Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction

doi:arXiv:2502.05445

	Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction
	Tian, Xuanyu1,2 ; Chen, Lixuan 3; Wu, Qing1 ; Du, Chenhe1 ; Shi, Jingjing 4; Wei, Hongjiang 5; Zhang, Yuyao1
	2025-02-08
状态	已发表
摘要	Emerging unsupervised implicit neural representation (INR) methods, such as NeRP, NeAT, and SCOPE, have shown great potential to address sparse-view computed tomography (SVCT) inverse problems. Although these INR-based methods perform well in relatively dense SVCT reconstructions, they struggle to achieve comparable performance to supervised methods in sparser SVCT scenarios. They are prone to being affected by noise, limiting their applicability in real clinical settings. Additionally, current methods have not fully explored the use of image domain priors for solving SVCsT inverse problems. In this work, we demonstrate that imperfect reconstruction results can provide effective image domain priors for INRs to enhance performance. To leverage this, we introduce Self-prior embedding neural representation (Spener), a novel unsupervised method for SVCT reconstruction that integrates iterative reconstruction algorithms. During each iteration, Spener extracts local image prior features from the previous iteration and embeds them to constrain the solution space. Experimental results on multiple CT datasets show that our unsupervised Spener method achieves performance comparable to supervised state-of-the-art (SOTA) methods on in-domain data while outperforming them on out-of-domain datasets. Moreover, Spener significantly improves the performance of INR-based methods in handling SVCT with noisy sinograms. Our code is available at https://github.com/MeijiTian/Spener.
语种	英语
DOI	arXiv:2502.05445
相关网址	查看原文
出处	Arxiv
收录类别	PPRN.PPRN
WOS记录号	PPRN:121315683
WOS类目	Computer Science, Software Engineering ; Engineering, Electrical& Electronic
资助项目	National Natural Science Foundation of China[62071299]
文献类型	预印本
条目标识符	https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/507024
专题	信息科学与技术学院信息科学与技术学院_博士生信息科学与技术学院_PI研究组_张玉瑶组
通讯作者	Zhang, Yuyao
作者单位	1.ShanghaiTech Univ, Sch Informat Sci & Technol, Shanghai 201210, Peoples R China 2.Lingang Lab, Shanghai 200031, Peoples R China 3.Univ Michigan, Elect & Comp Engn, Ann Arbor, MI 48105, USA 4.Huazhong Univ Sci & Technol, Tongji Hosp, Tongji Med Coll, Wuhan 430030, Peoples R China 5.Shanghai Jiao Tong Univ, Sch Biomed Engn, Shanghai 200127, Peoples R China
推荐引用方式 GB/T 7714	Tian, Xuanyu,Chen, Lixuan,Wu, Qing,et al. Unsupervised Self-Prior Embedding Neural Representation for Iterative Sparse-View CT Reconstruction. 2025.