A Custom Loss Function for Deep Learning-Based Brain MRI Reconstruction

The purpose of this work is to test and evaluate a number of candidate loss functions for the reconstruction of diagnostic quality brain MRI images using undersampled k-space data and CNNs. We investigate both per-pixel (L1) and perceptual based (SSIM) loss functions, before developing a custom loss function that incorporates elements of both. We train these loss functions implemented in a UNet architecture on both 4x and 8x undersampled 16-coil MRI data. The custom loss function is shown to produce both the best quantitative results and also sharper and more detailed reconstructions across a number of image contrasts.