PathReasoner-R1: Instilling Structured Reasoning into Pathology Vision-Language Model via Knowledge-Guided Policy Optimization
This addresses the need for transparent, clinically grounded reasoning in computational pathology to enhance trust and error rectification for medical experts.
The paper tackles the problem of lack of verifiable evidence-linked reasoning in pathology vision-language models by constructing PathReasoner, a large-scale dataset of whole-slide image reasoning with over 20K high-quality samples, and proposing PathReasoner-R1, which achieves state-of-the-art performance on benchmarks across various image scales.
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.