用智能代理动态分配专家模型，提升低剂量CT图像去噪效果
A-IDE : Agent-Integrated Denoising Experts
- 通过语义分析动态路由图像到对应解剖区域专家模型
- 在梅奥2016数据集上RMSE、PSNR、SSIM均优于单一模型
- 无需人工干预，适合数据稀疏的临床场景
基于深度学习的去噪方法虽提升了低剂量CT图像质量，但因不同解剖区域的灰度分布和结构差异，单一模型难以跨区域泛化。为此，我们提出Agent-Integrated Denoising Experts（A-IDE）框架，集成三个针对特定解剖区域优化的RED-CNN专家模型，并由决策型LLM代理管理。该代理利用BiomedCLIP提取语义线索，动态将输入的低剂量CT扫描分配至最合适的专家模型。本方法在异构、数据稀缺环境下表现优异，通过任务分散自动防止过拟合。此外，由LLM驱动的智能流水线无需人工干预。在Mayo-2016数据集上的实验表明，A-IDE在RMSE、PSNR和SSIM指标上均优于单一统一去噪器。
原文摘要 · Abstract (English)
Recent advances in deep-learning based denoising methods have improved Low-Dose CT image quality. However, due to distinct HU distributions and diverse anatomical characteristics, a single model often struggles to generalize across multiple anatomies. To address this limitation, we introduce \textbf{Agent-Integrated Denoising Experts (A-IDE)} framework, which integrates three anatomical region-specialized RED-CNN models under the management of decision-making LLM agent. The agent analyzes semantic cues from BiomedCLIP to dynamically route incoming LDCT scans to the most appropriate expert model. We highlight three major advantages of our approach. A-IDE excels in heterogeneous, data-scarce environments. The framework automatically prevents overfitting by distributing tasks among multiple experts. Finally, our LLM-driven agentic pipeline eliminates the need for manual interventions. Experimental evaluations on the Mayo-2016 dataset confirm that A-IDE achieves superior performance in RMSE, PSNR, and SSIM compared to a single unified denoiser.
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。