Multi-Layer Pseudo-Supervision for histopathology Tissue semantic segmentation using patch-level classification labels

作     者：Han, Chu Lin, Jiatai Mai, Jinhai Wang, Yi Zhang, Qingling Zhao, Bingchao Chen, Xin Pan, Xipeng Shi, Zhenwei Xu, Xiaowei Yao, Su Yan, Lixu Lin, Huan Xu, Zeyan Huang, Xiaomei Han, Guoqiang Liang, Changhong Liu, Zaiyi 

作者机构：The Department of Radiology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou China Guangdong Cardiovascular Institute Guangzhou China The Department of Radiology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangdong Guangzhou510080 China The School of Computer Science and Engineering South China University of Technology Guangzhou China Guangdong Cardiovascular Institute Guangdong Provincial Key Laboratory of South China Structural Heart Disease Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangzhou510080 China The Department of Pathology Guangdong Provincial People's Hospital Guangdong Academy of Medical Sciences Guangdong Guangzhou510080 China The National-Regional Key Technology Engineering Laboratory for Medical Ultrasound Guangdong Key Laboratory for Biomedical Measurements and Ultrasound Imaging School of Biomedical Engineering Health Science Center Shenzhen University Shenzhen China The Department of Radiology Guangzhou First People's Hospital The Second Affiliated Hospital of South China University of Technology Guangzhou510180 China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2021年

核心收录：

主　　题：Semantic Segmentation 

摘      要：Tissue-level semantic segmentation is a vital step in computational pathology. Fully-supervised models have already achieved outstanding performance with dense pixel-level annotations. However, drawing such labels on the giga-pixel whole slide images is extremely expensive and time-consuming. In this paper, we use only patch-level classification labels to achieve tissue semantic segmentation on histopathology images, finally reducing the annotation efforts. We proposed a two-step model including a classification and a segmentation phases. In the classification phase, we proposed a CAM-based model to generate pseudo masks by patch-level labels. In the segmentation phase, we achieved tissue semantic segmentation by our proposed Multi-Layer Pseudo-Supervision. Several technical novelties have been proposed to reduce the information gap between pixel-level and patch-level annotations. As a part of this paper, we introduced a new weakly-supervised semantic segmentation (WSSS) dataset for lung adenocarcinoma (LUAD-HistoSeg). We conducted several experiments to evaluate our proposed model on two datasets. Our proposed model outperforms two state-of-the-art WSSS approaches. Note that we can achieve comparable quantitative and qualitative results with the fully-supervised model, with only around a 2% gap for MIoU and FwIoU. By comparing with manual labeling, our model can greatly save the annotation time from hours to minutes. The source code is available at: https://***/ChuHan89/*** Codes 68U10 © 2021, CC BY.