解决3D CT报告生成中病灶覆盖不全问题，通过动态检索增强视觉表征。
Beyond the Embedding Bottleneck: Adaptive Retrieval-Augmented 3D CT Report Generation
- 引入自适应检索机制，用文本信息补偿3D图像表征的维度瓶颈
- 在CT-RATE数据集上临床F1提升至0.480，较基线+6点
- 适合关注医学影像生成与检索增强融合的临床研究者
从3D CT体数据自动生成放射科报告常因病灶覆盖不全而受限。我们实证表明，该局限源于表征瓶颈：对比学习生成的3D CT嵌入虽能区分病灶，但存在严重维度集中，512维中仅有约2个有效维度。进一步发现，语言模型规模扩大无法带来性能提升，说明瓶颈在于视觉表征而非生成器。该瓶颈同时限制生成与检索；静态检索方法无法提升临床效果，甚至可能恶化性能。为此，我们提出AdaRAG-CT，一种自适应增强框架，通过受控检索引入补充文本信息，并在生成时选择性融合。在CT-RATE基准测试中，该方法达到当前最优临床效能，临床F1从CT-Agent的0.420提升至0.480（+6点）；消融实验验证了检索与生成组件的共同贡献。代码已开源。
原文摘要 · Abstract (English)
Automated radiology report generation from 3D CT volumes often suffers from incomplete pathology coverage. We provide empirical evidence that this limitation stems from a representational bottleneck: contrastive 3D CT embeddings encode discriminative pathology signals, yet exhibit severe dimensional concentration, with as few as 2 effective dimensions out of 512. Corroborating this, scaling the language model yields no measurable improvement, suggesting that the bottleneck lies in the visual representation rather than the generator. This bottleneck limits both generation and retrieval; naive static retrieval fails to improve clinical efficacy and can even degrade performance. We propose \textbf{AdaRAG-CT}, an adaptive augmentation framework that compensates for this visual bottleneck by introducing supplementary textual information through controlled retrieval and selectively integrating it during generation. On the CT-RATE benchmark, AdaRAG-CT achieves state-of-the-art clinical efficacy, improving Clinical F1 from 0.420 (CT-Agent) to 0.480 (+6 points); ablation studies confirm that both the retrieval and generation components contribute to the improvement. Code is available at https://github.com/renjie-liang/Adaptive-RAG-for-3DCT-Report-Generation.
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。