UniSino: Physics-Driven Foundational Model for Universal CT Sinogram Standardization
This addresses the need for generalizable correction methods in CT imaging to improve diagnostic accuracy, though it appears incremental as it builds on foundational models by shifting to the projection domain.
The paper tackles the problem of degraded CT sinograms due to undersampling and noise, which cause artifacts and reduce diagnostic accuracy, by proposing UniSino, a foundational model that standardizes sinograms in the projection domain, achieving superior reconstruction quality and robustness across multiple datasets.
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.