Computer-Aided Diagnosis of Myocardial Infarction Using Ultrasound Images with Second-Order Statistics, DWT and HOS Methods: A Comparative Study

Ng Yin Kwee博士，南洋理工大学，新加坡

摘要: Myocardial Infarction (MI) or heart attack is the most common type of coronary heart disease (CHD) and is the leading cause of cardiac death worldwide. Precise and timely identification of MI and extent of muscle damage helps in early treatment and reduction in the time taken for further tests. MI diagnosis using 2D echocardiography is prone to inter/intra observer variability in the assessment. Therefore, a computerised scheme based on image processing and artificial intelligent techniques can reduce the workload of clinicians and improve the diagnosis accuracy. A Computer-Aided Diagnosis (CAD) of infarcted and normal ultrasound images will be useful for clinicians.

In this talk, I will first discuss the application of various texture analysis methods to accurately extract the features and detect normal and infarcted myocardium using echocardiography images. In this work, the performance of CAD approach using DWT, second order statistics calculated from Gray-Level Co-Occurrence Matrix (GLCM) and Higher Order Spectra (HOS) texture descriptors are compared. The proposed system is validated using 1600 MI and 1600 normal ultrasound images, obtained from 80 patients with MI and 80 normal subjects respectively. The extracted features are ranked based on t-value and fed to the Support Vector Machine (SVM) classifier, to obtain the best performance using minimum number of features. The features extracted from DWT coefficients obtained an accuracy of 98.8%, sensitivity of 98.5%, specificity of 99%; GLCM have achieved an accuracy of 92.1%, sensitivity of 88.1%, specificity of 96%; and HOS obtained an accuracy of 98.6%, sensitivity of 98.0%, specificity of 99.2%. Among the three techniques presented HOS texture descriptor yielded the highest classification accuracy. Thus proposed CAD approach may be used as an adjunct tool to assist cardiologists in making a more accurate diagnosis on the presence of MI in hospitals and polyclinics.