arXiv 2508.172992026-09-01cs.CV

FoundDiff：用于通用低剂量CT去噪的基础扩散模型

FoundDiff: Foundational Diffusion Model for Generalizable Low-Dose CT Denoising

Institute of Science and Technology for Brain-inspired Intelligence and MOE Frontiers Center for Brain Science, Fudan University（脑启发智能科学技术研究所和脑科学前沿中心，复旦大学）；Shanghai Key Lab of Intelligent Information Processing, School of Computer Science, Fudan University（智能信息处理上海市重点实验室，复旦大学计算机科学学院）；School of Cyber Science and Engineering, Sichuan University（四川大学网络科学与工程学院）；School of Biomedical Engineering, Shanghai Jiao Tong University（上海交通大学生物医学工程学院）

Zhihao Chen, Qi Gao, Zilong Li, Junping Zhang, Yi Zhang, Jun Zhao, Hongming Shan

备注：: 14 pages, 8 figures

阅读 PDF

arXiv 页面 ↗HTML 原文 ↗

AI总结：

该研究针对现有低剂量CT去噪方法泛化性差的问题，提出基础扩散模型FoundDiff，采用DA-CLIP与DA-Diff的两阶段策略，在多数据集上验证了其优异去噪性能与泛化能力。

摘要：

低剂量计算机断层扫描（CT）去噪对于减少辐射暴露同时确保诊断可接受的图像质量至关重要。尽管近年来深度学习（DL）带来了显著进展，但现有的基于DL的方法通常在特定剂量水平和解剖区域上训练，难以处理不同扫描条件下的多样噪声特征和解剖异质性，限制了其在临床场景中的通用性和鲁棒性。本文提出了FoundDiff，一种用于跨多种剂量水平和解剖区域的统一通用LDCT去噪的基础扩散模型。FoundDiff采用两阶段策略：（i）剂量-解剖感知和（ii）自适应去噪。首先，我们开发了一种剂量和解剖感知的对比语言-图像预训练模型（DA-CLIP），通过利用专门的对比学习策略学习连续表示，这些表示可量化有序剂量变化并识别显著解剖区域，从而实现鲁棒的剂量和解剖感知。其次，我们设计了一种剂量和解剖感知的扩散模型（DA-Diff），通过基于Mamba的新型剂量和解剖条件块（DACB）将从DA-CLIP学习到的剂量和解剖嵌入协同集成到扩散过程中，以执行自适应且通用的去噪。在涵盖三个解剖区域的大型模拟多剂量CT数据集上进行的广泛实验，以及在Mayo-2016、CQ500和仔猪数据集上的跨数据集评估，均表明其具有优异的去噪性能和对未见过的剂量水平及解剖区域的强泛化能力。代码和模型可在https://github.com/hao1635/FoundDiff获取。

英文摘要：

Low-dose computed tomography (CT) denoising is crucial for reduced radiation exposure while ensuring diagnostically acceptable image quality. Despite significant advancements driven by deep learning (DL) in recent years, existing DL-based methods, typically trained on a specific dose level and anatomical region, struggle to handle diverse noise characteristics and anatomical heterogeneity during varied scanning conditions, limiting their generalizability and robustness in clinical scenarios. In this paper, we propose FoundDiff, a foundational diffusion model for unified and generalizable LDCT denoising across various dose levels and anatomical regions. FoundDiff employs a two-stage strategy: (i) dose-anatomy perception and (ii) adaptive denoising. First, we develop a dose- and anatomy-aware contrastive language-image pre-training model (DA-CLIP) to achieve robust dose and anatomy perception by leveraging specialized contrastive learning strategies to learn continuous representations that quantify ordinal dose variations and identify salient anatomical regions. Second, we design a dose- and anatomy-aware diffusion model (DA-Diff) to perform adaptive and generalizable denoising by synergistically integrating the learned dose and anatomy embeddings from DA-CLIP into diffusion process via a novel dose and anatomy conditional block (DACB) based on Mamba. Extensive experiments on a large simulated multi-dose CT dataset spanning three anatomical regions, together with cross-dataset evaluations on Mayo-2016, CQ500, and piglet datasets, demonstrate superior denoising performance and strong generalization to unseen dose levels and anatomical regions. The codes and models are available at https: //github.com/hao1635/FoundDiff.

机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。