Generalized Deep Learning-based Proximal Gradient Descent for MR Reconstruction
This addresses the need for adaptable MR reconstruction methods in clinical practice, though it is incremental as it builds on existing proximal gradient descent frameworks.
The paper tackled the problem of generalizing deep learning-based MR reconstruction across varying acquisition settings by decoupling the learned regularization from the forward model, resulting in a ~3 dB improvement in peak signal-to-noise ratio compared to conventional L1 regularization.
The data consistency for the physical forward model is crucial in inverse problems, especially in MR imaging reconstruction. The standard way is to unroll an iterative algorithm into a neural network with a forward model embedded. The forward model always changes in clinical practice, so the learning component's entanglement with the forward model makes the reconstruction hard to generalize. The deep learning-based proximal gradient descent was proposed and use a network as regularization term that is independent of the forward model, which makes it more generalizable for different MR acquisition settings. This one-time pre-trained regularization is applied to different MR acquisition settings and was compared to conventional L1 regularization showing ~3 dB improvement in the peak signal-to-noise ratio. We also demonstrated the flexibility of the proposed method in choosing different undersampling patterns.