MRI recovery with self-calibrated denoisers without fully-sampled data

Objective Acquiring fully sampled training data is challenging for many MRI applications. We present a self-supervised image reconstruction method, termed ReSiDe, capable of recovering images solely from undersampled data. Materials and methods ReSiDe is inspired by plug-and-play (PnP) methods, but...

Full description

Saved in:
Bibliographic Details
Published in:Magma (New York, N.Y.) Vol. 38; no. 1; pp. 53 - 66
Main Authors: Shafique, Muhammad, Liu, Sizhuo, Schniter, Philip, Ahmad, Rizwan
Format: Journal Article
Language:English
Published: Cham Springer International Publishing 01.02.2025
Subjects:
Algorithms
Basic Science - Reconstruction algorithms and artificial intelligence
Biomedical Engineering and Bioengineering
Brain - diagnostic imaging
Calibration
Computer Appl. in Life Sciences
Health Informatics
Heart - diagnostic imaging
Humans
Image Processing, Computer-Assisted - methods
Imaging
Magnetic Resonance Imaging - methods
Medicine
Medicine & Public Health
Phantoms, Imaging
Radiology
Reproducibility of Results
Research Article
Signal-To-Noise Ratio
Solid State Physics
Reconstruction
MRI
Self-supervised
ISSN:1352-8661, 0968-5243, 1352-8661
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Objective Acquiring fully sampled training data is challenging for many MRI applications. We present a self-supervised image reconstruction method, termed ReSiDe, capable of recovering images solely from undersampled data. Materials and methods ReSiDe is inspired by plug-and-play (PnP) methods, but unlike traditional PnP approaches that utilize pre-trained denoisers, ReSiDe iteratively trains the denoiser on the image or images that are being reconstructed. We introduce two variations of our method: ReSiDe-S and ReSiDe-M. ReSiDe-S is scan-specific and works with a single set of undersampled measurements, while ReSiDe-M operates on multiple sets of undersampled measurements and provides faster inference. Studies I, II, and III compare ReSiDe-S and ReSiDe-M against other self-supervised or unsupervised methods using data from T1- and T2-weighted brain MRI, MRXCAT digital perfusion phantom, and first-pass cardiac perfusion, respectively. Results ReSiDe-S and ReSiDe-M outperform other methods in terms of peak signal-to-noise ratio and structural similarity index measure for Studies I and II, and in terms of expert scoring for Study III. Discussion We present a self-supervised image reconstruction method and validate it in both static and dynamic MRI applications. These developments can benefit MRI applications where the availability of fully sampled training data is limited.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
ISSN:1352-8661
0968-5243
1352-8661
DOI:10.1007/s10334-024-01207-1