70 Deep learning to diagnose cardiac amyloidosis from cardiac magnetic resonance findings

Abstract

Background. Cardiac magnetic resonance (CMR) is part of the diagnostic work-up for cardiac amyloidosis (CA). Deep learning (DL) is an application of artificial intelligence that may allow to automatically analyze CMR findings and establish the likelihood of CA. Methods. 1.5 T CMR was performed in 187 subjects with suspected CA (n=92, 49% with unexplained left ventricular-LV-hypertrophy; n=95, 51% with blood dyscrasia and suspected light-chain amyloidosis). Patients were randomly assigned to the training (n=121, 65%), validation (n=28, 15%), and testing subgroups (n=38, 20%). Short axis (SA), 2-chamber (2C), 4-chamber (4C) late gadolinium enhancement (LGE) images were evaluated by 3 networks (DL algorithms). The tags "amyloidosis present" or "absent" were attributed when the average probability of CA from the 3 networks was >=50% or <50%, respectively. The DL strategy was compared to a machine learning (ML) algorithm considering all manually extracted features (LV volumes, mass and function, LGE pattern, early blood-pool darkening, pericardial and pleural effusion, etc.), to reproduce exam reading by an experienced operator. Results. The DL strategy displayed good diagnostic accuracy (84%), with an area under the curve (AUC) of 0.96. The precision (positive predictive value), recall score (sensitivity), and F1 score (a measure of test accuracy) were 78%, 94%, and 86% respectively. A ML algorithm considering all CMR features had a similar diagnostic yield to DL strategy (AUC 0.93 vs. 0.96; p=0.45). Conclusions. A DL approach evaluating LGE acquisitions displayed a similar diagnostic performance for CA to a ML-based approach, which simulates CMR reading by experienced operators.