激光与光电子学进展, 2020, 57 (22): 221021, 网络出版: 2020-11-12
基于改进ResNeXt的乳腺癌组织病理学图像分类 下载: 1045次
Breast Cancer Histopathological Image Classification Based on Improved ResNeXt
图像处理 组织病理图像 卷积神经网络 残差网络 八度卷积 异构卷积 image processing histopathological images convolution neural network residual network octave convolution heterogeneous convolution
摘要
为实现对乳腺癌组织病理图像的准确自动分级,提出了一种改进的卷积神经网络,依次引入两种不同的卷积结构,以提高网络对病理图像的识别准确率。以深度残差网络(ResNeXt)为基础网络,用八度卷积(OctConv)替代传统卷积层,在特征提取阶段降低特征图中的冗余特征,提高了细节特征的提取效果;用异构卷积(HetConv)代替网络中的部分传统卷积层,以降低模型的训练参数。为了克服因数据样本较少出现的过拟合问题,采用一种基于图像分块思想的数据增强方法。实验结果表明,该网络在图像级别的四分类任务中准确率达到91.25%,表明所设计的网络模型具有较高的识别率和较好的实时性。
Abstract
In this paper, to achieve accurate automatic classification of breast cancer histopathological images, an improved convolutional neural network is proposed, and two different convolutional structures are introduced in order to improve the accuracy of histopathological image recognition by the network. Based on using deep residual network (ResNeXt) as basic network, octave convolution (OctConv) is used to replace the traditional convolutional layer to reduce the redundant features in the feature map during feature extraction stage and improve the effect of detailed feature extraction. Heterogeneous convolution (HetConv) is introduced to replace part of the traditional convolutional layers in the network, reducing model training parameters. To overcome the problem of over-fitting due to the small number of data samples, an effective data enhancement method based on the idea of image block is adopted. The experimental results demonstrate that the accuracy of the network on the four classification tasks of the network at the image level reaches 91.25%, indicating that the designed network model has a higher recognition rate and a better real-time performance.
牛学猛, 吕晓琪, 谷宇, 张宝华, 张明, 任国印, 李菁. 基于改进ResNeXt的乳腺癌组织病理学图像分类[J]. 激光与光电子学进展, 2020, 57(22): 221021. Xuemeng Niu, Xiaoqi Lü, Yu Gu, Baohua Zhang, Ming Zhang, Guoyin Ren, Jing Li. Breast Cancer Histopathological Image Classification Based on Improved ResNeXt[J]. Laser & Optoelectronics Progress, 2020, 57(22): 221021.