PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimization

TL;DR

PathReasoner-R1 introduces a knowledge-guided training approach for pathology vision-language models, enabling structured, transparent reasoning aligned with medical knowledge, thereby improving diagnostic robustness and clinical trust.

Contribution

The paper presents PathReasoner-R1, a novel model that integrates medical knowledge graphs into reasoning training, creating the first large-scale WSI reasoning dataset and a reinforcement learning framework for structured pathology reasoning.

Findings

Achieves state-of-the-art performance on pathology reasoning benchmarks.

Demonstrates improved logical consistency and robustness in diagnoses.

Provides a new dataset and training pipeline for pathology vision-language models.

Abstract

Vision-Language Models (VLMs) are advancing computational pathology with superior visual understanding capabilities. However, current systems often reduce diagnosis to directly output conclusions without verifiable evidence-linked reasoning, which severely limits clinical trust and hinders expert error rectification. To address these barriers, we construct PathReasoner, the first large-scale dataset of whole-slide image (WSI) reasoning. Unlike previous work reliant on unverified distillation, we develop a rigorous knowledge-guided generation pipeline. By leveraging medical knowledge graphs, we explicitly align structured pathological findings and clinical reasoning with diagnoses, generating over 20K high-quality instructional samples. Based on the database, we propose PathReasoner-R1, which synergizes trajectory-masked supervised fine-tuning with reasoning-oriented reinforcement learning to instill structured chain-of-thought capabilities. To ensure medical rigor, we engineer a knowledge-aware multi-granular reward function incorporating an Entity Reward mechanism strictly aligned with knowledge graphs. This effectively guides the model to optimize for logical consistency rather than mere outcome matching, thereby enhancing robustness. Extensive experiments demonstrate that PathReasoner-R1 achieves state-of-the-art performance on both PathReasoner and public benchmarks across various image scales, equipping pathology models with transparent, clinically grounded reasoning capabilities. Dataset and code are available at https://github.com/cyclexfy/PathReasoner-R1.