Memory Efficient Model Based Deep Learning Reconstructions for High Spatial Resolution 3D Non-Cartesian Acquisitions

TL;DR

This paper introduces a memory-efficient block-wise learning method for deep learning-based 3D MRI reconstruction, enabling high-resolution, fast, and high-quality images on a single GPU by reducing memory demands.

Contribution

The authors develop a novel block-wise learning approach that combines gradient checkpointing and patch-wise training to enable deep learning reconstruction of large 3D MRI data on limited GPU memory.

Findings

Significantly improves image quality over L1 wavelet compressed sensing.

Reduces reconstruction time by 38 times.

Enables high-resolution 3D MRI reconstruction on a single GPU.

Abstract

Objective: Model based deep learning (MBDL) has been challenging to apply to the reconstruction of 3D non-Cartesian MRI acquisitions due to extreme GPU memory demand (>250 GB using traditional backpropagation) primarily because the entire volume is needed for data-consistency steps embedded in the model. The goal of this work is to develop and apply a memory efficient method called block-wise learning that combines gradient checkpointing with patch-wise training to allow for fast and high-quality 3D non-Cartesian reconstructions using MBDL. Approach: Block-wise learning applied to a single unroll decomposes the input volume into smaller patches, gradient checkpoints each patch, passes each patch iteratively through a neural network regularizer, and then rebuilds the full volume from these output patches for data-consistency. This method is applied across unrolls during training. Block-wise learning significantly reduces memory requirements by tying GPU memory to user selected patch size instead of the full volume. This algorithm was used to train a MBDL architecture to reconstruct highly undersampled, 1.25mm isotropic, pulmonary magnetic resonance angiography volumes with matrix sizes varying from 300-450 x 200-300 x 300-450 on a single GPU. We compared block-wise learning reconstructions against L1 wavelet compressed reconstructions and proxy ground truth images. Main results: MBDL with block-wise learning significantly improved image quality relative to L1 wavelet compressed sensing while simultaneously reducing average reconstruction time 38x. Significance: Block-wise learning allows for MBDL to be applied to high spatial resolution, 3D non-Cartesian datasets with improved image quality and significant reductions in reconstruction time relative to traditional iterative methods