Artificial intelligence-powered four-fold upscaling of human brain synthetic metabolite maps

Objective Compared with anatomical magnetic resonance imaging modalities, metabolite images from magnetic resonance spectroscopic imaging often suffer from low quality and detail due to their larger voxel sizes. Conventional interpolation techniques aim to enhance these low-resolution images; howeve...

Full description

Saved in:
Bibliographic Details
Main Authors: Erin B Bjørkeli, Jonn T Geitung, Morteza Esmaeili
Format: Article
Language:English
Published: SAGE Publishing 2025-04-01
Series:Journal of International Medical Research
Online Access:https://doi.org/10.1177/03000605251330578
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1849325068950175744
author Erin B Bjørkeli
Jonn T Geitung
Morteza Esmaeili
author_facet Erin B Bjørkeli
Jonn T Geitung
Morteza Esmaeili
author_sort Erin B Bjørkeli
collection DOAJ
description Objective Compared with anatomical magnetic resonance imaging modalities, metabolite images from magnetic resonance spectroscopic imaging often suffer from low quality and detail due to their larger voxel sizes. Conventional interpolation techniques aim to enhance these low-resolution images; however, they frequently struggle with issues such as edge preservation, blurring, and input quality limitations. This study explores an artificial intelligence–driven approach to improve the quality of synthetically generated metabolite maps. Methods Using an open-access database of 450 participants, we trained and tested a model on 350 participants, evaluating its performance against spline and nearest-neighbor interpolation methods. Metrics such as structural similarity index, peak signal-to-noise ratio, and learned perceptual image patch similarity were used for comparison. Results Our model not only increased spatial resolution but also preserved critical image details, outperforming traditional interpolation methods in both image fidelity and edge preservation. Conclusions This artificial intelligence–powered super-resolution technique could substantially enhance magnetic resonance spectroscopic imaging quality, aiding in more accurate neurological assessments.
format Article
id doaj-art-cc9e45bfd4194263b7e3cc2ee9a56faf
institution Kabale University
issn 1473-2300
language English
publishDate 2025-04-01
publisher SAGE Publishing
record_format Article
series Journal of International Medical Research
spelling doaj-art-cc9e45bfd4194263b7e3cc2ee9a56faf2025-08-20T03:48:31ZengSAGE PublishingJournal of International Medical Research1473-23002025-04-015310.1177/03000605251330578Artificial intelligence-powered four-fold upscaling of human brain synthetic metabolite mapsErin B BjørkeliJonn T GeitungMorteza EsmaeiliObjective Compared with anatomical magnetic resonance imaging modalities, metabolite images from magnetic resonance spectroscopic imaging often suffer from low quality and detail due to their larger voxel sizes. Conventional interpolation techniques aim to enhance these low-resolution images; however, they frequently struggle with issues such as edge preservation, blurring, and input quality limitations. This study explores an artificial intelligence–driven approach to improve the quality of synthetically generated metabolite maps. Methods Using an open-access database of 450 participants, we trained and tested a model on 350 participants, evaluating its performance against spline and nearest-neighbor interpolation methods. Metrics such as structural similarity index, peak signal-to-noise ratio, and learned perceptual image patch similarity were used for comparison. Results Our model not only increased spatial resolution but also preserved critical image details, outperforming traditional interpolation methods in both image fidelity and edge preservation. Conclusions This artificial intelligence–powered super-resolution technique could substantially enhance magnetic resonance spectroscopic imaging quality, aiding in more accurate neurological assessments.https://doi.org/10.1177/03000605251330578
spellingShingle Erin B Bjørkeli
Jonn T Geitung
Morteza Esmaeili
Artificial intelligence-powered four-fold upscaling of human brain synthetic metabolite maps
Journal of International Medical Research
title Artificial intelligence-powered four-fold upscaling of human brain synthetic metabolite maps
title_full Artificial intelligence-powered four-fold upscaling of human brain synthetic metabolite maps
title_fullStr Artificial intelligence-powered four-fold upscaling of human brain synthetic metabolite maps
title_full_unstemmed Artificial intelligence-powered four-fold upscaling of human brain synthetic metabolite maps
title_short Artificial intelligence-powered four-fold upscaling of human brain synthetic metabolite maps
title_sort artificial intelligence powered four fold upscaling of human brain synthetic metabolite maps
url https://doi.org/10.1177/03000605251330578
work_keys_str_mv AT erinbbjørkeli artificialintelligencepoweredfourfoldupscalingofhumanbrainsyntheticmetabolitemaps
AT jonntgeitung artificialintelligencepoweredfourfoldupscalingofhumanbrainsyntheticmetabolitemaps
AT mortezaesmaeili artificialintelligencepoweredfourfoldupscalingofhumanbrainsyntheticmetabolitemaps