Coil2Coil 3D: Improved self-supervised MR image denoising using phased-array coil images based on 3D structure information

A deep-learning-based denoising method by extending Coil2Coil method based on 3D network was proposed. This method utilizes 3D information to conserve more tissue structure details. When tested for the synthetic noise-added images, the quantitative metrics were improved than using 2D network (PSNR: 46.57 ± 2.50 for 3D vs. 45.96 ± 2.47 for 2D). For the real-world noise, the proposed method also demonstrated qualitatively improved denoising than 2D case by conserving the structure details in MR images. Additionally, the quantitative mapping experiment for R2* showed the more accurate mapping results, suggesting improvement of the quantification by 3D denoising.