基于误差反向传播神经网络的胃癌细胞识别研究  

Research on Recognizing Gastric Cancer Cell Based on Back Propagation Neural Network

作　　者：陈先来[1] 肖晓旦[1] 杨荣[2] 刘建平[3] 

机构地区：[1]中南大学湘雅医学院 [2]中南大学湘雅医院胃肠外科,长沙410078 [3]国防科技大学机电工程与自动化学院,长沙410073

出　　处：《中国循证医学杂志》2007年第9期637-640,共4页Chinese Journal of Evidence-based Medicine

基　　金：国防科技大学机电工程与自动化学院创新基金"胃癌细胞识别知识库的自动创建";湖南省社会科学基金"临床决策信息环境的研究"(编号:06ZC92)

摘　　要：目的探讨误差反向传播(backpro pagation,BP)神经网络在胃癌细胞识别中的应用价值。方法在308例胃切除病例的胃组织切片中选取510个胃细胞,其中腺癌细胞210个,非癌性细胞300个,测量细胞的10个形态学特征。将所得到的数据随机分成A组(训练组)和B组(测试组)。建立三层BP神经网络,并利用A组数据对神经网络进行训练,再利用A、B两组数据对网络模型进行检验测试。结果BP神经网络对A组细胞识别的灵敏度为99%,特异度为99%,阳性预测值为98%,阴性预测值为99%,识别正确率为98%;对B组细胞识别的灵敏度为99%,特异度为97%,阳性预测值为96%,阴性预测值为99%,识别正确率为98%。ROC曲线下面积为0.99。结论本研究结果显示,BP神经网络用于胃癌细胞识别非常有效,可用于胃癌细胞的自动识别。Objective To investigate the value of back propagation （BP） neural network for recognizing gastriccancer cell. Methods A total of 510 cells was selected from 308 patients. There were 210 gastricadenocarcinoma cells and 300 non-cancer gastriccells. Ten morphological parameters were measured for each cell. These data were randomly divided into two groups： training dataset （A） and test dataset （B）. A threelayer BPneural network was built and trained by using dataset A. The network was then tested with dataset A and B. Results For data A, the sensitivity of network was 99%, specificity 99%, positive predictive value 98%, negative predictive value 99%, and accuracy 99%, For data B, the sensitivity of network was 99%, specificity 97%, positive predictive value 96%, negative predictive value 99%, the accuracy 98%. With receiver operator characteristic（ROC） curve evaluation, the area under ROC curve was 0.99. Conclusion The model based on BP neural network is very effective. A BPneural network can be used for effectively recognizing gastric cancer cell.

关 键 词：基于误差反向传播神经网络 胃肿瘤 细胞识别 

分 类 号：R735.2[医药卫生—肿瘤]