Diagnostic Accuracy of Radiomics Versus Visual or Threshold-Based Assessment for Myocardial Scar/Fibrosis Detection on Cardiac MRI: A Systematic Review

Background: Myocardial scar and fibrosis predict adverse cardiac outcomes. Late gadolinium enhancement (LGE) cardiac magnetic resonance (CMR) is the reference standard for detection. However, it requires gadolinium-based contrast agents (GBCAs), which may be unsuitable for some patients. Cine balanced steady-state free precession (bSSFP) sequences are universally acquired in routine CMR. They may enable contrast-free scar detection via radiomics analysis. Aim: To systematically review the diagnostic accuracy of cine CMR radiomics for myocardial scar or fibrosis detection. The reference standard is visual or threshold-based LGE. Methods: This review followed PRISMA guidelines and was registered in PROSPERO (CRD420251121699). We searched MEDLINE, Embase, and Cochrane Library up to 8 August 2025. Eligible studies compared cine CMR radiomics with LGE-based assessment in patients with suspected or known scar/fibrosis. Quality was assessed using QUADAS-2 and Radiomics Quality Score (RQS). Results: Five retrospective studies (n = 1484) were included. Two focused on myocardial infarction, two on hypertrophic cardiomyopathy, and one on ischaemic versus dilated cardiomyopathy. Diagnostic performance was good to excellent (AUC 0.74–0.96). Methodological heterogeneity was substantial in reference standards, segmentation, preprocessing, feature selection, and modelling. Only one study used external validation. QUADAS-2 showed high bias risk in patient selection and index test domains. RQS scores were low (30–42%), indicating limited reproducibility and validation. Conclusions: Cine CMR radiomics shows promise as a non-contrast alternative for detecting myocardial scar and fibrosis. However, methodological standardisation, multicentre validation, and prospective studies are needed before clinical adoption.