AutoSamp: Autoencoding k-space Sampling via Variational Information Maximization for 3D MRI
arXiv:2306.02888 · doi:10.1109/TMI.2024.3443292
Abstract
Accelerated MRI protocols routinely involve a predefined sampling pattern that undersamples the k-space. Finding an optimal pattern can enhance the reconstruction quality, however this optimization is a challenging task. To address this challenge, we introduce a novel deep learning framework, AutoSamp, based on variational information maximization that enables joint optimization of sampling pattern and reconstruction of MRI scans. We represent the encoder as a non-uniform Fast Fourier Transform that allows continuous optimization of k-space sample locations on a non-Cartesian plane, and the decoder as a deep reconstruction network. Experiments on public 3D acquired MRI datasets show improved reconstruction quality of the proposed AutoSamp method over the prevailing variable density and variable density Poisson disc sampling for both compressed sensing and deep learning reconstructions. We demonstrate that our data-driven sampling optimization method achieves 4.4dB, 2.0dB, 0.75dB, 0.7dB PSNR improvements over reconstruction with Poisson Disc masks for acceleration factors of R = 5, 10, 15, 25, respectively. Prospectively accelerated acquisitions with 3D FSE sequences using our optimized sampling patterns exhibit improved image quality and sharpness. Furthermore, we analyze the characteristics of the learned sampling patterns with respect to changes in acceleration factor, measurement noise, underlying anatomy, and coil sensitivities. We show that all these factors contribute to the optimization result by affecting the sampling density, k-space coverage and point spread functions of the learned sampling patterns.
Accepted for publication in IEEE Transactions on Medical Imaging (TMI)
References in corpus (10)
- Image reconstruction by domain transform manifold learning
- MoDL: Model Based Deep Learning Architecture for Inverse Problems
- Compressed Sensing MRI Reconstruction using a Generative Adversarial Network with a Cyclic Loss
- Deep learning for undersampled MRI reconstruction
- J-MoDL: Joint Model-Based Deep Learning for Optimized Sampling and Reconstruction
- B-spline Parameterized Joint Optimization of Reconstruction and K-space Trajectories (BJORK) for Accelerated 2D MRI
- OEDIPUS: An Experiment Design Framework for Sparsity-Constrained MRI
- Active MR k-space Sampling with Reinforcement Learning
- Learning Sampling and Model-Based Signal Recovery for Compressed Sensing MRI
- Efficient approximation of Jacobian matrices involving a non-uniform fast Fourier transform (NUFFT)