This work aims at developing a generalizable Magnetic Resonance Imaging (MRI) reconstruction method in the meta-learning framework. Specifically, we develop a deep reconstruction network induced by a learnable optimization algorithm (LOA) to solve the nonconvex nonsmooth variational model of MRI image reconstruction. In this model, the nonconvex nonsmooth regularization term is parameterized as a structured deep network where the network parameters can be learned from data. We partition these network parameters into two parts: a task-invariant part for the common feature encoder component of the regularization, and a task-specific part to account for the variations in the heterogeneous training and testing data. We train the regularization parameters in a bilevel optimization framework which significantly improves the robustness of the training process and the generalization ability of the network. We conduct a series of numerical experiments using heterogeneous MRI data sets with various undersampling patterns, ratios, and acquisition settings. The experimental results show that our network yields greatly improved reconstruction quality over existing methods and can generalize well to new reconstruction problems whose undersampling patterns/trajectories are not present during training.

Drug repurposing is a quick and economical strategy for developing new therapies with approved drugs. H5N1 is a highly pathogenic avian influenza virus subtype that can cause severe acute lung injury (ALI) and a high mortality rate due to limited treatments. The use of RNA interference (RNAi) is a reliable approach to identify essential genes in diseases. In most genomewide RNAi screenings, virus replication is the readout of interference. Since H5N1 virus infection could induce significant cell death and the percentage of cell death is associated with virus lethality, we designed a genomewide RNAi screening method to identify repurposable drugs against H5N1 virus with cell death as the readout. We discovered that the neurological drug ifenprodil and the anticancer drug flavopiridol could effectively ameliorate murine ALI after influenza A H5N1 virus infection, suggesting that they might be novel remedies for H5N1 virus-induced ALI in addition to the traditional indications.

Learned optimization algorithms are promising approaches to inverse problems by leveraging advanced numerical optimization schemes and deep neural network techniques in machine learning. In this paper, we propose a novel deep neural network architecture imitating an extra proximal gradient algorithm to solve a general class of inverse problems with a focus on applications in image reconstruction. The proposed network features learned regularization that incorporates adaptive sparsification mappings, robust shrinkage selections, and nonlocal operators to improve solution quality. Numerical results demonstrate the improved efficiency and accuracy of the proposed network over several state-of-the-art methods on a variety of test problems.