Breast cancer histopathology image classification based on dual-stream high-order network
Breast cancer histopathology image classification based on dual-stream high-order network
复制标题
DOI：
10.1016/j.bspc.2022.104007
复制
发表时间：
2022-09
期刊：
影响因子：
--
通讯作者：
Y. Zou;Shannan Chen;Chao Che;Jianxin Zhang;Qiang Zhang
中科院分区：
文献类型：
--
作者：
Y. Zou;Shannan Chen;Chao Che;Jianxin Zhang;Qiang Zhang
利用病理图像对乳腺癌进行早期诊断具有重要意义。近年来，随着计算机辅助诊断技术的发展，基于卷积神经网络（CNN）的乳腺癌组织病理学图像分类方法也在不断创新。为了获得具有更强判别表示能力的病理组织特征用于分类，提出了一种新的双流高阶乳腺癌病理图像分类网络DsHoNet。首先构建一个由6个卷积层组成的浅层网络作为双流网络的骨干，其中一个流利用批归一化（BN）层保留原始特征信息，特征分布更加清晰;另一个流引入Ghost模块，利用一系列线性变换提取更丰富的补充特征。然后，通过协方差池化层进一步增强两个流的输出，以实现更强大的深度高阶统计特征用于分类。在公开的BreakHis数据集上进行的大量评估实验表明，DsHoNet在图像级和患者级的最佳识别率分别为99.01%和99.25%，与同类产品相比表现良好。
The early diagnosis of breast cancer using pathological images is of the vital importance. Recently, breast cancer histopathology image classification methods based on convolution neural network (CNN) are constantly innovating with the development of computer-aided diagnosis technology. To obtain pathological tissue features with more discriminant presentation capability for classification, this work proposes a novel dual-stream high-order breast cancer pathological image classification network named DsHoNet. To be precise, a shallow network composed of six convolution layers is built as the backbone of the dual-stream network firstly, in which one stream utilizes batch normalization (BN) layer to retain the original feature information with clearer feature distribution, while another stream introduces the Ghost module to extract richer supplementary features by utilizing a series of linear transformations. Then, outputs of the two streams are further enhanced via a covariance pooling layer to achieve more powerful deep high-order statistic features for classification. Extensive evaluation experiments carried out on the public BreakHis dataset demonstrate that the optimal recognition rates of DsHoNet are 99.01% and 99.25% respectively at the image-level and patient-level, performing favorably against its counterparts.