Convolutional neural networks trained end-to-end achieve state-of-the-art image quality for accelerated MRI. But end-to-end networks are trained for a specific undersampling operator. A more flexible approach that can work with any undersampling operator at inference is to train a generative image prior and impose it during reconstruction. In this work, we train a flow-based generator on image patches and then impose it as a prior in the reconstruction. We find that this method achieves slightly better reconstruction quality than state-of-the-art un-trained methods and slightly worse quality than neural networks trained end-to-end on the 4x accelerated multi-coil fastMRI dataset.
This abstract and the presentation materials are available to members only; a login is required.