Using Deep Learning to Simultaneously Reduce Noise and Motion Artifacts in Brain MR Imaging.

Isao Muro, Tetsuro Isoiwa, Shuhei Shibukawa, Keisuke Usui, Yuhei Otsuka
{"title":"Using Deep Learning to Simultaneously Reduce Noise and Motion Artifacts in Brain MR Imaging.","authors":"Isao Muro, Tetsuro Isoiwa, Shuhei Shibukawa, Keisuke Usui, Yuhei Otsuka","doi":"10.2463/mrms.mp.2024-0098","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>To reduce motion artifacts (MA) and noise in brain MRI using deep learning to promote clinical utility.</p><p><strong>Methods: </strong>T1-weighted (T1W), T2-weighted (T2W), and fluid attenuated inversion recovery (FLAIR) images of the brain (including sagittal, coronal, and axial sections) of 20 healthy volunteers were collected using a 3.0T MR system. Simulated images with horizontal and vertical phase directions exhibiting varying white noise and MA (n = 115200) were created for each sequence and trained in deep learning (36000 pairs), validation (200 pairs), and testing (200 pairs, 2000 pairs) datasets. Images with MA and noise and images without MA and noise were included. A training model was constructed to remove noise and MA. The model's ability to remove noise and MA was evaluated by the structural similarity index (SSIM) and peek signal to noise ratio (PSNR). The SSIM and PSNR between the ground-truth and output images were calculated (SSIMout, PSNRout), and the SSIM and PSNR between the ground-truth and input images were calculated (SSIMinp, PSNRinp). The ratio of SSIMinp to SSIMout was then evaluated as the improvement ratio of SSIM (IMPRs) and the ratio of PSNRinp to PSNRout as the improvement ratio of PSNR (IMPRp). In addition, 10 radio technologists performed visual evaluation.</p><p><strong>Results: </strong>The SSIMout were >0.95 and 33 dB, respectively, for T1W, T2W, and FLAIR images with different contrasts. The mean value of SSIMinp was 0.72. Noise and MA removal effects were observed in images, with an average value of 72 dB. Visual evaluation revealed that the reduction effect in the output image was higher than that observed in the input image.</p><p><strong>Conclusion: </strong>The method proposed herein, which uses separate training models for the T1W, T2W, and FLAIR sequences, is a valuable approach for removing MA and noise, independent of the imaging direction and artifact orientation. An improvement in image quality was achieved by generating a large amount of training data through simulation.</p>","PeriodicalId":94126,"journal":{"name":"Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine","volume":" ","pages":""},"PeriodicalIF":0.0000,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.2463/mrms.mp.2024-0098","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: To reduce motion artifacts (MA) and noise in brain MRI using deep learning to promote clinical utility.

Methods: T1-weighted (T1W), T2-weighted (T2W), and fluid attenuated inversion recovery (FLAIR) images of the brain (including sagittal, coronal, and axial sections) of 20 healthy volunteers were collected using a 3.0T MR system. Simulated images with horizontal and vertical phase directions exhibiting varying white noise and MA (n = 115200) were created for each sequence and trained in deep learning (36000 pairs), validation (200 pairs), and testing (200 pairs, 2000 pairs) datasets. Images with MA and noise and images without MA and noise were included. A training model was constructed to remove noise and MA. The model's ability to remove noise and MA was evaluated by the structural similarity index (SSIM) and peek signal to noise ratio (PSNR). The SSIM and PSNR between the ground-truth and output images were calculated (SSIMout, PSNRout), and the SSIM and PSNR between the ground-truth and input images were calculated (SSIMinp, PSNRinp). The ratio of SSIMinp to SSIMout was then evaluated as the improvement ratio of SSIM (IMPRs) and the ratio of PSNRinp to PSNRout as the improvement ratio of PSNR (IMPRp). In addition, 10 radio technologists performed visual evaluation.

Results: The SSIMout were >0.95 and 33 dB, respectively, for T1W, T2W, and FLAIR images with different contrasts. The mean value of SSIMinp was 0.72. Noise and MA removal effects were observed in images, with an average value of 72 dB. Visual evaluation revealed that the reduction effect in the output image was higher than that observed in the input image.

Conclusion: The method proposed herein, which uses separate training models for the T1W, T2W, and FLAIR sequences, is a valuable approach for removing MA and noise, independent of the imaging direction and artifact orientation. An improvement in image quality was achieved by generating a large amount of training data through simulation.

查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
利用深度学习同时减少脑磁共振成像中的噪声和运动伪影
本文章由计算机程序翻译,如有差异,请以英文原文为准。
求助全文
约1分钟内获得全文 去求助
来源期刊
自引率
0.00%
发文量
0
期刊最新文献
Using Deep Learning to Simultaneously Reduce Noise and Motion Artifacts in Brain MR Imaging. Breast Diffusion-weighted MR Imaging: Current Applications, Insights from Screening, and Future Directions. Institutional Variability in Ultrafast Breast MR Imaging: Comparing Compressed Sensing and View Sharing Techniques with Different Patient Populations and Contrast Injection Protocols. MR Imaging Indices for Brain Interstitial Fluid Dynamics and the Effects of Orexin Antagonists on Sleep. Toward Clinical Implementation of Magnetic Resonance Imaging for Placental Function.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1