Physics-informed deep learning approach to quantification of human brain metabolites from magnetic resonance spectroscopy data

Simple item page
dc.contributor.authorShamaei, Amirmohammadcs
dc.contributor.authorStarčuková, Janacs
dc.contributor.authorStarčuk, Zenoncs
dc.coverage.issue1cs
dc.coverage.volume158cs
dc.date.issued2023-04-05cs
dc.description.abstractPurpose: While the recommended analysis method for magnetic resonance spectroscopy data is linear combination model (LCM) fitting, the supervised deep learning (DL) approach for quantification of MR spectroscopy (MRS) and MR spectroscopic imaging (MRSI) data recently showed encouraging results; however, supervised learning requires ground truth fitted spectra, which is not practical. Moreover, this work investigates the feasibility and efficiency of the LCM-based self-supervised DL method for the analysis of MRS data.Method: We present a novel DL-based method for the quantification of relative metabolite concentrations, using quantum-mechanics simulated metabolite responses and neural networks. We trained, validated, and evaluated the proposed networks with simulated and publicly accessible in-vivo human brain MRS data and compared the performance with traditional methods. A novel adaptive macromolecule fitting algorithm is included. We investigated the performance of the proposed methods in a Monte Carlo (MC) study. Result: The validation using low-SNR simulated data demonstrated that the proposed methods could perform quantification comparably to other methods. The applicability of the proposed method for the quantification of in-vivo MRS data was demonstrated. Our proposed networks have the potential to reduce computation time significantly.Conclusion: The proposed model-constrained deep neural networks trained in a self-supervised manner can offer fast and efficient quantification of MRS and MRSI data. Our proposed method has the potential to facilitate clinical practice by enabling faster processing of large datasets such as high-resolution MRSI datasets, which may have thousands of spectra.en
dc.formattextcs
dc.format.extent1-15cs
dc.format.mimetypeapplication/pdfcs
dc.identifier.citationCOMPUTERS IN BIOLOGY AND MEDICINE. 2023, vol. 158, issue 1, p. 1-15.en
dc.identifier.doi10.1016/j.compbiomed.2023.106837cs
dc.identifier.issn0010-4825cs
dc.identifier.other183318cs
dc.identifier.urihttp://hdl.handle.net/11012/213625
dc.language.isoencs
dc.publisherElseviercs
dc.relation.ispartofCOMPUTERS IN BIOLOGY AND MEDICINEcs
dc.relation.urihttps://www.sciencedirect.com/science/article/pii/S0010482523003025cs
dc.rightsCreative Commons Attribution 4.0 Internationalcs
dc.rights.accessopenAccesscs
dc.rights.sherpahttp://www.sherpa.ac.uk/romeo/issn/0010-4825/cs
dc.rights.urihttp://creativecommons.org/licenses/by/4.0/cs
dc.subjectMR spectroscopyen
dc.subjectInverse problemen
dc.subjectDeep learningen
dc.subjectMachine learningen
dc.subjectConvolutional neural networken
dc.subjectMetabolite quantificationen
dc.titlePhysics-informed deep learning approach to quantification of human brain metabolites from magnetic resonance spectroscopy dataen
dc.type.driverarticleen
dc.type.statusPeer-revieweden
dc.type.versionpublishedVersionen
sync.item.dbidVAV-183318en
sync.item.dbtypeVAVen
sync.item.insts2025.02.03 15:39:56en
sync.item.modts2025.01.17 17:33:18en
thesis.grantorVysoké učení technické v Brně. Fakulta elektrotechniky a komunikačních technologií. Ústav biomedicínského inženýrstvícs
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
1s2.0S0010482523003025main.pdf
Size:
8.18 MB
Format:
Adobe Portable Document Format
Description:
1s2.0S0010482523003025main.pdf
Download
Collections
Ústav biomedicínského inženýrství