Learning spatially adaptive sparsity level maps for arbitrary convolutional dictionaries
This work addresses interpretability and robustness issues in image reconstruction for low-field MRI, though it is incremental as it builds on an existing method with improvements in network design and training.
The paper tackled the problem of improving interpretability and robustness in learned image reconstruction methods by extending a model-based convolutional dictionary regularization approach with spatially adaptive sparsity level maps, achieving filter-permutation invariance and adaptability to different dictionaries at inference time, and showing reduced performance degradation on out-of-distribution data compared to other deep learning methods.
State-of-the-art learned reconstruction methods often rely on black-box modules that, despite their strong performance, raise questions about their interpretability and robustness. Here, we build on a recently proposed image reconstruction method, which is based on embedding data-driven information into a model-based convolutional dictionary regularization via neural network-inferred spatially adaptive sparsity level maps. By means of improved network design and dedicated training strategies, we extend the method to achieve filter-permutation invariance as well as the possibility to change the convolutional dictionary at inference time. We apply our method to low-field MRI and compare it to several other recent deep learning-based methods, also on in vivo data, in which the benefit for the use of a different dictionary is showcased. We further assess the method's robustness when tested on in- and out-of-distribution data. When tested on the latter, the proposed method suffers less from the data distribution shift compared to the other learned methods, which we attribute to its reduced reliance on training data due to its underlying model-based reconstruction component.