Compressive MR Fingerprinting reconstruction with Neural Proximal Gradient iterations
This work addresses reliability in MRF reconstruction for medical imaging, representing an incremental improvement by integrating physical models into a neural framework.
The paper tackled the problem of ensuring consistency with physical models in Magnetic Resonance Fingerprinting (MRF) reconstruction by proposing ProxNet, a learned proximal gradient descent framework that incorporates forward acquisition and Bloch dynamic models, achieving superior quantitative inference accuracy and smaller storage requirements compared to deep learning baselines.
Consistency of the predictions with respect to the physical forward model is pivotal for reliably solving inverse problems. This consistency is mostly un-controlled in the current end-to-end deep learning methodologies proposed for the Magnetic Resonance Fingerprinting (MRF) problem. To address this, we propose ProxNet, a learned proximal gradient descent framework that directly incorporates the forward acquisition and Bloch dynamic models within a recurrent learning mechanism. The ProxNet adopts a compact neural proximal model for de-aliasing and quantitative inference, that can be flexibly trained on scarce MRF training datasets. Our numerical experiments show that the ProxNet can achieve a superior quantitative inference accuracy, much smaller storage requirement, and a comparable runtime to the recent deep learning MRF baselines, while being much faster than the dictionary matching schemes. Code has been released at https://github.com/edongdongchen/PGD-Net.