基于人工神经网络的诊断模型对针吸细胞学诊断小细胞型乳腺癌的应用研究  

The application study based on the artificial neural network diagnostic model for differentiate diagnosis small cell mammary carcinoma with the cell form stereological quantitative parameters by fine needle aspiration cytology

作　　者：龚平[1] 郭华雄[1] 王文清[1] 王杏红[1] 李春燕[1] 赵廷宽[1] 

机构地区：[1]华中科技大学同济医学院附属荆州医院,434020

出　　处：《中国体视学与图像分析》2008年第2期98-101,共4页Chinese Journal of Stereology and Image Analysis

基　　金：湖北省荆州市重点科学项目资助(No.20072PE1-1)

摘　　要：目的探讨人工神经网络(ANN)诊断模型对小细胞型乳腺癌的针吸细胞学诊断价值。方法利用MPIAS-2000系统对60例乳腺癌及30例乳腺良性病变针吸细胞的29项形态定量参数进行定量分析,建立人工神经网络诊断模型,对19例小细胞型乳腺癌进行人工神经网络诊断模型的判别分析。结果人工神经网络诊断模型对小细胞乳腺癌及良性病变的诊断特异性为100%,敏感性为84.2%。结论利用乳腺癌针吸细胞形态定量的人工神经网络诊断模型,对辅助针吸细胞学诊断小细胞型乳腺癌具有重要的参考价值。Objective To establish diagnostic models of cell form parameters in mammary carcinoma FNA＇s smears by an artificial neural network （ANN） methods,and apply the models to discriminate diagnosis of the small cell mammary cancer and benign lesion. Methods The cell form quantitative parameters of 60 breast cancer cases and 30 benign lesion cases were analysis by MPIAS-2000, all of cases were provided histology. The ANN diagnosis models of cancer and benign lesion were established combined with the 29 cell quantitative parameters. 19 small cell mammary cancers and 20 benign lesions cases were analyzed of blind test. Results The ANN model of cell form quantitative parameters had an sensitivity of 84.2% and specialty of 100 % for differentiation diagnosis of the small cell breast carcinoma. Conclusion Method of erecting models based on cell form quantitative parameters with ANN could identify small cell breast carcinoma and benign lesion. It may be valuable and new idea for FNA＇c in the differentiation of breast diseases.

关 键 词：针吸细胞学 细胞形态定量参数 人工神经网络 诊断模型 小细胞型乳腺癌 

分 类 号：R737.9[医药卫生—肿瘤]