Joint magnetic resonance imaging artifacts and noise reduction on discrete shape space of images

Liu，Xiangyuan1,2; Wu，Zhongke1; Wang，Xingce1; Liu，Quansheng3; Pozo，Jose M.4; Frangi，Alejandro F.5,6,7

2024-09-01

10.1016/j.patcog.2024.110495

Pattern Recognition   影响因子和分区

0031-3203

Magnetic resonance (MR) images can be corrupted by artifacts and noise, potentially leading to misinterpretation of the images. In this paper, we propose a novel approach based on the discrete shape space of images (DSSI) to jointly reduce artifacts and noise in MR images. The proposed method restores MR images in multiple domains based on the distinct generation mechanisms of noise and artifacts. The images in multiple domains are analyzed in a non-Euclidean space. The DSSI is constructed as a Riemannian manifold to measure the intrinsic properties of images. Images are considered shapes from a geometric perspective, and the impact of similarity transformations (e.g., rotation, scaling, and translation) on image analysis is eliminated. The patch-based rank-ordered difference (PROD) detector is defined in k-space within the framework of DSSI to detect and remove sparse outliers that cause artifacts. In addition, a novel similarity function for images is defined using the DSSI and be used to design the improved filter. Finally, the convergence of the improved filter is theoretically analyzed, indicating that our method offers an effective estimator of the ideal image. The experimental results of various MR images demonstrate that the proposed approach outperforms classical and state-of-the-art methods for artifact correction and noise removal, both qualitatively and quantitatively.

Artifact and noise Discrete shape space of images PROD detector Riemannian manifold

SCI ; EI

英语

其他

20241715980946

Geometry ; Image analysis ; Image denoising ; Image enhancement ; Magnetic resonance imaging

Magnetism: Basic Concepts and Phenomena:701.2 ; Information Theory and Signal Processing:716.1 ; Data Processing and Image Processing:723.2 ; Imaging Techniques:746 ; Acoustic Noise:751.4 ; Mathematics:921

ENGINEERING

2-s2.0-85191162882

Scopus

1.School of Artificial Intelligence,Beiing Normal University,Beijing,No.19, Xinjiekouwai St, Haidian District,100875,China
2.National Center for Applied Mathematics Shenzhen,Southern University of Science and Technology,Shenzhen City,No.1088, Xueyuan St, Nanshan District,518055,China
3.Univ Bretagne Sud,Vannes,CNRS UMR 6205, LMBA,F-56000,France
4.School of Computing and School of Medicine,University of Leeds,Leeds,West Yorkshire,LS29JT,United Kingdom
5.Christabel Pankhurst Institute,Division of Informatics,Imaging,and Data Sciences,School of Health Sciences,and the Department of Computer Science,School of Engineering,University of Manchester,Manchester,Oxford Rd,M139PL,United Kingdom
6.Medical Imaging Research Centre (MIRC),Department of Cardiovascular Sciences,and the Department of Electrical Engineering,KU Leuven,Leuven,Belgium
7.lan Turing Institute,London,United Kingdom

Liu，Xiangyuan,Wu，Zhongke,Wang，Xingce,et al. Joint magnetic resonance imaging artifacts and noise reduction on discrete shape space of images[J]. Pattern Recognition,2024,153.

Liu，Xiangyuan,Wu，Zhongke,Wang，Xingce,Liu，Quansheng,Pozo，Jose M.,&Frangi，Alejandro F..(2024).Joint magnetic resonance imaging artifacts and noise reduction on discrete shape space of images.Pattern Recognition,153.

Liu，Xiangyuan,et al."Joint magnetic resonance imaging artifacts and noise reduction on discrete shape space of images".Pattern Recognition 153(2024).