Saved in:
Bibliographic Details
Main Authors: Gautam, Siddhant, Li, Angqi, Ravishankar, Saiprasad
Format: Preprint
Published: 2023
Subjects:
Online Access:https://arxiv.org/abs/2312.08507
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914348433145856
author Gautam, Siddhant
Li, Angqi
Ravishankar, Saiprasad
author_facet Gautam, Siddhant
Li, Angqi
Ravishankar, Saiprasad
contents There has been much recent interest in adapting undersampled trajectories in MRI based on training data. In this work, we propose a novel patient-adaptive MRI sampling algorithm based on grouping scans within a training set. Scan-adaptive sampling patterns are optimized together with an image reconstruction network for the training scans. The training optimization alternates between determining the best sampling pattern for each scan (based on a greedy search or iterative coordinate descent (ICD)) and training a reconstructor across the dataset. The eventual scan-adaptive sampling patterns on the training set are used as labels to predict sampling design using nearest neighbor search at test time. The proposed algorithm is applied to the fastMRI knee multicoil dataset and demonstrates improved performance over several baselines.
format Preprint
id arxiv_https___arxiv_org_abs_2312_08507
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Patient-Adaptive and Learned MRI Data Undersampling Using Neighborhood Clustering
Gautam, Siddhant
Li, Angqi
Ravishankar, Saiprasad
Image and Video Processing
There has been much recent interest in adapting undersampled trajectories in MRI based on training data. In this work, we propose a novel patient-adaptive MRI sampling algorithm based on grouping scans within a training set. Scan-adaptive sampling patterns are optimized together with an image reconstruction network for the training scans. The training optimization alternates between determining the best sampling pattern for each scan (based on a greedy search or iterative coordinate descent (ICD)) and training a reconstructor across the dataset. The eventual scan-adaptive sampling patterns on the training set are used as labels to predict sampling design using nearest neighbor search at test time. The proposed algorithm is applied to the fastMRI knee multicoil dataset and demonstrates improved performance over several baselines.
title Patient-Adaptive and Learned MRI Data Undersampling Using Neighborhood Clustering
topic Image and Video Processing
url https://arxiv.org/abs/2312.08507