Synthetic Vasculature and Pathology Enhance Vision-Language Model Reasoning

Abstract

Vision-language models (VLMs) offer a promising path toward interpretable medical diagnosis by allowing users to ask about clinical explanations alongside predictions and across different modalities. However, training VLMs for detailed reasoning requires large-scale image-text datasets. In many specialized domains, for example in reading optical coherence tomography angiography (OCTA) images, such precise text with grounded description of pathologies is scarce or even non-existent. To overcome this bottleneck, we introduce synthetic vasculature reasoning (SVR), a framework that controllably synthesizes images and corresponding text, specifically: realistic retinal vasculature with diabetic retinopathy (DR) features: capillary dropout, microaneurysms, intraretinal microvascular abnormalities, and tortuosity, while automatically generating granular reasoning texts. Based on this we curate OCTA-100K-SVR, an OCTA image-reasoning dataset with 100,000 pairs. Our experiments show that a general-purpose VLM (Qwen3-VL-8b) trained on the dataset achieves a zero-shot balanced classification accuracy of 86.69% on real OCTA images, demonstrating performance comparable to supervised baselines. Through human expert evaluation we also demonstrate that it significantly enhances explanation quality and pathology localization on clinical data.