvel Hopital Civil, University Hospital, 67091 Strasbourg, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Catherine","family":"Roy","sequence":"additional","affiliation":[{"name":"Department of Radiology, Nouvel Hopital Civil, University Hospital, 67091 Strasbourg, France"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas Hellmut","family":"Schindler","sequence":"additional","affiliation":[{"name":"Division of Nuclear Medicine, Mallinckrodt Institute of Radiology, Washington University School of Medicine, Saint Louis, MO 63110, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soraya","family":"El Ghannudi","sequence":"additional","affiliation":[{"name":"Department of Radiology, Nouvel Hopital Civil, University Hospital, 67091 Strasbourg, France"},{"name":"Department of Nuclear Medicine, Nouvel Hopital Civil, University Hospital, 67091 Strasbourg, France"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2021,8,27]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"1549","DOI":"10.1016\/j.jcmg.2019.06.009","article-title":"State-of-the-Art Deep Learning in Cardiovascular Image Analysis","volume":"12","author":"Litjens","year":"2019","journal-title":"JACC Cardiovasc. Imaging"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"e271","DOI":"10.1016\/S2589-7500(19)30123-2","article-title":"A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: A systematic review and meta-analysis","volume":"1","author":"Liu","year":"2019","journal-title":"Lancet Digit. Health"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1","DOI":"10.3389\/fcvm.2020.00001","article-title":"Image-Based Cardiac Diagnosis With Machine Learning: A Review","volume":"7","author":"Campello","year":"2020","journal-title":"Front Cardiovasc. Med."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"1113","DOI":"10.1259\/bjr.20190812","article-title":"Development and application of artificial intelligence in cardiac imaging","volume":"93","author":"Jiang","year":"2020","journal-title":"Br. J. Radiol."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1002\/jmri.25932","article-title":"Fully automated segmentation of the left ventricle in cine cardiac MRI using neural network regression","volume":"48","author":"Tan","year":"2018","journal-title":"J. Magn. Reason. Imaging."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"25","DOI":"10.3389\/fcvm.2020.00025","article-title":"Deep Learning for Cardiac Image Segmentation: A Review","volume":"7","author":"Chen","year":"2020","journal-title":"Front Cardiovasc. Med."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1038\/s41746-018-0065-x","article-title":"Deep echocardiography: Data-efficient supervised and semi-supervised deep learning towards automated diagnosis of cardiac disease","volume":"1","author":"Madani","year":"2018","journal-title":"NPJ Digit. Med."},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"1623","DOI":"10.1161\/CIRCULATIONAHA.118.034338","article-title":"Fully Automated Echocardiogram Interpretation in Clinical Practice","volume":"138","author":"Zhang","year":"2018","journal-title":"Circulation"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1654","DOI":"10.1016\/j.jcmg.2018.01.020","article-title":"Deep Learning for Prediction of Obstructive Disease From Fast Myocardial Perfusion SPECT: A Multicenter Study","volume":"11","author":"Betancur","year":"2018","journal-title":"J. Am. Coll. Cardiol. Img."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"81","DOI":"10.1016\/j.compbiomed.2018.11.008","article-title":"Cardiac sarcoidosis classification with deep convolutional neural network-based features using polar maps","volume":"104","author":"Togo","year":"2019","journal-title":"Comput. Biol. Med."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1186\/s12968-020-00690-4","article-title":"Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance","volume":"22","author":"Martini","year":"2020","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"3931","DOI":"10.1007\/s00330-020-07454-9","article-title":"Deep learning algorithm to improve hypertrophic cardiomyopathy mutation prediction using cardiac cine images","volume":"31","author":"Zhou","year":"2020","journal-title":"Eur. Radiol."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"1180","DOI":"10.1016\/j.jcmg.2017.08.005","article-title":"Role of Cardiac Magnetic Resonance in the Diagnosis and Prognosis of Nonischemic Cardiomyopathy","volume":"10","author":"Patel","year":"2017","journal-title":"J. Am. Coll. Cardiol. Img."},{"key":"ref_14","first-page":"e783","article-title":"2011 ACCF\/AHA guideline for the diagnosis and treatment of hypertrophic cardiomyopathy","volume":"124","author":"Gersh","year":"2011","journal-title":"Circulation"},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1038","DOI":"10.1002\/jmri.24649","article-title":"Impact of age, sex, and indexation method on MR left ventricular reference values in the Framingham Heart Study offspring cohort","volume":"41","author":"Yeon","year":"2015","journal-title":"J. Magn. Reason. Imaging"},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1186\/s12968-020-00683-3","article-title":"Reference ranges (\u201cnormal values\u201d) for cardiovascular magnetic resonance (CMR) in adults and children: 2020 update","volume":"22","author":"Hetzel","year":"2020","journal-title":"J. Cardiovasc. Magn. Reson."},{"key":"ref_17","unstructured":"Chollet, F. (2017). Deep Learning with Python, Manning Publications. Chapter 5."},{"key":"ref_18","unstructured":"Simonyan, K., and Zisserman, A. (2014). Very Deep Convolutional Network for Large Scale Image Recognition. arXiv."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","article-title":"Grad-CAM: Visual Explanations from Deep Networks via Gradient-Based Localization","volume":"128","author":"Selvaraju","year":"2019","journal-title":"Int. J. Comput. Vis."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"1839","DOI":"10.1038\/s41598-021-81525-9","article-title":"Evaluation of transfer learning in deep convolutional neural network models for cardiac short axis slice classification","volume":"11","author":"Ho","year":"2021","journal-title":"Sci. Rep."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Kim, I., Rajaraman, S., and Antani, S. (2019). Visual Interpretation of Convolutional Neural Network Predictions in Classifying Medical Image Modalities. Diagnostics, 9.","DOI":"10.3390\/diagnostics9020038"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"665","DOI":"10.1038\/s42256-020-00257-z","article-title":"Shortcut Learning in Deep Neural Networks","volume":"2","author":"Geirhos","year":"2020","journal-title":"Nat. Mach. Intell."},{"key":"ref_23","unstructured":"Oakden-Rayner, L., Dunnmon, J., Carneiro, G., and R\u00e9, C. (, January April). Hidden Stratification Causes Clinically Meaningful Failures in Machine Learning for Medical Imaging. Proceedings of the ACM Conference of Health, Inference, and Learning, Toronto, ON, Canada. https:\/\/arxiv.org\/abs\/1909.12475."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"80","DOI":"10.1016\/j.media.2019.06.001","article-title":"Explainable cardiac pathology classification on cine MRI with motion characterization by semi-supervised learning of apparent flow","volume":"56","author":"Zheng","year":"2019","journal-title":"Med. Image Anal."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"103356","DOI":"10.1016\/j.compbiomed.2019.103356","article-title":"Cine MRI analysis by deep learning of optical flow: Adding the temporal dimension","volume":"111","author":"Yan","year":"2019","journal-title":"Comput. Biol. Med."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"1946","DOI":"10.1016\/j.jcmg.2018.11.024","article-title":"Radiomic Analysis of Myocardial Native T1 Imaging Discriminates Between Hypertensive Heart Disease and Hypertrophic Cardiomyopathy","volume":"12","author":"Neisius","year":"2019","journal-title":"J. Am. Coll. Cardiol. Img."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"78","DOI":"10.1016\/j.ejrad.2017.04.024","article-title":"Differentiation between acute and chronic myocardial infarction by means of texture analysis of late gadolinium enhancement and cine cardiac magnetic resonance imaging","volume":"92","author":"Larroza","year":"2017","journal-title":"Eur. J. Radiol."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"e12246","DOI":"10.1097\/MD.0000000000012246","article-title":"Texture analysis of magnetic resonance T1 mapping with dilated cardiomyopathy: A machine learning approach","volume":"97","author":"Shao","year":"2018","journal-title":"Medicine"}],"container-title":["Diagnostics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2075-4418\/11\/9\/1554\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,11]],"date-time":"2025-10-11T06:53:40Z","timestamp":1760165620000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2075-4418\/11\/9\/1554"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,8,27]]},"references-count":28,"journal-issue":{"issue":"9","published-online":{"date-parts":[[2021,9]]}},"alternative-id":["diagnostics11091554"],"URL":"https:\/\/doi.org\/10.3390\/diagnostics11091554","relation":{},"ISSN":["2075-4418"],"issn-type":[{"value":"2075-4418","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,8,27]]}}}