Deep attention super-resolution of brain magnetic resonance images acquired under clinical protocols

Deep attention super-resolution of brain magnetic resonance images acquired under clinical protocols

Vast quantities of Magnetic Resonance Images (MRI) are routinely acquired in clinical practice but, to speed up acquisition, these scans are typically of a quality that is sufficient for clinical diagnosis but sub-optimal for large-scale precision medicine, computational diagnostics, and large-scale...

Full description

Saved in:
Bibliographic Details
Published in:Frontiers in computational neuroscience Vol. 16; p. 887633
Main Authors: Li, Bryan M., Castorina, Leonardo V., Valdés Hernández, Maria del C., Clancy, Una, Wiseman, Stewart J., Sakka, Eleni, Storkey, Amos J., Jaime Garcia, Daniela, Cheng, Yajun, Doubal, Fergus, Thrippleton, Michael T., Stringer, Michael, Wardlaw, Joanna M.
Format: Journal Article
Language:English
Published: Lausanne Frontiers Research Foundation 25-08-2022
Frontiers Media S.A
Subjects:
Algorithms
Attention
Automation
brain imaging
Brain research
Clinical medicine
Computational neuroscience
Datasets
Deep learning
explainable artificial intelligence
image reconstruction
Magnetic Resonance Imaging
Methods
Neural networks
Neuroimaging
Neuroscience
Precision medicine
Segmentation
Substantia alba
super-resolution
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Vast quantities of Magnetic Resonance Images (MRI) are routinely acquired in clinical practice but, to speed up acquisition, these scans are typically of a quality that is sufficient for clinical diagnosis but sub-optimal for large-scale precision medicine, computational diagnostics, and large-scale neuroimaging collaborative research. Here, we present a critic-guided framework to upsample low-resolution (often 2D) MRI full scans to help overcome these limitations. We incorporate feature-importance and self-attention methods into our model to improve the interpretability of this study. We evaluate our framework on paired low- and high-resolution brain MRI structural full scans (i.e., T1-, T2-weighted, and FLAIR sequences are simultaneously input) obtained in clinical and research settings from scanners manufactured by Siemens, Phillips, and GE. We show that the upsampled MRIs are qualitatively faithful to the ground-truth high-quality scans ( PSNR = 35.39; MAE = 3.78 E −3; NMSE = 4.32 E −10; SSIM = 0.9852; mean normal-appearing gray/white matter ratio intensity differences ranging from 0.0363 to 0.0784 for FLAIR, from 0.0010 to 0.0138 for T1-weighted and from 0.0156 to 0.074 for T2-weighted sequences). The automatic raw segmentation of tissues and lesions using the super-resolved images has fewer false positives and higher accuracy than those obtained from interpolated images in protocols represented with more than three sets in the training sample, making our approach a strong candidate for practical application in clinical and collaborative research.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 23
Edited by: Guang Yang, Imperial College London, United Kingdom
Reviewed by: Xujiong Ye, University of Lincoln, United Kingdom; Victor Gonzalez Castro, Universidad de León, Spain
ISSN:1662-5188
1662-5188
DOI:10.3389/fncom.2022.887633