AI RESEARCH
One CT Unified Model Training Framework to Rule All Scanning Protocols
arXiv CS.CV
•
ArXi:2603.15025v1 Announce Type: new Non-ideal measurement computed tomography (NICT), which lowers radiation at the cost of image quality, is expanding the clinical use of CT. Although unified models have shown promise in NICT enhancement, most methods require paired data, which is an impractical demand due to inevitable organ motion. Unsupervised approaches attempt to overcome this limitation, but their assumption of homogeneous noise neglects the variability of scanning protocols, leading to poor generalization and potential model collapse.