A cascade approach for the early detection and localization of myocardial infarction in 2D-echocardiography

Abstract

Myocardial infarction (MI) detection and localization through echocardiography are crucial for effective patient management. However, current diagnostic approaches rely heavily on visual assessment, which can be subjective. In this work we developed a cascade framework for automated MI diagnosis and localization in echocardiograms. Our method combines deep learning for left ventricle wall segmentation with machine learning classification using clinically relevant features. Specifically, we employ a U-Net architecture for segmentation, followed by a two-stage Random Forest classifier for MI detection and localization. We trained and evaluated our approach on two public datasets – CAMUS and HMC-QU. The proposed method achieved 100 % sensitivity and 89.8 % specificity for segment identification, outperforming single-stage classification methods. To the best of our knowledge, this is the first study to apply a multi-step artificial intelligence system combining segmentation and classification for MI diagnosis from echocardiography. This interpretable cascade framework exhibits high performance for early detection and localization of myocardial infarction, demonstrating potential as a clinical decision support tool.