Skip to content

SGRNet: Spatially Guided Radiology Network for Structured Radiological Reporting of Head and Neck Cancer

Aug 2026 · arXiv.org · Vol abs/2608.29153 · 0 citations · 26 references
Computer Science

TL;DR

This work reformulate report generation as an anatomically grounded, multi-label, structured reporting task, predicting localized tumor involvement across a hierarchical clinical schema, and introduces 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.

Abstract

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.

View source

Similar papers

Preprint Oct 2026

DiffUltra: Task-Guided Pathology Synthesis for Large-Scale Real-World Lung Ultrasound Data

Despite their scale, large medical imaging datasets may underrepresent clinically relevant pathological presentations. Synthetic data can expand coverage, but findings must remain compatible with surrounding anatomy. This is challenging in ultrasound, where findings resemble surrounding tissue and must be positioned re...

Gary Y. Li, Yu-Cheng Chou, Li Chen et al. · 0 citations
Sep 2026

Comorbidity-Aware Radiology Report Generation.

Chest X-ray report generation systems are valuable for assisting disease diagnosis and improving healthcare efficiency. However, existing methods still face two key challenges. First, multiple diseases often co-occur, leading to a combinatorial explosion of label combinations and sparse supervision for learning a gener...

Hong-Ze Zhu, Hong Liu, Ya-Wen Huang et al. · 0 citations
Open access Nov 2026

FASA-Net: A Frequency-Domain-Enhanced and Anatomically Constrained Vision-Language Framework for Automated Chest X-ray Report Generation.

Automated radiology report generation can reduce radiologists' workloads by producing preliminary reports from medical images. However, generating chest X-ray reports remains challenging. Subtle lesions and organ boundaries may be underrepresented, visual regions may be poorly aligned with medical terminology, and long...

Yu-Hai Yu, Jing Liu, Jia-Na Meng et al. · 0 citations
Open access Nov 2026

Volumetric chest CT report generation via state-space visual prompting and clinical-fact alignment

Objective. To address the memory bottlenecks of three-dimensional (3D) sequence modeling and the factual hallucinations associated with cross-entropy optimization in automated 3D chest computed tomography (CT) report generation. Approach. We propose an end-to-end framework that couples perception refinement with clinic...

Zi-Yang Li, De-Dong Yang, Rong-Tao Li et al. · 0 citations
Conference Oct 2026

VUD-Net: a compact uncertainty-feedback convolutional framework for MRI-based brain metastasis segmentation

Precise delineation of brain metastases on magnetic resonance imaging (MRI) is a key step in radiotherapy planning and follow-up assessment. The task remains difficult because metastatic foci vary markedly in size, occupy only a small fraction of the brain volume, and often show weak contrast at tumor-edema interfaces....

Jing-Xin Shi · 0 citations
Book Open access Nov 2026

CGFusion: Concept-Guided Multimodal Fusion for Interpretable Cancer Diagnosis and Prognosis

Integrating radiology, whole-slide pathology, and structured clinical data is essential for reliable cancer prediction, yet remains challenging due to substantial cross-modal heterogeneity. Existing multimodal models often fail to establish consistent cross-modal representations and provide limited semantic interpretab...

Yu-Yang Xie, F. Gu, Na Ji · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.