UniSino用物理模型统一标准化CT投影数据，提升重建质量。
UniSino: Physics-Driven Foundational Model for Universal CT Sinogram Standardization
- 直接在投影域建模，融合物理特性增强泛化能力。
- 在四个数据集上均优于现有方法，混合欠采样下表现突出。
- 适合医学影像、低剂量CT等需要鲁棒重建的场景。
CT成像原始数据采集过程中，多种因素会降低获取的sinogram质量，其中欠采样和噪声会导致重建图像中出现严重伪影和噪声，影响诊断准确性。传统校正方法依赖人工设计算法或固定经验参数，难以跨异构伪影类型通用。为此，我们提出UniSino——一种用于通用CT sinogram标准化的基础模型。与以往在图像域操作的基础模型不同，UniSino直接在投影域进行标准化，具备更强的跨多样欠采样场景的泛化能力。其训练框架融入sinogram的物理特性，提升了跨多个子任务的鲁棒性，在四个基准数据集上均取得优异表现。实验表明，UniSino在单个及混合欠采样情况下均实现更优的重建质量，展现出卓越的鲁棒性与泛化能力。代码已开源：https://github.com/yqx7150/UniSino。
原文摘要 · Abstract (English)
During raw-data acquisition in CT imaging, diverse factors can degrade the collected sinograms, with undersampling and noise leading to severe artifacts and noise in reconstructed images and compromising diagnostic accuracy. Conventional correction methods rely on manually designed algorithms or fixed empirical parameters, but these approaches often lack generalizability across heterogeneous artifact types. To address these limitations, we propose UniSino, a foundation model for universal CT sinogram standardization. Unlike existing foundational models that operate in image domain, UniSino directly standardizes data in the projection domain, which enables stronger generalization across diverse undersampling scenarios. Its training framework incorporates the physical characteristics of sinograms, enhancing generalization and enabling robust performance across multiple subtasks spanning four benchmark datasets. Experimental results demonstrate thatUniSino achieves superior reconstruction quality both single and mixed undersampling case, demonstrating exceptional robustness and generalization in sinogram enhancement for CT imaging. The code is available at: https://github.com/yqx7150/UniSino.
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。