Deep learning to diagnose cardiac amyloidosis from cardiovascular magnetic resonance

• Published in: Journal of cardiovascular magnetic resonance Vol. 22; no. 1; p. 84
• Main Authors: Martini, Nicola, Aimo, Alberto, Barison, Andrea, Della Latta, Daniele, Vergaro, Giuseppe, Aquaro, Giovanni Donato, Ripoli, Andrea, Emdin, Michele, Chiappino, Dante
• Format: Journal Article
• Language: English
• Published: England BioMed Central Ltd 07.12.2020; BioMed Central; Elsevier
• Subjects: Aged; Aged, 80 and over; Algorithms; Amyloid Neuropathies, Familial - diagnostic imaging; Amyloid Neuropathies, Familial - pathology; Amyloid Neuropathies, Familial - physiopathology; Amyloidosis; Artificial intelligence; Automation; Biopsy; Bisphosphonates; Blood; Cardiomyopathy, Hypertrophic - diagnostic imaging; Cardiomyopathy, Hypertrophic - pathology; Cardiomyopathy, Hypertrophic - physiopathology; Cardiovascular magnetic resonance; Chambers; Darkening; Deep Learning; Diagnosis; Diagnostic systems; Feature extraction; Female; Gadolinium; Heart; Heart enlargement; Humans; Hypertrophy; Hypertrophy, Left Ventricular - diagnostic imaging; Hypertrophy, Left Ventricular - pathology; Hypertrophy, Left Ventricular - physiopathology; Image enhancement; Image Processing, Computer-Assisted; Immunoglobulin Light-chain Amyloidosis - diagnostic imaging; Immunoglobulin Light-chain Amyloidosis - pathology; Immunoglobulin Light-chain Amyloidosis - physiopathology; Learning algorithms; Machine learning; Magnetic resonance; Magnetic Resonance Imaging, Cine; Male; Medical imaging equipment; Myocardium - pathology; Normal distribution; Pleural effusion; Predictive Value of Tests; Reproducibility of Results; Resonance; Scintigraphy; Strategy; Subgroups; Ultrasonic imaging; Ventricle; Ventricular Function, Left; Ventricular Remodeling; Work stations; United States > US; Deep learning; Amyloidosis; Diagnosis; Cardiovascular magnetic resonance; Artificial intelligence
• ISSN: 1097-6647; 1532-429X
• DOI: 10.1186/s12968-020-00690-4

Cardiovascular 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. 1.5 T CMR was performed in 206 subjects with suspected CA (n = 100, 49% with unexplained left ventricular (LV) hypertrophy; n = 106, 51% with blood dyscrasia and suspected light-chain amyloidosis). Patients were randomly assigned to the training (n = 134, 65%), validation (n = 30, 15%), and testing subgroups (n = 42, 20%). Short axis, 2-chamber, 4-chamber 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. The DL strategy displayed good diagnostic accuracy (88%), with an area under the curve (AUC) of 0.982. The precision (positive predictive value), recall score (sensitivity), and F1 score (a measure of test accuracy) were 83%, 95%, and 89% respectively. A ML algorithm considering all CMR features had a similar diagnostic yield to DL strategy (AUC 0.952 vs. 0.982; p = 0.39). 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.