Deep CNN with LM learning based myocardial ischemia detection in cardiac magnetic resonance images

• Published in: Conference proceedings (IEEE Engineering in Medicine and Biology Society. Conf.) Vol. 2019; pp. 824 - 827
• Main Authors: Muthulakshmi, M., Kavitha, G.
• Format: Conference Proceeding Journal Article
• Language: English
• Published: United States IEEE 01.07.2019
• Subjects: Algorithms; Convolutional neural networks; Deep learning; Heart; Humans; Machine learning algorithms; Magnetic Resonance Spectroscopy; Myocardial Ischemia - diagnostic imaging; Myocardium; Neural Networks, Computer; Training; Volume measurement
• ISSN: 1557-170X; 1558-4615
• DOI: 10.1109/EMBC.2019.8856838

Cardiovascular disease (CVD) is a chronic dysfunction caused by deterioration in cardiac physiology. It results in about 31% of mortality worldwide. Among CVDs, myocardial ischemia (MI) leads to restriction in blood supply to heart tissues. There is a need to develop an effective computer aided detection (CAD) system to reduce the fatality. In this work, an attempt is made to perform mass screening of myocardial ischemic subjects and left ventricle (LV) volume estimation from cardiac magnetic resonance (CMR) images using deep convolutional neural network (CNN) with Levenberg-Marquardt (LM) learning. LV volume measurement is an important predictor of myocardial ischemia. The CMR samples used in this analysis are obtained from Medical Image Computing and Computer Assisted Intervention (MICCAI) 2009 database. The results of the proposed model are compared with deep CNN based on gradient descent (GD) learning algorithm. The results show that deep CNN architecture with LM learning classifies ischemic subjects with high accuracy (86.39%) and sensitivity (90%). The LM learning based method gives an AUC of 0.93. The estimated LV volumes obtained from the trained network gives high correlation with the ground truth. Thus the results support that proposed framework of deep CNN architecture with LM learning can be used as an effective CAD system for diagnosis of cardiovascular disorders.