Water scaling strategy for metabolites quantified in MRS by deep learning | Publication

Title	Water scaling strategy for metabolites quantified in MRS by deep learning
Creator	蔡尚岳 Tsai, Shang-Yueh Huang, Yu-Long;Lin, Yi-Ru;Huang, Teng-Yi;Ko, Cheng-Wen
Contributor	應物所
Date	2020-08
Date Issued	29-Jul-2022 15:46:46 (UTC+8)
Summary	Recently, it has been shown that MRS can be analyzed by a convolutional neural network (CNN) with concentrations quantified in a relative way. Here, we propose to scale in vivo MRS data according to water signal in simulated spectra and in vivo data so that CNN spectra can be scaled to institutional units for possible between subject comparison. Our results show that the quantified metabolites are at the same level as those quantified using LCModel with water scaling method but with less repeatability. A further phantom study is necessary to validate the proposed method.
Relation	2020 Proceedings of International Society for Magnetic Resonance in Medicine, International Society for Magnetic Resonance in Medicine, pp.2844
Type	conference

dc.contributor	應物所
dc.creator (作者)	蔡尚岳
dc.creator (作者)	Tsai, Shang-Yueh
dc.creator (作者)	Huang, Yu-Long;Lin, Yi-Ru;Huang, Teng-Yi;Ko, Cheng-Wen
dc.date (日期)	2020-08
dc.date.accessioned	29-Jul-2022 15:46:46 (UTC+8)	-
dc.date.available	29-Jul-2022 15:46:46 (UTC+8)	-
dc.date.issued (上傳時間)	29-Jul-2022 15:46:46 (UTC+8)	-
dc.identifier.uri (URI)	http://nccur.lib.nccu.edu.tw/handle/140.119/140953	-
dc.description.abstract (摘要)	Recently, it has been shown that MRS can be analyzed by a convolutional neural network (CNN) with concentrations quantified in a relative way. Here, we propose to scale in vivo MRS data according to water signal in simulated spectra and in vivo data so that CNN spectra can be scaled to institutional units for possible between subject comparison. Our results show that the quantified metabolites are at the same level as those quantified using LCModel with water scaling method but with less repeatability. A further phantom study is necessary to validate the proposed method.
dc.format.extent	104 bytes	-
dc.format.mimetype	text/html	-
dc.relation (關聯)	2020 Proceedings of International Society for Magnetic Resonance in Medicine, International Society for Magnetic Resonance in Medicine, pp.2844
dc.title (題名)	Water scaling strategy for metabolites quantified in MRS by deep learning
dc.type (資料類型)	conference