ConMIL: interactive and contrastive text-guided multiple instance learning for whole slide image classification

Clicks: 21
ID: 328919
2026
Free PDF
Article Quality & Performance Metrics
Overall Quality
Not rated
Combines reader engagement with the AI quality analysis. This article has not been analysed, so there is no overall score — reader engagement is measured and shown alongside.
AI Quality Assessment
Not analyzed
Readership in this journal
Emerging

Ranked #462 of 983 articles by views in BMC Bioinformatics

Most read Least read

Bar heights use a square-root scale. Only the 120 most-read articles are drawn; the journal has 983 in total.

Mint this article as an NFT
Not yet minted

Create a permanent, verifiable on-chain record of this article on the Scimatic Network. The NFT is held in your Journament account, and you can withdraw it to your own wallet at any time.

5 SUSD one-off · no wallet required
Sign in to mint
Abstract
MOTIVATION: Whole-slide image (WSI) classification in computational pathology typically relies on Multiple Instance Learning (MIL) for weakly supervised analysis. Recent pathology vision-language models have inspired text-guided approaches, but these methods typically use text for representation alignment or region localization, rather than directly incorporating semantic signals into MIL attention weighting. Furthermore, these approaches often rely on static prompts and provide limited insight into the learned nonlinear transformations performed by the classifier. RESULTS: We propose ConMIL, an interactive contrastive text-guided MIL framework for WSI classification. At its core, ConMIL introduces a contrastive semantic-guided attention mechanism that uses paired positive and negative pathology-specific text embeddings to directly modulate MIL attention weighting. This mechanism is complemented by human-in-the-loop prompt refinement to improve semantic specificity and a Kolmogorov-Arnold Network (KAN) classifier that enables visualization and quantitative inspection of learned nonlinear transformations. Experiments on CAMELYON16, TCGA-BRCA, and BRACS demonstrate that ConMIL consistently outperforms representative MIL baselines while producing pathology-consistent attention heatmaps and inspectable nonlinear transformations. AVAILABILITY: The source code for ConMIL is available at https://github.com/anxuanhan/ConMIL. SUPPLEMENTARY INFORMATION: Supplementary data are available at Bioinformatics online.
Reference Key
openalex_W7213422450 Use this key to autocite in the manuscript while using SciMatic Manuscript Manager or Thesis Manager
Authors Anxuan Han, Alexandra Jolley, Lisa M. Butler, Weitong Chen
Are you one of these authors? Claim your profile
Journal BMC Bioinformatics
Year 2026
DOI
10.1093/bioinformatics/btag679
URL
https://doi.org/10.1093/bioinformatics/btag679
Keywords Keywords not found

Citations

No citations found. To add a citation, contact the admin at info@scimatic.org

Comments

No comments yet. Be the first to comment on this article.