Deep Learning for Discrimination of Hypertrophic Cardiomyopathy and Hypertensive Heart Disease on MRI Native T1 Maps

• Published in: Journal of magnetic resonance imaging Vol. 59; no. 3; pp. 837 - 848
• Main Authors: Wang, Zi‐Chen, Fan, Zhang‐Zhengyi, Liu, Xi‐Yuan, Zhu, Ming‐Jie, Jiang, Shan‐Shan, Tian, Song, Chen, Bing‐Hua, Wu, Lian‐Ming
• Format: Journal Article
• Language: English
• Published: Hoboken, USA John Wiley & Sons, Inc 01.03.2024; Wiley Subscription Services, Inc
• Subjects: Cardiomyopathy; Cardiomyopathy, Hypertrophic; Cardiovascular disease; Cardiovascular diseases; Deep Learning; Diagnostic systems; Differential diagnosis; Feasibility; Feature extraction; Field strength; Heart Diseases; Humans; Hypertension; hypertensive heart disease; hypertrophic cardiomyopathy; Machine learning; magnetic resonance imaging; Magnetic Resonance Imaging - methods; Male; Mapping; Medical imaging; Middle Aged; Performance evaluation; Population studies; Radiomics; Retrospective Studies; Statistical analysis; Statistical tests; deep learning; hypertensive heart disease; magnetic resonance imaging; hypertrophic cardiomyopathy
• ISSN: 1053-1807; 1522-2586; 1522-2586
• DOI: 10.1002/jmri.28904

Background Native T1 and radiomics were used for hypertrophic cardiomyopathy (HCM) and hypertensive heart disease (HHD) differentiation previously. The current problem is that global native T1 remains modest discrimination performance and radiomics requires feature extraction beforehand. Deep learning (DL) is a promising technique in differential diagnosis. However, its feasibility for discriminating HCM and HHD has not been investigated. Purpose To examine the feasibility of DL in differentiating HCM and HHD based on T1 images and compare its diagnostic performance with other methods. Study Type Retrospective. Population 128 HCM patients (men, 75; age, 50 years ± 16) and 59 HHD patients (men, 40; age, 45 years ± 17). Field Strength/Sequence 3.0T; Balanced steady‐state free precession, phase‐sensitive inversion recovery (PSIR) and multislice native T1 mapping. Assessment Compare HCM and HHD patients baseline data. Myocardial T1 values were extracted from native T1 images. Radiomics was implemented through feature extraction and Extra Trees Classifier. The DL network is ResNet32. Different input including myocardial ring (DL‐myo), myocardial ring bounding box (DL‐box) and the surrounding tissue without myocardial ring (DL‐nomyo) were tested. We evaluate diagnostic performance through AUC of ROC curve. Statistical Tests Accuracy, sensitivity, specificity, ROC, and AUC were calculated. Independent t test, Mann–Whitney U‐test and Chi‐square test were adopted for HCM and HHD comparison. P < 0.05 was considered statistically significant. Results DL‐myo, DL‐box, and DL‐nomyo models showed an AUC (95% confidential interval) of 0.830 (0.702–0.959), 0.766 (0.617–0.915), 0.795 (0.654–0.936) in the testing set. AUC of native T1 and radiomics were 0.545 (0.352–0.738) and 0.800 (0.655–0.944) in the testing set. Data Conclusion The DL method based on T1 mapping seems capable of discriminating HCM and HHD. Considering diagnostic performance, the DL network outperformed the native T1 method. Compared with radiomics, DL won an advantage for its high specificity and automated working mode. Level of Evidence 4 Technical Efficacy Stage 2