DuDoCROP: Dual-Domain CLIP-Assisted Residual Optimization Perception Model for CT Metal Artifact Reduction

作者：Xinrui Zhang, Ailong Cai, Shaoyu Wang, Linyuan Wang, Zhizhong Zheng, Lei Li, Bin Yan · 发表于：IEEE Transactions on Radiation and Plasma Medical Sciences · 年份：2025 · DOI：10.1109/trpms.2025.3628646 · 被引用次数：1 · 研究领域：Advanced X-ray and CT Imaging、Medical Imaging Techniques and Applications、Advanced X-ray Imaging Techniques

Metal artifacts in computed tomography (CT) imaging pose significant challenges to accurate clinical diagnosis. The presence of high-density metallic implants results in artifacts that deteriorate image quality, manifesting in the forms of streaking, blurring, or beam hardening effects, etc. Nowadays, various deep learning-based approaches, particularly generative models, have been proposed for metal artifact reduction (MAR). However, these methods exhibit limited perception ability in the diverse morphologies of different metal implants with artifacts, which may generate spurious anatomical structures and exhibit inferior generalization capability. To address the issues, we leverage visual-language model (VLM) to identify these morphological features and introduce them into a dual-domain CLIP-assisted residual optimization perception model (DuDoCROP) for MAR. Specifically, a dual-domain CLIP (DuDoCLIP) is fine-tuned using contrastive learning to extract semantic descriptions of clean images and metal-affected regions in both image domain and sinogram domain. Subsequently, a diffusion model is guided by the embeddings of DuDoCLIP, thereby enabling the dual-domain prior generation. Additionally, we design prompt engineering for more precise image-text descriptions that can enhance the model’s perception capability. Then, a downstream task is devised for the one-step residual optimization and integration of dual-domain priors. Ultimately, a new perceptual indicator (PI) is prop...