Denoising low-field MR images with a deep learning algorithm based on simulated data from easily accessible open-source software
Aram Salehi, Mathieu Mach, Chloé Najac, Beatrice Lena, Thomas O’Reilly, Yiming Dong, Peter Börnert, Hieab H.H. Adams, Tavia E. Evans, Andrew M. Webb · Journal of Magnetic Resonance · 2024
• A deep learning pipeline for low field MRI has been developed based on open-source simulation data. • This pipeline produces effective denoising of low field images while maintaining high spatial frequencies. • Comparisons with a 3T FLAIR scan show its ability to highlight low contrast to noise white matter hyperintensities. In this study, we introduce a denoising method aimed at improving the contrast ratio in low-field MRI (LFMRI) using an advanced 3D deep convolutional residual network model. Our approach employs synthetic brain imaging datasets that closely mimic the contrast and noise characteristics of LFMRI scans, addressing the limitation of available in-vivo LFMRI datasets for training deep learning models. In the simulation data, the Relative Contrast Ratio (RCR) increased, and similar improvements were observed in the in-vivo data across different imaging conditions. Comparative evaluations demonstrate that our model performs better than the widely used non-deep learning method, BM4D, in enhancing RCR and maintaining high spatial frequency components in in-vivo data.