MiCo: Multiple Instance Learning with Context-Aware Clustering for Whole Slide Image Analysis

2025/06/22 by Junjian Li, Jin Liu, Li, Junjian +9 · 1 citation
Computer Science · #AI in cancer detection #Centroid #Cluster analysis #Discriminative model #Feature (linguistics) #Feature vector #Image Retrieval and Classification Techniques #Medical Image Segmentation Techniques #Pattern recognition (psychology) #Semantic feature #Semantics (computer science)

paper · pdf · doi:10.48550/arxiv.2506.18028

published in arXiv (Cornell University) (Cornell University)

openalex publication_date 2025/06/22 · openalex created_date 2025/10/14 · openalex updated_date 2026/08/05

Abstract

Multiple instance learning (MIL) has shown significant promise in histopathology whole slide image (WSI) analysis for cancer diagnosis and prognosis. However, the inherent spatial heterogeneity of WSIs presents critical challenges, as morphologically similar tissue types are often dispersed across distant anatomical regions. Conventional MIL methods struggle to model these scattered tissue distributions and capture cross-regional spatial interactions effectively. To address these limitations, we propose a novel Multiple instance learning framework with Context-Aware Clustering (MiCo), designed to enhance cross-regional intra-tissue correlations and strengthen inter-tissue semantic associations in WSIs. MiCo begins by clustering instances to distill discriminative morphological patterns, with cluster centroids serving as semantic anchors. To enhance cross-regional intra-tissue correlations, MiCo employs a Cluster Route module, which dynamically links instances of the same tissue type across distant regions via feature similarity. These semantic anchors act as contextual hubs, propagating semantic relationships to refine instance-level representations. To eliminate semantic fragmentation and strengthen inter-tissue semantic associations, MiCo integrates a Cluster Reducer module, which consolidates redundant anchors while enhancing information exchange between distinct semantic groups. Extensive experiments on two challenging tasks across nine large-scale public cancer datasets demonstrate the effectiveness of MiCo, showcasing its superiority over state-of-the-art methods. The code is available at https://github.com/junjianli106/MiCo.

Citations

• Multimodal Whole Slide Foundation Model for Pathology
• Dynamic Graph Representation with Knowledge-aware Attention for Histopathology Whole Slide Image Analysis
• Feature Re-Embedding: Towards Foundation Model-Level Performance in Computational Pathology
• HVTSurv: Hierarchical Vision Transformer for Patient-Level Survival Prediction from Whole Slide Image
• Whole Slide Images are 2D Point Clouds: Context-Aware Survival Prediction using Patch-based Graph Convolutional Networks
• Neural Discrete Representation Learning

Cited by

• Towards Reliable Stain Transfer: An Iterative Data-Model Co-Optimization Framework Based on Multimodal Expert-Guided Assessment

Related

• Advances in Multiple Instance Learning for Whole Slide Image Analysis: Techniques, Challenges, and Future Directions
• The Whole Pathological Slide Classification via Weakly Supervised Learning
• Long-MIL: Scaling Long Contextual Multiple Instance Learning for Histopathology Whole Slide Image Analysis
• MicroMIL: Graph-Based Multiple Instance Learning for Context-Aware Diagnosis with Microscopic Images
• Diagnose Like a Pathologist: Transformer-Enabled Hierarchical Attention-Guided Multiple Instance Learning for Whole Slide Image Classification