Skin-R1: Toward Trustworthy Clinical Reasoning for Dermatological Diagnosis

TL;DR

SkinR1 is a novel dermatological vision-language model that integrates textbook-based reasoning with reinforcement learning to improve trustworthiness, accuracy, and generalization in skin disease diagnosis.

Contribution

It introduces a unified framework combining reasoning generation, supervised fine-tuning, and reinforcement learning to enhance clinical reasoning in dermatology models.

Findings

Achieves superior diagnostic accuracy across multiple datasets.

Demonstrates the effectiveness of reasoning supervision via ablation studies.

Shows improved generalization to large, sparsely-annotated datasets.

Abstract

The emergence of vision-language models (VLMs) has opened new possibilities for clinical reasoning and has shown promising performance in dermatological diagnosis. However, their trustworthiness and clinical utility are often limited by three major factors: (1) Data heterogeneity, where diverse datasets lack consistent diagnostic labels and clinical concept annotations; (2) Absence of grounded diagnostic rationales, leading to a scarcity of reliable reasoning supervision; and (3) Limited scalability and generalization, as models trained on small, densely annotated datasets struggle to transfer nuanced reasoning to large, sparsely-annotated ones. To address these limitations, we propose SkinR1, a novel dermatological VLM that combines deep, textbook-based reasoning with the broad generalization capabilities of reinforcement learning (RL). SkinR1 systematically resolves the key challenges through a unified, end-to-end framework. First, we design a textbook-based reasoning generator that synthesizes high-fidelity, hierarchy-aware, and differential-diagnosis (DDx)-informed trajectories, providing reliable expert-level supervision. Second, we leverage the constructed trajectories for supervised fine-tuning (SFT) empowering the model with grounded reasoning ability. Third, we develop a novel RL paradigm that, by incorporating the hierarchical structure of diseases, effectively transfers these grounded reasoning patterns to large-scale, sparse data. Extensive experiments on multiple dermatology datasets demonstrate that SkinR1 achieves superior diagnostic accuracy. The ablation study demonstrates the importance of the reasoning foundation instilled by SFT.