-
Memory-efficient Learning for High-Dimensional MRI Reconstruction
-
Ke Wang and Michael Kellman and Christopher M. Sandino and Kevin Zhang and Shreyas S. Vasanawala and Jonathan I. Tamir and Stella X. Yu and Michael Lustig
-
International Conference on Medical Image Computing and Computer Assisted Intervention, Online, 27 September - 1 October 2021
-
Paper
|
Poster
|
arXiv
-
Abstract
-
Deep learning (DL) based unrolled reconstructions have shown state-of-the-art performance for under-sampled magnetic resonance imaging (MRI). Similar to compressed sensing, DL can leverage high-dimensional data (e.g. 3D, 2D+time, 3D+time) to further improve performance. However, network size and depth are currently limited by the GPU memory required for backpropagation. Here we use a memory-efficient learning (MEL) framework which favorably trades off storage with a manageable increase in computation during training. Using MEL with multi-dimensional data, we demonstrate improved image reconstruction performance for in-vivo 3D MRI and 2D+time cardiac cine MRI. MEL uses far less GPU memory while marginally increasing the training time, which enables new applications of DL to high-dimensional MRI. Our code is available at \url{https://github.com/mikgroup/MEL_MRI}.
-
Keywords
-
magnetic resonance imaging, unrolled reconstruction, memory-efficient learning
|