Spectro-ViT: A vision transformer model for GABA-edited MEGA-PRESS reconstruction using spectrograms.

Autor: Dias G; School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil. Electronic address: g172441@dac.unicamp.br., Berto RP; Department of Biomedical Engineering, University of Calgary, Calgary, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary, Canada; Alberta Children's Hospital Research Institute, Calgary, Canada., Oliveira M; School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil., Ueda L; School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil; Research and Development Center in Telecommunications, CPQD, Campinas, Brazil., Dertkigil S; School of Medical Sciences, University of Campinas, Campinas, Brazil., Costa PDP; School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil; Artificial Intelligence Lab., Recod.ai, University of Campinas, Campinas, Brazil., Shamaei A; Hotchkiss Brain Institute, University of Calgary, Calgary, Canada; Department of Electrical and Software Engineering, University of Calgary, Calgary, Canada., Bugler H; Department of Biomedical Engineering, University of Calgary, Calgary, Canada; Hotchkiss Brain Institute, University of Calgary, Calgary, Canada; Alberta Children's Hospital Research Institute, Calgary, Canada., Souza R; Hotchkiss Brain Institute, University of Calgary, Calgary, Canada; Department of Electrical and Software Engineering, University of Calgary, Calgary, Canada., Harris A; Hotchkiss Brain Institute, University of Calgary, Calgary, Canada; Alberta Children's Hospital Research Institute, Calgary, Canada; Department of Radiology, University of Calgary, Calgary, Canada., Rittner L; School of Electrical and Computer Engineering, University of Campinas, Campinas, Brazil.
Jazyk: angličtina
Zdroj: Magnetic resonance imaging [Magn Reson Imaging] 2024 Nov; Vol. 113, pp. 110219. Date of Electronic Publication: 2024 Jul 26.
DOI: 10.1016/j.mri.2024.110219
Abstrakt: This study investigated the use of a Vision Transformer (ViT) for reconstructing GABA-edited Magnetic Resonance Spectroscopy (MRS) data from a reduced number of transients. Transients refer to the samples collected during an MRS acquisition by repeating the experiment to generate a signal of sufficient quality. Specifically, 80 transients were used instead of the typical 320 transients, aiming to reduce scan time. The 80 transients were pre-processed and converted into a spectrogram image representation using the Short-Time Fourier Transform (STFT). A pre-trained ViT, named Spectro-ViT, was fine-tuned and then tested using in-vivo GABA-edited MEGA-PRESS data. Its performance was compared against other pipelines in the literature using quantitative quality metrics and estimated metabolite concentration values, with the typical 320-transient scans serving as the reference for comparison. The Spectro-ViT model exhibited the best overall quality metrics among all other pipelines against which it was compared. The metabolite concentrations from Spectro-ViT's reconstructions for GABA+ achieved the best average R 2 value of 0.67 and the best average Mean Absolute Percentage Error (MAPE) value of 9.68%, with no significant statistical differences found compared to the 320-transient reference. The code to reproduce this research is available at https://github.com/MICLab-Unicamp/Spectro-ViT.
Competing Interests: Declaration of competing interest None.
(Copyright © 2024 The Author(s). Published by Elsevier Inc. All rights reserved.)
Databáze: MEDLINE
Externí odkaz: