Off-the-grid model based deep learning (O-MODL)
This work addresses computational efficiency in image reconstruction for medical imaging or similar domains, but appears incremental as it builds on existing model-based deep learning frameworks.
The authors tackled the problem of image reconstruction by introducing an off-the-grid model-based deep learning algorithm that learns non-linear annihilation relations in Fourier space, resulting in a significant reduction in computational complexity compared to structured low-rank methods.
We introduce a model based off-the-grid image reconstruction algorithm using deep learned priors. The main difference of the proposed scheme with current deep learning strategies is the learning of non-linear annihilation relations in Fourier space. We rely on a model based framework, which allows us to use a significantly smaller deep network, compared to direct approaches that also learn how to invert the forward model. Preliminary comparisons against image domain MoDL approach demonstrates the potential of the off-the-grid formulation. The main benefit of the proposed scheme compared to structured low-rank methods is the quite significant reduction in computational complexity.