GenDiff：一种具有结构先验细化的剂量和解剖感知扩散模型，用于低剂量CT重建和泛化
GenDiff: A Dose and Anatomy Aware Diffusion Model with Structural Prior Refinement for Low-Dose CT Reconstruction and Generalization
浏览论文内容
中文总结 AI 辅助
针对低剂量CT重建中现有方法局限性，提出GenDiff框架，联合建模剂量与解剖信息，集成多种模块，经多数据集实验验证，该方法在不同条件下鲁棒性强且重建质量优，是低剂量CT成像的有前途方案。
中文摘要 AI 辅助
计算机断层扫描（CT）是临床诊断的关键成像方式，但降低辐射剂量不可避免地会引入严重噪声和结构化伪影，降低图像质量。现有基于深度学习的低剂量CT（LDCT）重建方法通常针对固定剂量水平或特定解剖区域进行优化，限制了其在实际临床环境中的鲁棒性和泛化能力。我们提出了GenDiff，一种用于LDCT重建的基于扩散的通用框架，该框架在统一的重建网络中联合建模连续辐射剂量和解剖信息。所提出的框架集成了剂量-解剖编码器以学习采集感知嵌入，一个由剂量和解剖条件控制的冷扩散主干用于迭代细化，一个物理一致性更新以确保对CT正向模型的保真度，以及一个结构先验细化模块（SPRM），该模块在抑制剂量依赖性伪影的同时保留解剖结构。在多解剖临床数据集上进行的广泛实验，包括未见的超低剂量条件以及分布外的体模和动物数据集，表明GenDiff始终优于现有的基于卷积神经网络和基于扩散的重建方法。所提出的方法在不同剂量水平、解剖区域和采集域中保持强大的鲁棒性的同时，实现了卓越的重建质量，使其成为实际低剂量CT成像的有前途的解决方案。
英文摘要
Computed tomography (CT) is a critical imaging modality for clinical diagnosis, but reducing radiation dose inevitably introduces severe noise and structured artifacts that degrade image quality. Existing deep learning-based low-dose CT (LDCT) reconstruction methods are typically optimized for fixed dose levels or specific anatomical regions, limiting their robustness and generalization in realistic clinical settings. We propose GenDiff, a generalizable diffusion-based framework for LDCT reconstruction that jointly models continuous radiation dose and anatomical information within a unified reconstruction network. The proposed framework integrates a Dose-Anatomy Encoder to learn acquisition-aware embeddings, a dose- and anatomy-conditioned cold diffusion backbone for iterative refinement, a physics-consistency update to enforce fidelity to the CT forward model, and a Structural Prior Refinement Module (SPRM) that preserves anatomical structures while suppressing dose-dependent artifacts. Extensive experiments on multi-anatomy clinical datasets, including unseen ultra-low-dose conditions as well as out-of-distribution phantom and animal datasets, demonstrate that GenDiff consistently outperforms state-of-the-art convolutional neural network and diffusion-based reconstruction methods. The proposed approach achieves superior reconstruction quality while maintaining strong robustness across different dose levels, anatomical regions, and acquisition domains, making it a promising solution for practical low-dose CT imaging.
发表机构
- Faculty of Information Science & Technology, Multimedia University, Malaysia（马来西亚多媒体大学信息科学与技术学院）
机构由 AI 辅助整理，请以论文原文为准。
