Extraction of Individual Metabolite Spectrum in Proton Magnetic Resonance Spectroscopy of Mouse Brain Using Deep LearningExtraction of Individual Metabolite Spectrum in Proton Magnetic Resonance Spectroscopy of Mouse Brain Using Deep Learning
- Other Titles
- Extraction of Individual Metabolite Spectrum in Proton Magnetic Resonance Spectroscopy of Mouse Brain Using Deep Learning
- Authors
- Yoonho Hwang; Woo-Seung Kim; Chang-Soo Yun; Jae-Hyung Yeon; Hyeon-Man Baek; Bong Soo Han; Dong Youn Kim
- Issue Date
- Sep-2021
- Publisher
- 한국자기학회
- Keywords
- Proton magnetic resonance spectroscopy (1H-MRS); high magnetic field (9.4T); MR spectrum; metabolite quantification; deep learning; convolutional autoencoder
- Citation
- Journal of Magnetics, v.26, no.3, pp.356 - 362
- Journal Title
- Journal of Magnetics
- Volume
- 26
- Number
- 3
- Start Page
- 356
- End Page
- 362
- URI
- https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/82726
- DOI
- 10.4283/JMAG.2021.26.3.356
- ISSN
- 1226-1750
- Abstract
- The present study aims to develop a deep learning (DL) model to quantify metabolites. To apply DL to metabolite quantification using 1H-MRS data, Convolutional autoencoder (CAE) were designed to extract line‐narrowed, baseline‐removed, and noise-free metabolite spectra for each metabolite. Fifty thousand simulation data were generated by varying the SNR (4-12), linewidth (6-22 Hz), phase shift (± 5°), and frequency shift (± 5 Hz) on phantom spectra. The data were divided into 45,000 simulation data for training and 5,000 test data, and the mean absolute percent errors (MAPEs) were used to evaluate the performance of the CAE. The average MAPE of the metabolites was 13.64 ± 11.38 %. Fourteen metabolites were within the reported concentration ranges.
These findings showed that the proposed method had similar or improved performance than conventional methods. The proposed method using DL was the recent and up-to-date quantification one and has clinically potential applicability.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - 보건과학대학 > 의용생체공학과 > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/gachon/handle/2020.sw.gachon/82726)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.