发表机构
University of Strasbourg; IHU Strasbourg; Indian Institute of Technology (IIT) Madras; All India Institute of Medical Sciences（斯特拉斯堡大学; 斯特拉斯堡大学医院研究所; 印度马德拉斯理工学院; 全印度医学科学院）
机构由 AI 辅助整理，请以论文原文为准。AI 中文总结
SGRNet是用于头颈部癌症结构化放射学报告的网络，通过整合自动器官分割等空间先验，在184例多中心数据上较基线提升8.8个百分点，实现0.60的mAP。
AI 中文摘要
自动放射学报告生成可减轻临床工作量并消除观察者间的差异，但标准自由文本生成模型在密集区域存在幻觉风险，且在数据稀缺时性能不佳。我们针对头颈部癌症（HNC）的对比增强CT（CECT）成像解决这些挑战，将报告生成重新表述为基于解剖学的多标签结构化报告任务，预测分层临床方案中的局部肿瘤累及情况。为弥合缺失代谢成像（如PET）的视觉差距，我们引入SGRNet（空间引导放射学网络），包含两种低成本空间先验：自动器官分割和通过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整合，以引导网络关注肿瘤引起的细微结构改变。在包含184对头颈部癌症CECT体积及报告的多中心数据集上，针对5个临床显著、密集排列的解剖亚部位评估，SGRNet的平均精度（mAP）达0.60，较仅基于体积的强3D基线方法提升了8.8个百分点。
英文摘要
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.
