Divide-and-Attention Network for HE-Stained Pathological Image Classification

doi:10.3390/biology11070982

	Divide-and-Attention Network for HE-Stained Pathological Image Classification
	Yan, Rui 1,2; Yang, Zhidong 1; Li, Jintao 1; Zheng, Chunhou 3; Zhang, Fa 1
	2022-07-01
发表期刊	BIOLOGY-BASEL
卷号	11 期号:7 页码:17
摘要	Simple Summary We propose a Divide-and-Attention network that can learn representative pathological image features with respect to different tissue structures and adaptively focus on the most important ones. In addition, we introduce deep canonical correlation analysis constraints in the feature fusion process of different branches, so as to maximize the correlation of different branches and ensure that the fused branches emphasize specific tissue structures. Extensive experiments on three different pathological image datasets show that the proposed method achieved competitive results. Since pathological images have some distinct characteristics that are different from natural images, the direct application of a general convolutional neural network cannot achieve good classification performance, especially for fine-grained classification problems (such as pathological image grading). Inspired by the clinical experience that decomposing a pathological image into different components is beneficial for diagnosis, in this paper, we propose a Divide-and-Attention Network (DANet) for Hematoxylin-and-Eosin (HE)-stained pathological image classification. The DANet utilizes a deep-learning method to decompose a pathological image into nuclei and non-nuclei parts. With such decomposed pathological images, the DANet first performs feature learning independently in each branch, and then focuses on the most important feature representation through the branch selection attention module. In this way, the DANet can learn representative features with respect to different tissue structures and adaptively focus on the most important ones, thereby improving classification performance. In addition, we introduce deep canonical correlation analysis (DCCA) constraints in the feature fusion process of different branches. The DCCA constraints play the role of branch fusion attention, so as to maximize the correlation of different branches and ensure that the fused branches emphasize specific tissue structures. The experimental results of three datasets demonstrate the superiority of the DANet, with an average classification accuracy of 92.5% on breast cancer classification, 95.33% on colorectal cancer grading, and 91.6% on breast cancer grading tasks.
关键词	pathological image classification attention mechanism convolutional neural network knowledge embedding
DOI	10.3390/biology11070982
收录类别	SCI
语种	英语
资助项目	Strategic Priority Research Program of the Chinese Academy of Sciences[XDA16021400] ; National Key Research and Development Program of China[2021YFF0704300] ; NSFC[61932018] ; NSFC[62072441] ; NSFC[62072280]
WOS研究方向	Life Sciences & Biomedicine - Other Topics
WOS类目	Biology
WOS记录号	WOS:000831586600001
出版者	MDPI
引用统计	被引频次：5[WOS] [WOS记录] [WOS相关记录]
文献类型	期刊论文
条目标识符	http://119.78.100.204/handle/2XEOYT63/19485
专题	中国科学院计算技术研究所期刊论文_英文
通讯作者	Zheng, Chunhou; Zhang, Fa
作者单位	1.Chinese Acad Sci, Inst Comp Technol, High Performance Comp Res Ctr, Beijing 100045, Peoples R China 2.Univ Chinese Acad Sci, Beijing 101408, Peoples R China 3.Anhui Univ, Sch Artificial Intelligence, Hefei 230093, Peoples R China
推荐引用方式 GB/T 7714	Yan, Rui,Yang, Zhidong,Li, Jintao,et al. Divide-and-Attention Network for HE-Stained Pathological Image Classification[J]. BIOLOGY-BASEL,2022,11(7):17.
APA	Yan, Rui,Yang, Zhidong,Li, Jintao,Zheng, Chunhou,&Zhang, Fa.(2022).Divide-and-Attention Network for HE-Stained Pathological Image Classification.BIOLOGY-BASEL,11(7),17.
MLA	Yan, Rui,et al."Divide-and-Attention Network for HE-Stained Pathological Image Classification".BIOLOGY-BASEL 11.7(2022):17.