摘要
文章采用竞争Hopfield神经网络的自动聚类分割方法从腹水脱落细胞显微图像中分割可疑细胞和可疑细胞核,提取癌细胞的15个形态特征,利用柔性BP神经网络分类器对腹水脱落癌细胞进行分类识别。通过对临床病例的检验分析,表明该方法能获得较高的诊断正确率。
A competitive Hopfield neural network is used in this paper to segment suspected cell and nucleus from the complex background in the microscopic image of cells fallen into peritoneal effusion.15features of cancer cell are ab-stracted.These features are employed to construct a flexible BP neural network classifier,which classifies and recognizes the cancer cells fallen into peritoneal effusion.Tests are performed using clinic cases recommended by the pathologists,results show that the proposed algorithm can efficiently segment cell image and receive higher accuracy of cancer cell diagnosis.
出处
《计算机工程与应用》
CSCD
北大核心
2003年第36期214-216,共3页
Computer Engineering and Applications
基金
江苏省教育厅省属高校自然科学研究项目(编号:01KJB520004)
