Deep‐Learning‐Based Disease Classification in Patients Undergoing Cine Cardiac MRI

• Published in: Journal of magnetic resonance imaging Vol. 61; no. 4; pp. 1635 - 1647
• Main Authors: Jacob, Athira J., Chitiboi, Teodora, Schoepf, U. Joseph, Sharma, Puneet, Aldinger, Jonathan, Baker, Charles, Lautenschlager, Carla, Emrich, Tilman, Varga‐Szemes, Akos
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.04.2025; Wiley Subscription Services, Inc
• Subjects: Accuracy; Adult; Aged; Algorithms; Cardiomyopathy; Cardiomyopathy, Dilated - diagnostic imaging; Cardiomyopathy, Hypertrophic - diagnostic imaging; Cardiovascular diseases; Classification; Confidence intervals; Deep Learning; Dilated cardiomyopathy; Disease; disease classification; Feature extraction; Female; Field strength; Heart - diagnostic imaging; Heart diseases; Heart Ventricles - diagnostic imaging; Humans; Image Interpretation, Computer-Assisted - methods; Image Processing, Computer-Assisted - methods; Ischemia; Labels; Machine learning; Magnetic resonance imaging; Magnetic Resonance Imaging, Cine - methods; Male; Middle Aged; model interpretability; Myocardial Ischemia - diagnostic imaging; myocardial strain; Population studies; Reproducibility of Results; Retrospective Studies; Sensitivity and Specificity; Statistical analysis; Statistical tests; Ventricle; deep learning; myocardial strain; model interpretability; disease classification
• DOI: 10.1002/jmri.29619
• ISSN: 1053-1807; 1522-2586

Background Automated approaches may allow for fast, reproducible clinical assessment of cardiovascular diseases from MRI. Purpose To develop an MRI‐based deep learning (DL) disease classification algorithm to distinguish among normal subjects (NORM), patients with dilated cardiomyopathy (DCM), hypertrophic cardiomyopathy (HCM), and ischemic heart disease (IHD). Study Type Retrospective. Population A total of 1337 subjects (55% female), comprising normal subjects (N = 568), and patients with DCM (N = 151), HCM (N = 177), and IHD (N = 441). Field Strength/Sequence Balanced steady‐state free precession cine sequence at 1.5/3.0 T. Assessment Bi‐ventricular morphological and functional features and global and segmental left ventricular strain features were automatically extracted from short‐ and long‐axis cine images. Variational autoencoder models were trained on the extracted features and compared against consensus disease label provided by two expert readers (13 and 14 years of experience). Adding unlabeled, normal data to the training was explored to increase specificity of NORM class. Statistical Tests Tenfold cross‐validation for model development; mean, standard deviation (SD) for measurements; classification metrics: area under the curve (AUC), confusion matrix, accuracy, specificity, precision, recall; 95% confidence intervals; Mann–Whitney U test for significance. Results AUCs of 0.952 for NORM, 0.881 for DCM, 0.908 for HCM, and 0.856 for IHD and overall accuracy of 0.778 were obtained, with specificity of 0.908 for the NORM class using both SAX and LAX features. Longitudinal strain features slightly improved classification metrics by 0.001 to 0.03 points, except for HCM‐AUC. Differences in accuracy, metrics for NORM class and HCM‐AUC were statistically significant. Cotraining using unlabeled data increased the specificity for the NORM class to 0.961. Data Conclusion Cardiac function features automatically extracted from cine MRI have potential to be used for disease classification, especially for normal‐abnormal classification. Feature analyses showed that strain features were important for disease labeling. Cotraining using unlabeled data may help to increase specificity for normal‐abnormal classification. Level of Evidence 3 Technical Efficacy Stage 1