基于神经网络和模糊理论的心功能辅助诊断专家系统

COMPUTER-AIDED DIAGNOSIS SYSTEM FOR HEART FUNCTION BASED ON ARTIFICIAL NEURAL NETWORKS AND FUZZY THEORY

通过对大量心脏病典型病例之超声心动图指标参量进行分析与总结 ,并结合专家经验 ,提出了一种对心功能进行全面、定量分级的客观方法 ,采用将神经网络技术与模糊理论相结合的方法 ,研制出心功能辅助诊断专家系统 .该系统具有在线学习能力、可扩充性和较强的容错能力 .临床实验结果正确率达到 90 .7% 。

WT5”BZ]In this paper,a computer aided diagnosis system for heart function based on artificial neural networks and fuzzy logic is introduced.Sensitive parameters reflecting heart function,provided by echocardiography,were used as input of neural networks and their corresponding heart function as output.To obain an analytic and discrimination model closer to brain,we combined fuzzy theory with neural network technology.In our research input parameters were fuzzzily treated.During distinguishing the type of illness,we used fuzzy interval,fuzzy number and possibility distribution concepts,and got its corresponding membership.Meanwhile the membership was divided into interval of linguistic consisting with language expression.The selected network was BP,and back propagation algorithm was used to train the network.After studying the result evaluated by experts,the neural network was used to appreciate 150 testees heart function,of which 90.7 % was consistent with experts diagnosis. [WT5”HZ]