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

2026-01-29

AI Summary

This work addresses the lack of verifiable, structured reasoning mechanisms in existing pathological vision-language models, which suffer from low clinical credibility and limited error correction capabilities. To this end, we introduce PathReasoner, the first large-scale whole-slide image reasoning dataset, along with the PathReasoner-R1 model. By integrating a medical knowledge graph into the training process through knowledge-guided policy optimization, our approach aligns diagnostic predictions with explicit pathological reasoning. Key innovations include trajectory-masked supervised fine-tuning, reasoning-oriented reinforcement learning, and a reward function combining entity-level and multi-granularity knowledge-aware signals to enhance logical consistency. Experiments demonstrate that PathReasoner-R1 achieves state-of-the-art performance on both the PathReasoner dataset and multiple public pathological benchmarks, significantly improving transparency and clinically trustworthy reasoning across multi-scale histopathological images.

Technology Category

• Knowledge Representation and Reasoning: Diagnosis and Abductive Reasoning
• Computer Vision: Visual Reasoning & Symbolic Representations
• Reasoning under Uncertainty: Other Foundations of Reasoning under Uncertainty

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

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.

Problem

• Vision-Language Models
• Computational Pathology
• Structured Reasoning
• Clinical Trust
• Evidence-linked Reasoning

Innovation

• Knowledge-Guided Policy Optimization
• Structured Reasoning
• Vision-Language Model
• Medical Knowledge Graph
• Reinforcement Learning