Improving Fast MRI Reconstructions with Pretext Learning in Low-Data Regime.

Supervised deep learning methods have shown great promise for making magnetic resonance (MR) imaging scans faster. However, these supervised deep learning models need large volumes of labelled data to learn valuable representations and produce high-fidelity MR image reconstructions. The data used to train these models are often fully-sampled raw MR data, retrospectively under-sampled to simulate different MR acquisition acceleration factors. Obtaining high-quality, fully sampled raw MR data is costly and time-consuming. In this paper, we exploit the self supervision based learning by introducing a pretext method to boost feature learning using the more commonly available under-sampled MR data. Our experiments using different deep-learning-based reconstruction models in a low data regime demonstrate that self-supervision ensures stable training and improves MR image reconstruction.