A Genetic-Algorithm-Based Method for Optimization of Fuzzy Reasoning and Its Application to Classification of Heart Disease from Ultrasonic Images (特集:画像処理技術の新産業応用)
スポンサーリンク
概要
- 論文の詳細を見る
This paper describes a method for optimizing the parameters of fuzzy rules using genetic algorithms (GAs) for classification of myocardial heart disease from ultrasonic images. Gaussian-distributed membership functions (GDMFs) constructed from the texture features inherent in the ultrasound images are used, and the coefficients acted as a set of parameters to adjust the magnitudes of the standard deviations of the GDMFs are employed. Optimal coefficients are determined through training process using the GA. The GA-based fuzzy classifier is used to discriminate two sets of echocardiographic images, namely, normal case (23 samples) and abnormal case (22 samples), diagnosed by a highly trained physician. The results of our experiments are very promising. In the best case, we achieve a classification rate of 95.8%. The results indicate that the method has potential utility for computer-aided diagnosis of myocardial heart disease.
- 社団法人 電気学会の論文
著者
関連論文
- Breast Tumor Classification by Neural Networks Fed with Sequential-Dependence Factors to the Input Layer
- Feature-Based Image Analysis for Classification of Echocardiographic Images
- Evaluation of Radiographic Images by Using Sequential Dependency
- An Improved Algorithm for Automated Detection of Ventricular Contours from Cardiac Magnetic Resonance Images (特集:生体に関する信号および画像処理)
- A Computer-Aided System for Discrimination of Dilated Cardiomyopathy Using Echocardiographic Images
- Automatic Segmentation of Liver Structure in CT Images Using a Neural Network (Special Section of Letters Selected from the 1994 IEICE Spring Conference)
- A Genetic-Algorithm-Based Method for Optimization of Fuzzy Reasoning and Its Application to Classification of Heart Disease from Ultrasonic Images (特集:画像処理技術の新産業応用)