🤖 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.