基于Cycle-GAN和改进DPN网络的乳腺癌病理图像分类

张雪芹,李天任

Breast cancer pathological image classification based on Cycle-GAN and improved DPN network

Xue-qin ZHANG,Tian-ren LI

表 3 不同归一化方法下良恶性分类准确率对比

Tab.3 Comparison of accuracy of benign and malignant classification under different normalization methods

% 方法 FPR FNR Recall Precision F1-score I 无归一化 24.4 8.9 90.0 78.64 83.94 83.33 Vahadane法归一化 13.3 4.4 95.5 87.76 91.47 91.11 Cycle-GAN归一化 10.0 3.3 96.7 90.63 93.56 93.33