Decomposing Whole Slide Image Report Generation with Graph-Constrained Multiple Instance Learning Workflows

📅 2026-08-15
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This study addresses the challenges of opaque reasoning and poor narrative coherence in whole-slide image report generation by proposing an organ-conditioned graph-based decomposable framework. The approach decouples the generation process into visual recognition, structured reasoning, and text synthesis, leveraging multi-instance learning and large language models to construct interpretable reasoning chains that facilitate modular debugging and error attribution. Experimental results demonstrate that the model achieves a chain-wise Jaccard score of 0.702 on the reg2026 test set. Furthermore, diagnostic consistency on external TCGA data improves significantly from 61.8% to 92.6%, effectively enabling stage-level error localization and enhancing overall report quality through transparent, structured inference.
📝 Abstract
Whole-slide image (WSI) report generation requires recognizing spatially distributed pathological features and organizing them into a coherent diagnostic narrative. Although direct vision-to-text models can yield fluent reports, they obscure the contributions and failure modes of visual recognition, structured reasoning, and language generation. We propose a decomposed framework in which frozen Virchow2 tile embeddings are aggregated by multiple-instance learning (MIL) classification heads that answer organ-specific diagnostic questions. An organ-conditioned graph constrains the assembly of these answers into a structured reasoning chain, which a language model realizes as a pathology report. On the REG2026 held-out set of 2,028 slides, the proposed workflow achieved a chain-Jaccard score of 0.702. Performance fell to 0.420 without graph-based chain construction, 0.398 when the organ-specific graphs were replaced by a single organ-agnostic graph, and 0.371 when the language model constructed the chain freely from MIL predictions. Using the same report generator, graph-structured chains improved the report score from 0.330 to 0.495. On 350 external TCGA WSIs spanning the seven REG organs without fine-tuning, the expected organ graph was selected in 64.0% of cases and ranked among the top three in 86.6%. Providing the correct organ graph increased agreement with coarse TCGA primary-diagnosis labels from 61.8% to 92.6%, identifying organ routing as a main bottleneck under domain shift. Overall, organ-conditioned, graph-constrained chain assembly improves structured reasoning and report generation while enabling stage-specific error localization.
Problem

Research questions and friction points this paper is trying to address.

Whole Slide Image Report Generation
Structured Reasoning
Error Localization
Interpretability
Innovation

Methods, ideas, or system contributions that make the work stand out.

Graph-Constrained Reasoning
Decomposed Framework
Multiple Instance Learning
Organ-Conditioned Graph
WSI Report Generation
🔎 Similar Papers
No similar papers found.
💼 Related Jobs
No related jobs found.
A
Antony Gitau
Faculty of Technology, Natural Sciences and Maritime Sciences, University of South-Eastern Norway, Borre, Norway
M
Martyna Borak
Faculty of Biomedical Engineering, Silesian University of Technology, Zabrze, Poland
B
Bjørn-Jostein Singstad
Faculty of Technology, Natural Sciences and Maritime Sciences, University of South-Eastern Norway, Borre, Norway
M
Martin Paulson
Center for Cancer and Blood Diseases, Vestfold Hospital Trust, Tønsberg, Norway
K
Karl Thomas Hjelmervik
Faculty of Technology, Natural Sciences and Maritime Sciences, University of South-Eastern Norway, Borre, Norway
O
Ola Marius Lysaker
Faculty of Technology, Natural Sciences and Maritime Sciences, University of South-Eastern Norway, Borre, Norway
V
Veralia Gabriela Sanchez
Faculty of Technology, Natural Sciences and Maritime Sciences, University of South-Eastern Norway, Borre, Norway