Rethinking Mitosis Detection: Towards Diverse Data and Feature Representation

作     者：Wang, Hao Lin, Jiatai Li, Danyi Wang, Jing Zhao, Bingchao Shi, Zhenwei Pan, Xipeng Wang, Huadeng Li, Bingbing Liang, Changhong Han, Guoqiang Liang, Li Han, Chu Liu, Zaiyi 

作者机构：The School of Computer Science and Engineering South China University of Technology Guangzhou510006 China Department of Radiology Guangdong Provincial People’s Hospital Guangdong Academy of Medical Sciences Southern Medical University Guangzhou510080 China Guangdong Provincial Key Laboratory of Artificial Intelligence in Medical Image Analysis and Application Guangzhou510080 China The Department of Pathology Nanfang Hospital Basic Medical College Southern Medical University Guangdong Guangzhou China Guangdong Province Key Laboratory of Molecular Tumor Pathology Guangdong Guangzhou China The Department of Pathology Guangdong Provincial People’s Hospital Ganzhou Hospital Ganzhou China The School of Computer Science and Information Security Guilin University of Electronic Technology Guilin541004 China 

出 版 物：《arXiv》 (arXiv)

年 卷 期：2023年

核心收录：

主　　题：Chemical detection 

摘      要：Mitosis detection is one of the fundamental tasks in computational pathology, which is extremely challenging due to the heterogeneity of mitotic cell. Most of the current studies solve the heterogeneity in the technical aspect by increasing the model complexity. However, lacking consideration of the biological knowledge and the complex model design may lead to the overfitting problem while limited the generalizability of the detection model. In this paper, we systematically study the morphological appearances in different mitotic phases as well as the ambiguous non-mitotic cells and identify that balancing the data and feature diversity can achieve better generalizability. Based on this observation, we propose a novel generalizable framework (MitDet) for mitosis detection. The data diversity is considered by the proposed diversity-guided sample balancing (DGSB). And the feature diversity is preserved by inter- and intra- class feature diversity-preserved module (InCDP). Stain enhancement (SE) module is introduced to enhance the domain-relevant diversity of both data and features simultaneously. Extensive experiments have demonstrated that our proposed model outperforms all the SOTA approaches in several popular mitosis detection datasets in both internal and external test sets using minimal annotation efforts with point annotations only. Comprehensive ablation studies have also proven the effectiveness of the rethinking of data and feature diversity balancing. By analyzing the results quantitatively and qualitatively, we believe that our proposed model not only achieves SOTA performance but also might inspire the future studies in new perspectives. Source code is at https://***/Onehour0108/MitDet. © 2023, CC BY.