From Correlation to Causation: Max-Pooling-Based Multi-Instance Learning Leads to More Robust Whole Slide Image Classification
UniSA STEM, University of South Australia（南澳大利亚大学STEM学院）；School of Computer Science and Engineering, Southeast University（东南大学计算机科学与工程学院）；Key Lab. of Computer Network and Information Integration (Southeast University), MoE, China（计算机网络与信息集成重点实验室（东南大学），教育部，中国）；School of Information and Physical Sciences, The University of Newcastle（新castle大学信息与物理科学学院）；Mohamed bin Zayed University of Artificial Intelligence (MBZUAI)（穆罕默德·本·扎耶德人工智能大学）
Xin Liu, Weijia Zhang, Wei Tang, Thuc Duy Le, Jiuyong Li, Lin Liu, Min-Ling Zhang
In whole slide images (WSIs) analysis, attention-based multi-instance learning (MIL) models are susceptible to spurious correlations and degrade under domain shift. These methods may assign high attention weights to non-tumor regions, such as staining biases or artifacts, leading to unreliable tumor region localization. In this paper, we revisit max-pooling-based MIL methods from a causal perspective. Under mild assumptions, our theoretical results demonstrate that max-pooling encourages the model to focus on causal factors while ignoring bias-related factors. Furthermore, we discover that existing max-pooling-based methods may overfit the training set through rote memorization of instance features and fail to learn meaningful patterns. To address these issues, we propose FocusMIL, which couples max-pooling with an instance-level variational information bottleneck (VIB) to learn compact, predictive latent representations, and employs a multi-bag mini-batch scheme to stabilize optimization. We conduct comprehensive experiments on three real-world datasets and one semi-synthetic dataset. The results show that, by capturing causal factors, FocusMIL exhibits significant advantages in out-of-distribution scenarios and instance-level tumor region localization tasks.
Shanghai Artificial Intelligence Laboratory（上海人工智能实验室）；Academy for Engineering and Technology, Fudan University（复旦大学工程与技术学院）；Fudan University Shanghai Cancer Center（复旦大学附属肿瘤医院）；Zhongshan Hospital, Fudan University（复旦大学中山医院）
Beyond accuracy: quantifying the reliability of Multiple Instance Learning for Whole Slide Image classification
Department of Biomedical Engineering, Eindhoven University of Technology（埃因霍温理工大学生物医学工程系）；Flensburg Artificial Intelligence Research Group (FLAIR), Flensburg University of Applied Sciences（弗劳恩霍夫应用科技大学人工智能研究组）；University of Veterinary Medicine Vienna（维也纳兽医大学）
PTCMIL: Multiple Instance Learning via Prompt Token Clustering for Whole Slide Image Analysis
The University of British Columbia（不列颠哥伦比亚大学）；Vector Institute（向量研究所）；Chungnam National University（Chungnam国立大学）；The Hong Kong University of Science and Technology（香港科学与技术大学）
本文提出 PTCMIL，利用可学习提示词元、投影聚类、词元合并与原型池化实现端到端 WSI 的 MIL 聚合，在八个数据集上取得优于现有方法的分类与生存分析性能。
School of Biomedical Engineering（生物医学工程学院）；Department of Pathology and Laboratory Medicine（病理与检验医学系）；Vancouver Prostate Centre（温哥华前列腺中心）；BC Cancer Institute（不列颠哥伦比亚省癌症研究所）；The University of British Columbia（不列颠哥伦比亚大学）
HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image
Tsinghua University（清华大学）；Tsinghua Shenzhen International Graduate School, Tsinghua University（清华大学深圳国际研究生院）；Peking University（北京大学）；School of Electronic and Computer Engineering, Peking University（北京大学电子与计算机工程学院）；Harbin Institute of Technology（哈尔滨工业大学）；Harbin Institute of Technology (Shenzhen)（哈尔滨工业大学（深圳））
CAPRMIL: Context-Aware Patch Representations for Multiple Instance Learning
National and Kapodistrian University of Athens（希腊国家与卡波迪斯蒂亚纳大学）；Archimedes, Athena Research Center（阿提卡研究中心）；MICS Laboratory, CentraleSupélec, Université Paris-Saclay（中央超导实验室，巴黎萨克雷大学）；IHU PRISM, National Center for Precision Medicine in Oncology, Gustave Roussy（IHU PRISM，国家精准医学在肿瘤学中的研究中心，格斯塔夫·鲁西医院）
MILD-Net: Minimal Information Loss Dilated Network for Gland Instance Segmentation in Colon Histology Images
University of Warwick（华威大学）；The Chinese University of Hong Kong（香港中文大学）；University Hospitals Coventry and Warwickshire（考文垂与华威大学医院）；The Alan Turing Institute（艾伦·图灵研究所）
