On learning adaptive acquisition policies for undersampled multi-coil MRI reconstruction
This addresses the challenge of improving MRI reconstruction quality for faster scanning, particularly at high acceleration factors, but is incremental as it builds on existing methods with mixed results.
The paper tackles the problem of jointly learning acquisition policies and reconstruction models for undersampled multi-coil MRI, finding that adaptive policies show on-par performance at 4× acceleration and a more than 2% improvement in SSIM at 8× acceleration, though the best policies learned to be non-adaptive.
Most current approaches to undersampled multi-coil MRI reconstruction focus on learning the reconstruction model for a fixed, equidistant acquisition trajectory. In this paper, we study the problem of joint learning of the reconstruction model together with acquisition policies. To this end, we extend the End-to-End Variational Network with learnable acquisition policies that can adapt to different data points. We validate our model on a coil-compressed version of the large scale undersampled multi-coil fastMRI dataset using two undersampling factors: $4\times$ and $8\times$. Our experiments show on-par performance with the learnable non-adaptive and handcrafted equidistant strategies at $4\times$, and an observed improvement of more than $2\%$ in SSIM at $8\times$ acceleration, suggesting that potentially-adaptive $k$-space acquisition trajectories can improve reconstructed image quality for larger acceleration factors. However, and perhaps surprisingly, our best performing policies learn to be explicitly non-adaptive.