• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>journal of magnetics >Extraction of Individual Metabolite Spectrum in Proton Magnetic Resonance Spectroscopy of Mouse Brain Using Deep Learning
【24h】

Extraction of Individual Metabolite Spectrum in Proton Magnetic Resonance Spectroscopy of Mouse Brain Using Deep Learning

机译：基于深度学习的小鼠大脑质子磁共振波谱提取单个代谢物谱

获取原文
获取原文并翻译 | 示例
           
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The present study aims to develop a deep learning (DL) model to quantify metabolites. To apply DL to metabolite quantification using H-1-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 degrees), 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 fmdings 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.
机译：本研究旨在开发一种深度学习 （DL） 模型来量化代谢物。为了使用 H-1-MRS 数据将 DL 应用于代谢物定量，设计了卷积自动编码器 （CAE） 来提取每种代谢物的线窄、基线去除和无噪声的代谢物谱图。通过改变幻象光谱上的SNR（4-12）、线宽（6-22 Hz）、相移（+/- 5度）和频移（+/- 5 Hz）生成了5万个仿真数据。将数据分为45,000个用于训练的仿真数据和5,000个测试数据，并使用平均绝对百分比误差（MAPE）来评估CAE的性能。代谢物的平均MAPE为13.64 +/- 11.38 %。14种代谢物在报告的浓度范围内。这些结果表明，所提方法与传统方法具有相似或更高的性能。使用DL的拟议方法是最新和最新的定量方法，具有临床上的潜在适用性。

著录项

相似文献

  • 外文文献
  • 中文文献
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号