Automatic Myocardial Disease Prediction From Delayed-Enhancement Cardiac MRI and Clinical Information

TL;DR

This paper introduces deep learning models that automatically predict myocardial diseases using DE-CMR images and clinical data, achieving high accuracy and demonstrating the value of combining imaging with metadata.

Contribution

The work presents novel neural network architectures that integrate DE-CMR imaging and clinical information for improved myocardial disease classification.

Findings

Classification accuracy exceeds 85% with neural networks.

Incorporating DE-CMR data boosts accuracy to 95-100%.

Deep learning effectively supports myocardial disease diagnosis.

Abstract

Delayed-enhancement cardiac magnetic resonance (DE-CMR)provides important diagnostic and prognostic information on myocardial viability. The presence and extent of late gadolinium enhancement (LGE)in DE-CMR is negatively associated with the probability of improvement in left ventricular function after revascularization. Moreover, LGE findings can support the diagnosis of several other cardiomyopathies, but their absence does not rule them out, making disease classification by visual assessment difficult. In this work, we propose deep learning neural networks that can automatically predict myocardial disease from patient clinical information and DE-CMR. All the proposed networks achieve very good classification accuracy (>85%). Including information from DE-CMR (directly as images or as metadata following DE-CMR segmentation) is valuable in this classification task, improving the accuracy to 95-100%.