Integration of Cine-cardiac Magnetic Resonance Radiomics and Machine Learning for Differentiating Ischemic and Dilated Cardiomyopathy

• Published in: Academic radiology
• Main Authors: Deng, Jia, Zhou, Langtao, Li, Yueyan, Yu, Ying, Zhang, Jingjing, Liao, Bihong, Luo, Guanghua, Tian, Jinwei, Zhou, Hong, Tang, Huifang
• Format: Journal Article
• Language: English
• Published: United States 01.07.2024
• Subjects: Cardiomyopathy; Cine; Cardiac magnetic resonance; Machine learning; Radiomics
• ISSN: 1878-4046
• DOI: 10.1016/j.acra.2024.03.032

This study aims to evaluate the capability of machine learning algorithms in utilizing radiomic features extracted from cine-cardiac magnetic resonance (CMR) sequences for differentiating between ischemic cardiomyopathy (ICM) and dilated cardiomyopathy (DCM). This retrospective study included 115 cardiomyopathy patients subdivided into ICM (n = 64) and DCM cohorts (n = 51). We collected invasive clinical (IC), noninvasive clinical (NIC), and combined clinical (CC) feature subsets. Radiomic features were extracted from regions of interest (ROIs) in the left ventricle (LV), LV cavity (LVC), and myocardium (MYO). We tested 10 classical machine learning classifiers and validated them through fivefold cross-validation. We compared the efficacy of clinical feature-based models and radiomics-based models to identify the superior diagnostic approach. In the validation set, the Gaussian naive Bayes (GNB) model outperformed the other models in all categories, with areas under the curve (AUCs) of 0.879 for IC_GNB, 0.906 for NIC_GNB, and 0.906 for CC_GNB. Among the radiomics models, the MYO_LASSOCV_MLP model demonstrated the highest AUC (0.919). In the test set, the MYO_RFECV_GNB radiomics model achieved the highest AUC (0.857), surpassing the performance of the three clinical feature models (IC_GNB: 0.732; NIC_GNB: 0.75; CC_GNB: 0.786). Radiomics models leveraging MYO images from cine-CMR exhibit promising potential for differentiating ICM from DCM, indicating the significant clinical application scope of such models. The integration of radiomics models and machine learning methods utilizing cine-CMR sequences enhances the diagnostic capability to distinguish between ICM and DCM, minimizes examination risks for patients, and potentially reduces the duration of medical imaging procedures.