English

INSIGHT: Explainable Weakly-Supervised Medical Image Analysis

Image and Video Processing 2025-08-15 v3 Artificial Intelligence Computer Vision and Pattern Recognition

Abstract

Due to their large sizes, volumetric scans and whole-slide pathology images (WSIs) are often processed by extracting embeddings from local regions and then an aggregator makes predictions from this set. However, current methods require post-hoc visualization techniques (e.g., Grad-CAM) and often fail to localize small yet clinically crucial details. To address these limitations, we introduce INSIGHT, a novel weakly-supervised aggregator that integrates heatmap generation as an inductive bias. Starting from pre-trained feature maps, INSIGHT employs a detection module with small convolutional kernels to capture fine details and a context module with a broader receptive field to suppress local false positives. The resulting internal heatmap highlights diagnostically relevant regions. On CT and WSI benchmarks, INSIGHT achieves state-of-the-art classification results and high weakly-labeled semantic segmentation performance. Project website and code are available at: https://zhangdylan83.github.io/ewsmia/

Keywords

Cite

@article{arxiv.2412.02012,
  title  = {INSIGHT: Explainable Weakly-Supervised Medical Image Analysis},
  author = {Wenbo Zhang and Junyu Chen and Christopher Kanan},
  journal= {arXiv preprint arXiv:2412.02012},
  year   = {2025}
}

Comments

Accepted at MLHC 2025 (Machine Learning for Healthcare)

R2 v1 2026-06-28T20:20:34.289Z