Biomarker for detecting myocardial ischemia using multi class particle swarm optimization

ABSTRACT

Coronary Heart Disease is one of the life threats to mankind when the arteries become too narrow because of cholesterol blockages in the walls. When the blood flow to the heart is reduced by preventing the heart muscle from receiving enough oxygen, myocardial ischemia will occur. In this research work, analyzing was performed for the wall motion of the Left Ventricle. This work will be executed in three steps. The first step is to detect LV Border area. In the second step, shape, structural information are extracted and the best information is selected by using the B4 method. In the Third Step, the system will classify the disease category using MPSO – IWM, AWMI, LVD, CMP, IVS and normal. The system is validated using anatomical structure of Heart and medical rules as described by doctors and obtained an accuracy of 93.2%, Sensitivity of 94%, and Specificity of 91.5%.

KEYWORDS:

• Feature extraction
• feature selection
• classification

Disclosure statement

No potential conflict of interest was reported by the author(s).

Additional information

Notes on contributors

G. Wiselin Jiji

Dr G. Wiselin Jiji is a professor of computer science and engineering at Dr. Sivanthi Aditanar College of Engineering, Tiruchendur. She has published more than 100 scientific research papers. She is a recipient of 10 national and three state awards. Her long-term research focuses on Computer-Aided Detection (CAD) and Measurement (CAM) of lesions in medical images. CAD research aims at discovering the fundamental perception processes of human vision in the image-based diagnosis of lesions and developing mathematical/computational models that describes them. Her area of interests is computer-aided detection and diagnosis of abnormality using medical images and medical image analysis such as image enhancement, segmentation, feature extraction, object detection and pattern recognition.