用结构化报告+空间引导，提升头颈癌影像报告准确性
SGRNet: Spatially Guided Radiology Network for Structured Radiological Reporting of Head and Neck Cancer
- 将报告生成转为基于解剖结构的多标签分类任务
- 在5个关键部位实现mAP 0.60，比纯图像模型高8.8个百分点
- 适合需要高精度、低幻觉医学报告的临床研发人员
自动化放射科报告生成可减轻临床负担并减少观察者差异。然而，标准自由文本生成模型在密集区域存在幻觉风险，且在数据稀缺时表现不佳。本文针对增强型头颈部CT（CECT）影像中的头颈癌（HNC）问题提出解决方案。为保障事实安全，将报告生成重构为基于解剖结构的多标签、结构化报告任务，预测在分层临床框架下各解剖部位的局部肿瘤累及情况。为弥补缺乏代谢影像（如PET）带来的视觉信息缺失，提出SGRNet（空间引导放射科网络），引入两种低成本空间先验：自动器官分割结果和通过3D高斯热图建模的弱监督肿瘤定位图。这些先验通过空间特征调制动态融合，引导网络关注细微的肿瘤诱导结构改变。在包含184对头颈癌CECT影像与报告的多中心数据集上，针对五个临床上重要的密集解剖亚部位进行评估，SGRNet取得0.60的平均精确率（mAP），相比强的仅使用体积的3D基线模型绝对提升8.8个百分点。
原文摘要 · Abstract (English)
Automated radiological report generation can alleviate clinical workloads and eliminate observer variability. However, standard free-text generation models pose hallucination risks in dense regions and fail under data scarcity. We address these challenges in Head and Neck Cancer (HNC) from contrast-enhanced CT (CECT) imaging. To enforce factual safety, we reformulate report generation as an anatomically grounded, multi-label, structured reporting task, predicting localized tumor involvement across a hierarchical clinical schema. To bridge the visual gap from missing metabolic imaging (e.g., PET), we introduce SGRNet (Spatially Guided Radiology Network), incorporating two low-cost spatial priors: automated organ segmentations and weakly supervised tumor localization maps modeled via 3D Gaussian heatmaps. These priors are dynamically integrated via spatial feature modulation to guide the network toward subtle tumor-induced structural alterations. Evaluated on a multi-centric dataset of 184 paired HNC CECT volumes and reports, on five clinically salient, densely packed anatomical subsites, SGRNet achieves a mean Average Precision (mAP) of 0.60, an 8.8 percentage-point absolute improvement over strong volume-only 3D baselines.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。