PRS-Med: Position Reasoning Segmentation with Vision-Language Model in Medical Imaging
This work addresses the problem of enabling intuitive doctor-system interaction through natural language for more efficient diagnoses in medical imaging, representing a novel approach rather than an incremental improvement.
The paper tackles the challenge of position reasoning in medical image segmentation by introducing PRS-Med, a framework that integrates vision-language models to generate accurate segmentation masks and spatial reasoning outputs, significantly outperforming state-of-the-art methods across six imaging modalities.
Recent advancements in prompt-based medical image segmentation have enabled clinicians to identify tumors using simple input like bounding boxes or text prompts. However, existing methods face challenges when doctors need to interact through natural language or when position reasoning is required - understanding spatial relationships between anatomical structures and pathologies. We present PRS-Med, a framework that integrates vision-language models with segmentation capabilities to generate both accurate segmentation masks and corresponding spatial reasoning outputs. Additionally, we introduce the MMRS dataset (Multimodal Medical in Positional Reasoning Segmentation), which provides diverse, spatially-grounded question-answer pairs to address the lack of position reasoning data in medical imaging. PRS-Med demonstrates superior performance across six imaging modalities (CT, MRI, X-ray, ultrasound, endoscopy, RGB), significantly outperforming state-of-the-art methods in both segmentation accuracy and position reasoning. Our approach enables intuitive doctor-system interaction through natural language, facilitating more efficient diagnoses. Our dataset pipeline, model, and codebase will be released to foster further research in spatially-aware multimodal reasoning for medical applications.