一种用于CT扫描中空间关系可靠且可审计验证的模块化智能体

摘要

可靠的空间理解是未来医学视觉语言系统的重要前提，这类系统旨在支持放射学报告生成和结构化图像理解。尽管现代视觉语言模型（VLM）在许多医学影像任务中展现出良好的性能，但近期证据表明它们在受控空间推理方面仍然薄弱，且常常无法可靠地将空间关系锚定到图像证据中。鉴于放射学推理依赖于理解解剖结构和病灶的相对位置，这种空间能力不足对诊断准确性构成风险。我们提出了一种模块化医学影像智能体，用于轴向CT切片中的二值空间关系验证。该系统不直接端到端地预测空间答案，而是将任务分解为明确的阶段：语言解析、解剖定位和确定性几何验证。自然语言查询被转换为结构化关系元组，被查询的器官通过基于YOLO的检测器进行定位，最终的空间决策则使用确定性几何规则从物体中心计算得出。我们在保留的MIRP空间问答基准上评估了该方法，并将其与具有代表性的端到端VLM基线进行了比较。性能最佳的混合配置达到94.1%的准确率和94.2%的F1分数，在准确率上比直接Qwen2-VL提示高出42.5个百分点，同时保留了可解释的中间表示和可审计的推理阶段。结果表明，显式的模块化空间验证可以成为未来面向报告的医学影像智能体的一个有前景的构建模块。

English

Reliable spatial understanding is an important prerequisite for future medical vision-language systems that aim to support radiological report generation and structured image understanding. While modern vision-language models (VLMs) show promising performance on many medical imaging tasks, recent evidence suggests they remain weak in controlled spatial reasoning and often fail to reliably ground spatial relations in image evidence. Given that radiological reasoning hinges on understanding the relative positions of anatomical structures and findings, this spatial weakness poses risks to diagnostic accuracy. We present a modular medical imaging agent for binary spatial relation verification in axial CT slices. Instead of directly predicting spatial answers end-to-end, the system decomposes the task into explicit stages: language parsing, anatomical localization, and deterministic geometric verification. Natural-language queries are converted into structured relation tuples, queried organs are localized with a YOLO-based detector, and the final spatial decision is computed from object centers using deterministic geometric rules. We evaluate the approach on the held-out MIRP spatial QA benchmark and compare it against representative end-to-end VLM baselines. The best-performing hybrid configuration reaches 94.1% accuracy and 94.2% F1, outperforming direct Qwen2-VL prompting by 42.5 percentage points in accuracy, while preserving interpretable intermediate representations and auditable reasoning stages. The results suggest that explicit modular spatial verification can serve as a promising building block for future report-oriented medical imaging agents.