Proceedings

GroupMIL: Semantic Group Based Multiple Instance Learning for Whole Slide Image Analysing

Zhao Yao, Zhenmi Xie, Mengxin Tian, Guoqing Wu, Yaonan Wang, Min Liu

Download BibTeX Cite

Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence. AI and Health. Pages 6993-7000.

https://doi.org/10.24963/ijcai.2026/778

Keywords

  • Medical diagnosis: Medical diagnosis
  • Health data mining: Health data mining
  • Medical imaging: Medical imaging

Abstract

Whole Slide Image (WSI) analysis faces challenges due to gigapixel resolutions and slide-level weak supervision. Multiple Instance Learning (MIL) serves as a pivotal method for this task. However, existing MIL frameworks often fail to exploit the inherent redundancy of tissue patterns or the semantic coherence among similar patches within a WSI. We propose GroupMIL, a novel framework that introduces a differentiable grouping mechanism into the MIL framework. This approach enables the automatic emergence of semantic segments using only slide-level labels. We specifically introduce a multi-stage grouping block and a hierarchical aggregator, which progressively fuse features within and across groups to construct a robust slide-level representation. Extensive experiments on multiple public datasets across cancer subtyping and survival prediction tasks demonstrate that GroupMIL consistently surpasses state-of-the-art performance.

Zhao Yao, Zhenmi Xie, Mengxin Tian, Guoqing Wu, Yaonan Wang, and Min Liu. 2026. GroupMIL: Semantic Group Based Multiple Instance Learning for Whole Slide Image Analysing. In Proceedings of the Thirty-Fifth International Joint Conference on Artificial Intelligence, IJCAI-26. IJCAI, 6993–7000. https://doi.org/10.24963/ijcai.2026/778
Welcome Future Conferences AI Journal Division IJCAI Proceedings About IJCAI IJCAI Awards