超越单帧：跨体积MRI的多帧空间接地推理
Beyond a Single Frame: Multi-Frame Spatially Grounded Reasoning Across Volumetric MRI
AI总结：
本文提出SGMRI-VQA基准，通过多帧空间接地推理提升医学VLMs性能，展示监督微调提升接地能力。
摘要：
空间推理和视觉接地是视觉语言模型（VLMs）的核心能力，但大多数医学VLMs缺乏透明推理或空间证据。现有基准多基于孤立2D图像，忽略临床影像的体积特性。本文引入SGMRI-VQA基准，基于专家放射科医生注释的fastMRI+数据集，包含帧索引的边界框坐标。任务按检测、定位、计数/分类和描述分级，要求模型联合推理存在什么、在哪里以及跨哪些帧扩展。我们基准测试10个VLMs，显示监督微调Qwen3-VL-8B结合边界框监督能提升接地性能，表明针对性空间监督是实现临床推理的有效路径。
英文摘要：
Spatial reasoning and visual grounding are core capabilities for vision-language models (VLMs), yet most medical VLMs produce predictions without transparent reasoning or spatial evidence. Existing benchmarks also evaluate VLMs on isolated 2D images, overlooking the volumetric nature of clinical imaging, where findings can span multiple frames or appear on only a few slices. We introduce Spatially Grounded MRI Visual Question Answering (SGMRI-VQA), a 41,307-pair benchmark for multi-frame, spatially grounded reasoning on volumetric MRI. Built from expert radiologist annotations in the fastMRI+ dataset across brain and knee studies, each QA pair includes a clinician-aligned chain-of-thought trace with frame-indexed bounding box coordinates. Tasks are organized hierarchically across detection, localization, counting/classification, and captioning, requiring models to jointly reason about what is present, where it is, and across which frames it extends. We benchmark 10 VLMs and show that supervised fine-tuning of Qwen3-VL-8B with bounding box supervision consistently improves grounding performance over strong zero-shot baselines, indicating that targeted spatial supervision is an effective path toward grounded clinical reasoning.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
