Artificial Intelligence and Machine Learning Approaches for Automated Interpretation Across Echocardiography, Cardiac CT, and Cardiac MRI: A Systematic Review

Cardiovascular imaging has witnessed transformative advancements through artificial intelligence (AI) and machine learning (ML), yet the integration of these technologies across multiple modalities remains underexplored. This systematic review synthesizes evidence on AI/ML approaches for automated interpretation across echocardiography, cardiac computed tomography (CT), and cardiac magnetic resonance imaging (MRI), with a focus on clinically relevant tasks. Following PRISMA guidelines, we conducted a PubMed search (۲۰۱۷–۲۰۲۵), identifying ۱,۰۹۱ records. After rigorous screening, six studies (five reviews, one empirical) met inclusion criteria. Our analysis revealed that while deep learning dominates cardiac CT and MRI applications—particularly for segmentation and disease classification—echocardiography lags in empirical validation. The sole empirical study benchmarked AI performance across CT and MRI but excluded echocardiography, highlighting a critical gap in multi-modality research. Review articles consistently emphasized the potential of AI but noted persistent challenges, including data standardization, external validation, and clinical integration. Key limitations include the predominance of single-modality studies and a lack of head-to-head comparisons between traditional ML and deep learning methods. Future research should prioritize unified frameworks encompassing all three modalities, robust clinical validation, and standardized performance metrics to bridge these gaps. This review underscores AI’s transformative potential in cardiac imaging while advocating for more comprehensive, clinically grounded studies to realize its full impact.

Keywords:

Artificial intelligence , Cardiac Imaging , Multi-modality , Deep Learning , Machine Learning