Optimized Parallel Combination of Deep Networks and Sparsity Regularization for MR Image Reconstruction (OPCoNS)
Abstract
This work examines optimized parallel combinations of deep networks and conventional regularized reconstruction for improved quality of MR image reconstructions from undersampled k-space data. Features learned by deep networks and typical model-based iterative algorithms (e.g., sparsity-penalized reconstruction) could complement each other for effective reconstructions. We observe that combining the image features from multiple approaches in a parallel fashion with appropriate learned weights leads to more effective image representations that are not captured by either strictly supervised or (unsupervised) conventional iterative methods.
References
Avrajit Ghosh, Shijun Liang, Anish Lahiri, and Saiprasad Ravishankar. "Optimized Parallel Combination of Deep Networks and Sparsity Regularization for MR Image Reconstruction (OPCoNS) ." ISMRM 2022.
Adaptive Local Neighborhood-based Neural Networks for MR Image Reconstruction from Undersampled Data
Recent medical image reconstruction techniques focus on generating high-quality medical images suitable for clinical use at the lowest possible cost and with the fewest possible adverse effects on patients. Recent works have shown significant promise for reconstructing MR images from sparsely sampled k-space data using deep learning. In this work, we propose a technique that rapidly estimates deep neural networks directly at reconstruction time by fitting them on small adaptively estimated neighborhoods of a training set. In brief, our algorithm alternates between searching for neighbors in a data set that are similar to the test reconstruction, and training a local network on these neighbors followed by updating the test reconstruction. Because our reconstruction model is learned on a dataset that is structurally similar to the image being reconstructed rather than being fit on a large, diverse training set, it is more adaptive to new scans. It can also handle changes in training sets and flexible scan settings, while being relatively fast. Our approach, dubbed LONDN-MRI, was validated on the FastMRI multi-coil knee data set using deep unrolled reconstruction networks. Reconstructions were performed at four fold and eight fold undersampling of k-space with 1D variable-density random phase-encode undersampling masks. Our results demonstrate that our proposed locally-trained method produces higher-quality reconstructions compared to models trained globally on larger datasets.
References
S. Liang, A. Sreevatsa, A. Lahiri and S. Ravishankar, "LONDN-MRI: Adaptive Local Neighborhood-Based Networks for MR Image Reconstruction from Undersampled Data," 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI), Kolkata, India, 2022.
S. Liang, A. Lahiri, & S. Ravishankar. (2022). "Adaptive Local Neighborhood-based Neural Networks for MR Image Reconstruction from Undersampled Data". arXiv preprint arXiv:2206.00775.