Diagnostic utility of artificial intelligence for left ventricular scar identification using cardiac magnetic resonance imaging—A systematic review

BackgroundAccurate, rapid quantification of ventricular scar using cardiac magnetic resonance imaging (CMR) carries importance in arrhythmia management and patient prognosis. Artificial intelligence (AI) has been applied to other radiological challenges with success.ObjectiveWe aimed to assess AI methodologies used for left ventricular scar identification in CMR, imaging sequences used for training, and its diagnostic evaluation.MethodsFollowing PRISMA recommendations, a systematic search of PubMed, Embase, Web of Science, CINAHL, OpenDissertations, arXiv, and IEEE Xplore was undertaken to June 2021 for full-text publications assessing left ventricular scar identification algorithms. No pre-registration was undertaken. Random-effect meta-analysis was performed to assess Dice Coefficient (DSC) overlap of learning vs predefined thresholding methods.ResultsThirty-five articles were included for final review. Supervised and unsupervised learning models had similar DSC compared to predefined threshold models (0.616 vs 0.633, P = .14) but had higher sensitivity, specificity, and accuracy. Meta-analysis of 4 studies revealed standardized mean difference of 1.11; 95% confidence interval -0.16 to 2.38, P = .09, I2 = 98% favoring learning methods.ConclusionFeasibility of applying AI to the task of scar detection in CMR has been demonstrated, but model evaluation remains heterogenous. Progression toward clinical application requires detailed, transparent, standardized model comparison and increased model generalizability. Accurate, rapid quantification of ventricular scar using cardiac magnetic resonance imaging (CMR) carries importance in arrhythmia management and patient prognosis. Artificial intelligence (AI) has been applied to other radiological challenges with success. We aimed to assess AI methodologies used for left ventricular scar identification in CMR, imaging sequences used for training, and its diagnostic evaluation. Following PRISMA recommendations, a systematic search of PubMed, Embase, Web of Science, CINAHL, OpenDissertations, arXiv, and IEEE Xplore was undertaken to June 2021 for full-text publications assessing left ventricular scar identification algorithms. No pre-registration was undertaken. Random-effect meta-analysis was performed to assess Dice Coefficient (DSC) overlap of learning vs predefined thresholding methods. Thirty-five articles were included for final review. Supervised and unsupervised learning models had similar DSC compared to predefined threshold models (0.616 vs 0.633, P = .14) but had higher sensitivity, specificity, and accuracy. Meta-analysis of 4 studies revealed standardized mean difference of 1.11; 95% confidence interval -0.16 to 2.38, P = .09, I2 = 98% favoring learning methods. Feasibility of applying AI to the task of scar detection in CMR has been demonstrated, but model evaluation remains heterogenous. Progression toward clinical application requires detailed, transparent, standardized model comparison and increased model generalizability.