2026-09-21T23:15:33Z https://www.ideals.illinois.edu/oai-pmh

oai:www.ideals.illinois.edu:2142/124727 2026-01-14 col_2142_5131 col_2142_8888 com_2142_5130 com_2142_8887 com_2142_234

Self-supervised multi-contrast MRI denoising Tu, Jiachen 2024-05-03 Mri Denoising Self-supervised Learning Multi-contrast Mri Magnetic Resonance Imaging (MRI) is pivotal in medical diagnostics, offering essential multi-contrast imaging capabilities. However, MRI quality is often compromised by inherent noise, which can hinder both image clarity and analytical accuracy. This thesis presents the "Corruption2Self" (C2S) framework, a self-supervised method for multi-contrast MRI denoising. C2S utilizes self-generated pseudo-labels from noisy data to enhance contrast fusion and Signal-to-Noise Ratio (SNR), providing a robust solution that facilitates shorter scanning times or improved spatial resolution—critical factors in enhancing patient experience and diagnostic precision. Comparative tests on the M4Raw dataset show that C2S substantially surpasses traditional methods like BM3D and Noise2Self in Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity Index Measure (SSIM). These results underscore the potential of self-supervised learning to improve multi-contrast MRI image quality. Text eng https://hdl.handle.net/2142/124727 Copyright 2024 Jiachen Tu Lam, Fan 2024-05 application/pdf en text Submission published under a 24 month embargo labeled 'Closed Access', the embargo will last until 2026-05-01 The student, Jiachen Tu, accepted the attached license on 2024-05-02 at 19:23. The student, Jiachen Tu, submitted this Thesis for approval on 2024-05-02 at 19:26. This Thesis was approved for publication on 2024-05-03 at 09:16. DSpace SAF Submission Ingestion Package generated from Vireo submission #20769 on 2024-09-16 at 00:51:17 M.S. Thesis Electrical & Computer Engr University of Illinois at Urbana-Champaign Electrical & Computer Eng