arXiv：cs.CL· Chandravardhan Singh Raghaw, Shahid Shafi Dar, Arnav Nishith Sharma, Shrey Modi, Nagendra Kumar·· 13 小时前
CliQ-RRG：临床知识引导的疾病感知视觉-文本对齐，用于问答式放射报告生成
CliQ-RRG: Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation
AI 导读
CliQ-RRG 是一个两阶段框架，用于生成可解释、临床落地的问答式放射报告。第一阶段用疾病感知视觉-文本对齐模块，配合 Prior-Guided Attention Module（PrAM）捕捉当前与既往扫描的多视图依赖；第二阶段以 GraphRAG 检索图结构临床证据，再由大语言模型重构为简洁的问答对与诊断摘要。在两个公开胸部 X 光基准上，其在词汇与临床指标上均持续优于既有方法，代码已公开。
正文
Abstract:Radiology reports are essential for diagnostic reasoning and patient care, yet their manual preparation is time-consuming and cognitively demanding. Automatic radiology report generation (RRG) offers a scalable alternative, but existing models often produce lengthy, unstructured narratives that overlook diagnostic cues and multi-view information. We present Clinical-Knowledge Guided Disease-aware Visual-Textual Alignment for QA-Style Radiology Report Generation (CliQ-RRG), a unified two-stage framework for interpretable and clinically grounded reporting. In Stage 1, CliQ-RRG employs a Disease-aware Visual-Textual Alignment module that aligns image and text representations using predicted disease embeddings, reinforced by a Prior-Guided Attention Module (PrAM) to capture multi-view dependencies across current and prior scans. In Stage 2, GraphRAG-guided retrieval augments intermediate textual representations with graph-grounded clinical evidence, and a large language model restructures them into concise, interpretable question-answer (QA) pairs with diagnostic summaries. Experiments on two public chest X-ray benchmarks demonstrate that CliQ-RRG consistently outperforms prior methods across both lexical and clinical metrics, generating accurate and clinically coherent QA-style radiology reports. Code is available at: this https URL.
| Comments: | Accepted: EMNLP Findings 2026 |
| Subjects: | Computation and Language (cs.CL) |
| Cite as: | arXiv:2610.13059 [cs.CL] |
| (or arXiv:2610.13059v1 [cs.CL] for this version) | |
| https://doi.org/10.48550/arXiv.2610.13059 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Chandravardhan Singh Raghaw Dr [view email]
[v1]
Fri, 9 Oct 2026 06:13:25 UTC (2,477 KB)
来源：arXiv：cs.CL · arxiv.org