D.-Y. Tsai, Y. Lee, M. Sekiya, M. Ohkubo, K. Kojima, and I. Yamada (Japan)
medical image processing, integrated medical imageanalysis, computer-aided diagnosis, soft computing
This paper presents a fuzzy-GA-based computer-aided diagnosis scheme for disease discrimination. The scheme is applied to discriminate myocardial heart disease from echocardiographic images and to detect and classify clustered micro-calcifications from mammograms. Unlike the conventional types of membership functions, Gaussian-distributed membership functions (GDMFs) are employed in this study. The GDMFs are initially generated using various texture-based features obtained from reference images. Subsequently the shapes of GDMFs are optimized by genetic-algorithm learning process. After optimization, the classifier is used for disease discrimination. We evaluate the performance of the proposed method in terms of accuracy, sensitivity, and specificity. Experimental results show that the proposed scheme has potential utility for computer-aided diagnosis in disease classification.
Important Links:
Go Back
