English

GAS-MIL: Group-Aggregative Selection Multi-Instance Learning for Ensemble of Foundation Models in Digital Pathology Image Analysis

Computer Vision and Pattern Recognition 2025-10-07 v1 Artificial Intelligence

Abstract

Foundation models (FMs) have transformed computational pathology by providing powerful, general-purpose feature extractors. However, adapting and benchmarking individual FMs for specific diagnostic tasks is often time-consuming and resource-intensive, especially given their scale and diversity. To address this challenge, we introduce Group-Aggregative Selection Multi-Instance Learning (GAS-MIL), a flexible ensemble framework that seamlessly integrates features from multiple FMs, preserving their complementary strengths without requiring manual feature selection or extensive task-specific fine-tuning. Across classification tasks in three cancer datasets-prostate (PANDA), ovarian (UBC-OCEAN), and breast (TCGA-BrCa)-GAS-MIL consistently achieves superior or on-par performance relative to individual FMs and established MIL methods, demonstrating its robustness and generalizability. By enabling efficient integration of heterogeneous FMs, GAS-MIL streamlines model deployment for pathology and provides a scalable foundation for future multimodal and precision oncology applications.

Keywords

Cite

@article{arxiv.2510.03555,
  title  = {GAS-MIL: Group-Aggregative Selection Multi-Instance Learning for Ensemble of Foundation Models in Digital Pathology Image Analysis},
  author = {Peiran Quan and Zifan Gu and Zhuo Zhao and Qin Zhou and Donghan M. Yang and Ruichen Rong and Yang Xie and Guanghua Xiao},
  journal= {arXiv preprint arXiv:2510.03555},
  year   = {2025}
}
R2 v1 2026-07-01T06:16:31.631Z