Denoising very low-field magnetic resonance images using native noise modeling.

Frontiers in neuroimaging Pub Date : 2025-05-06 eCollection Date: 2025-01-01 DOI:10.3389/fnimg.2025.1501801
Tonny Ssentamu, Alvin Kimbowa, Ronald Omoding, Edgar Atamba, Pius K Mukwaya, George W Jjuuko, Sairam Geethanath
{"title":"Denoising very low-field magnetic resonance images using native noise modeling.","authors":"Tonny Ssentamu, Alvin Kimbowa, Ronald Omoding, Edgar Atamba, Pius K Mukwaya, George W Jjuuko, Sairam Geethanath","doi":"10.3389/fnimg.2025.1501801","DOIUrl":null,"url":null,"abstract":"<p><p>Low-field MRI is gaining interest, especially in low-resource settings, due to its low cost, portability, small footprint, and low power consumption. However, it suffers from significant noise, limiting its clinical utility. This study introduces native noise denoising (NND), which leverages the inherent noise characteristics of the acquired low-field data. By obtaining the noise characteristics from corner patches of low-field images, we iteratively added similar noise to high-field images to create a paired noisy-clean dataset. A U-Net based denoising autoencoder was trained on this dataset and evaluated on three low-field datasets: the M4Raw dataset (0.3T), <i>in vivo</i> brain MRI (0.05T), and phantom images (0.05T). The NND approach demonstrated improvements in signal-to-noise ratio (SNR) of 32.76%, 19.02%, and 8.16% across the M4Raw, <i>in vivo</i> and phantom datasets, respectively. Qualitative assessments, including difference maps, line intensity plots, and effective receptive fields, suggested that NND preserves structural details and edges compared to random noise denoising (RND), indicating potential enhancements in visual quality. This substantial improvement in low-field imaging quality addresses the fundamental challenge of diagnostic confidence in resource-constrained settings. By mitigating the primary technical limitation of these systems, our approach expands the clinical utility of low-field MRI scanners, potentially facilitating broader access to diagnostic imaging across resource-limited healthcare environments globally.</p>","PeriodicalId":73094,"journal":{"name":"Frontiers in neuroimaging","volume":"4 ","pages":"1501801"},"PeriodicalIF":0.0000,"publicationDate":"2025-05-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC12089061/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in neuroimaging","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/fnimg.2025.1501801","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2025/1/1 0:00:00","PubModel":"eCollection","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

Abstract

Low-field MRI is gaining interest, especially in low-resource settings, due to its low cost, portability, small footprint, and low power consumption. However, it suffers from significant noise, limiting its clinical utility. This study introduces native noise denoising (NND), which leverages the inherent noise characteristics of the acquired low-field data. By obtaining the noise characteristics from corner patches of low-field images, we iteratively added similar noise to high-field images to create a paired noisy-clean dataset. A U-Net based denoising autoencoder was trained on this dataset and evaluated on three low-field datasets: the M4Raw dataset (0.3T), in vivo brain MRI (0.05T), and phantom images (0.05T). The NND approach demonstrated improvements in signal-to-noise ratio (SNR) of 32.76%, 19.02%, and 8.16% across the M4Raw, in vivo and phantom datasets, respectively. Qualitative assessments, including difference maps, line intensity plots, and effective receptive fields, suggested that NND preserves structural details and edges compared to random noise denoising (RND), indicating potential enhancements in visual quality. This substantial improvement in low-field imaging quality addresses the fundamental challenge of diagnostic confidence in resource-constrained settings. By mitigating the primary technical limitation of these systems, our approach expands the clinical utility of low-field MRI scanners, potentially facilitating broader access to diagnostic imaging across resource-limited healthcare environments globally.

使用原生噪声建模去噪非常低场磁共振图像。
由于低成本、便携性、占地面积小和低功耗,低场MRI越来越受到人们的关注,特别是在低资源环境中。然而,它的噪声很大,限制了它的临床应用。本研究引入了原生噪声去噪(NND),它利用了所获取的低场数据的固有噪声特性。通过从低场图像的角块中获取噪声特征,迭代地将相似的噪声添加到高场图像中,以创建成对的去噪数据集。在此数据集上训练了一个基于U-Net的去噪自编码器,并在M4Raw数据集(0.3T)、活体脑MRI (0.05T)和幻影图像(0.05T)三个低场数据集上进行了评估。NND方法在M4Raw、体内和模拟数据集上的信噪比(SNR)分别提高了32.76%、19.02%和8.16%。定性评估,包括差异图、线强度图和有效接受野,表明与随机噪声去噪(RND)相比,NND保留了结构细节和边缘,表明视觉质量的潜在增强。低场成像质量的大幅提高解决了资源受限环境下诊断信心的基本挑战。通过减轻这些系统的主要技术限制,我们的方法扩展了低场MRI扫描仪的临床应用,有可能促进在全球资源有限的医疗环境中更广泛地获得诊断成像。
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 求助全文
来源期刊
自引率
0.00%
发文量
0
×
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
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
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 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信