DeCo-MIL: Debiased Counterfactual Reasoning for Long-Tailed Whole Slide Image Analysis

2026-08-11

AI Summary

This study addresses model bias and rare class recognition degradation in long-tail Whole Slide Image (WSI) analysis caused by nested dual long-tail distributions at both slide and instance levels. To mitigate this, we propose Deco-MIL, a novel framework that innovatively integrates frequency-debiased counterfactual reasoning with redundant masking, anchor-stratified pseudo-bag construction, tail-aware oversampling, and consistency regularization to jointly decouple and alleviate coupled biases. Extensive experiments on three long-tail WSI benchmarks demonstrate that Deco-MIL achieves state-of-the-art performance, significantly improving tail-class recognition accuracy and overall classification efficacy. By effectively tackling the challenges of nested imbalance, this work establishes a new paradigm for long-tail medical image analysis, offering a robust solution for enhancing diagnostic reliability in data-scarce clinical scenarios.

Abstract

Multiple instance learning (MIL) is widely used for weakly supervised whole slide image (WSI) analysis. However, under long-tailed distributions, MIL-based WSI analysis faces a nested dual long-tail: an inter-slide class long tail and an intra-slide long tail of instance-level discriminative evidence. The two long tails are coupled: tail classes have few training slides, while their limited diagnostic evidence is concentrated in a few patches and obscured by abundant within-bag redundancy. This coupling biases models toward head classes and degrades rare-class recognition. To address this, we propose DeCo-MIL for long-tailed WSI analysis, which jointly alleviates the nested dual long-tail through frequency-debiased counterfactual reasoning. For the inner long tail, DeCo-MIL clusters patches into tissue-morphology anchors, replaces each anchor with its matched normal prototype to perform a counterfactual intervention, and estimates its counterfactual contribution to the ground-truth class using class-frequency-corrected predictions. These contributions guide redundancy masking to preserve scarce discriminative instances. For the outer long tail, DeCo-MIL constructs anchor-stratified pseudo-bags from redundancy-reduced bags and combines tail-aware oversampling with consistency regularization, increasing effective supervision for tail classes while preserving tissue-morphology composition. Extensive experiments on three long-tailed WSI benchmarks demonstrate that DeCo-MIL achieves state-of-the-art performance in both tail-class recognition and overall classification.

Problem

• Whole Slide Image Analysis
• Multiple Instance Learning
• Long-Tailed Distribution
• Nested Dual Long-Tail
• Rare-Class Recognition

Innovation

• Debiased Counterfactual Reasoning
• Nested Dual Long-Tail
• Multiple Instance Learning
• Whole Slide Image Analysis
• Redundancy Masking