Personalized synthetic MR imaging with deep learning enhancements

Purpose Personalized synthetic MRI (syn‐MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to obtain underlying parametric (ρ,T1,T2)$$ \left(\rho, {\mathrm{T}}_1,{\mathrm{T}}_2\right) $$ maps, from where MR images of that individ...

Full description

Saved in:
Bibliographic Details
Published in:Magnetic resonance in medicine Vol. 89; no. 4; pp. 1634 - 1643
Main Authors: Pal, Subrata, Dutta, Somak, Maitra, Ranjan
Format: Journal Article
Language:English
Published: United States Wiley Subscription Services, Inc 01.04.2023
John Wiley and Sons Inc
Subjects:
Bloch transform
Computer architecture
Customization
Deep Learning
deep‐image‐prior
denoising
Design parameters
Image acquisition
Image enhancement
Image Processing, Computer-Assisted - methods
Inverse problems
Low noise
Magnetic resonance imaging
Magnetic Resonance Imaging - methods
Maximum likelihood estimators
Neural networks
Neural Networks, Computer
Noise levels
Noise reduction
Nonuniformity
Regularization
Signal-To-Noise Ratio
Software
Synthesis
synthetic MRI
Technical Note
Technical Note—Computer Processing and Modeling
Training
Workflow
denoising
deep-learning
Bloch transform
synthetic MRI
deep-image-prior
ISSN:0740-3194, 1522-2594, 1522-2594
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Purpose Personalized synthetic MRI (syn‐MRI) uses MR images of an individual subject acquired at a few design parameters (echo time, repetition time, flip angle) to obtain underlying parametric (ρ,T1,T2)$$ \left(\rho, {\mathrm{T}}_1,{\mathrm{T}}_2\right) $$ maps, from where MR images of that individual at other design parameter settings are synthesized. However, classical methods that use least‐squares (LS) or maximum likelihood estimators (MLE) are unsatisfactory at higher noise levels because the underlying inverse problem is ill‐posed. This article provides a pipeline to enhance the synthesis of such images in three‐dimensional (3D) using a deep learning (DL) neural network architecture for spatial regularization in a personalized setting where having more than a few training images is impractical. Methods Our DL enhancements employ a Deep Image Prior (DIP) with a U‐net type denoising architecture that includes situations with minimal training data, such as personalized syn‐MRI. We provide a general workflow for syn‐MRI from three or more training images. Our workflow, called DIPsyn‐MRI, uses DIP to enhance training images, then obtains parametric images using LS or MLE before synthesizing images at desired design parameter settings. DIPsyn‐MRI is implemented in our publicly available Python package DeepSynMRI available at: https://github.com/StatPal/DeepSynMRI. Results We demonstrate feasibility and improved performance of DIPsyn‐MRI on 3D datasets acquired using the Brainweb interface for spin‐echo and FLASH imaging sequences, at different noise levels. Our DL enhancements improve syn‐MRI in the presence of different intensity nonuniformity levels of the magnetic field, for all but very low noise levels. Conclusion This article provides recipes and software to realistically facilitate DL‐enhanced personalized syn‐MRI.
Bibliography:Funding information
National Institute of Biomedical Imaging and Bioengineering, Grant/Award Number: R21EB034184
ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
content type line 23
Funding information National Institute of Biomedical Imaging and Bioengineering, Grant/Award Number: R21EB034184
ISSN:0740-3194
1522-2594
1522-2594
DOI:10.1002/mrm.29527