Year: 2024
Type: conference-paper
Abstract: End-to-End (E2E) unrolled optimization frameworks show promise for Magnetic Resonance (MR) image recovery, but suffer from high memory usage during training. In addition, these deterministic approaches do not offer opportunities for sampling from the posterior distribution. In this paper, we introduce a memory-efficient approach for E2E learning of the posterior distribution. We represent this distribution as the combination of a data-consistency-induced likelihood term and an energy model for the prior, parameterized by a Convolutional Neural Network (CNN). The CNN weights are learned from training data in an E2E fashion using maximum likelihood optimization. The learned model enables the recovery of images from undersampled measurements using the Maximum A Posteriori (MAP) optimization. In addition, the posterior model can be sampled to derive uncertainty maps about the reconstruction. Experiments on parallel MR image reconstruction show that our approach performs comparable to the memory-intensive E2E unrolled algorithm, performs better than its memory-efficient counterpart, and can provide uncertainty maps. Our framework paves the way towards MR image reconstruction in 3D and higher dimensions.
Authors: Jyothi Rikhab Chand, Mathews Jacob
Institution: University of Iowa
Language: English
Subfield: Radiology, Nuclear Medicine and Imaging
Field: Medicine
Domain: Health Sciences
Open Access status: green
Awards: Fast Multi-dimensional Diffusion MRI with Sparse Sampling and Model-basedDeep Learning Reconstruction, High Resolution MRSI for Alzheimer's Disease and Related Dementias, Novel Computational Framework for Free-Breathing & Ungated Dynamic MRI, Model Based Deep Learning Framework for Ultra-High Resolution Multi-Contrast MRI
OpenAlex ID: W4401750102