Improving DCE-MRI through Unfolded Low-Rank + Sparse Optimisation

A method for perfusion imaging with DCE-MRI is developed based on a combination of two popular paradigms: the low-rank + sparse model for optimisation-based reconstruction, and the deep unfolding. A learnable algorithm derived from a proximal method is designed with emphasis on simplicity and interpretability. The resulting deep network is trained and evaluated using a simulated measurement of a rat with a brain tumor, showing large performance gain over the classical low-rank + sparse baseline. Moreover, a quantitative perfusion analysis is performed based on the reconstructed sequence, proving that even training based on a simple pixel-wise error can lead to a significant improvement of the quality of the perfusion maps.