Improved quantitative parameter estimation for prostate T2 relaxometry using convolutional neural networks.

IF 2 4区 医学 Q3 RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING
Patrick J Bolan, Sara L Saunders, Kendrick Kay, Mitchell Gross, Mehmet Akcakaya, Gregory J Metzger
{"title":"Improved quantitative parameter estimation for prostate T<sub>2</sub> relaxometry using convolutional neural networks.","authors":"Patrick J Bolan, Sara L Saunders, Kendrick Kay, Mitchell Gross, Mehmet Akcakaya, Gregory J Metzger","doi":"10.1007/s10334-024-01186-3","DOIUrl":null,"url":null,"abstract":"<p><strong>Objective: </strong>Quantitative parameter mapping conventionally relies on curve fitting techniques to estimate parameters from magnetic resonance image series. This study compares conventional curve fitting techniques to methods using neural networks (NN) for measuring T<sub>2</sub> in the prostate.</p><p><strong>Materials and methods: </strong>Large physics-based synthetic datasets simulating T<sub>2</sub> mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Four combinations of different NN architectures and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness.</p><p><strong>Results: </strong>In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst the methods. On in vivo data, this best performing method produced low-noise T<sub>2</sub> maps and showed the least deterioration with increasing input noise levels.</p><p><strong>Discussion: </strong>This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T<sub>2</sub> estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.</p>","PeriodicalId":18067,"journal":{"name":"Magnetic Resonance Materials in Physics, Biology and Medicine","volume":" ","pages":"721-735"},"PeriodicalIF":2.0000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11417079/pdf/","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Magnetic Resonance Materials in Physics, Biology and Medicine","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1007/s10334-024-01186-3","RegionNum":4,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/7/23 0:00:00","PubModel":"Epub","JCR":"Q3","JCRName":"RADIOLOGY, NUCLEAR MEDICINE & MEDICAL IMAGING","Score":null,"Total":0}
引用次数: 0

Abstract

Objective: Quantitative parameter mapping conventionally relies on curve fitting techniques to estimate parameters from magnetic resonance image series. This study compares conventional curve fitting techniques to methods using neural networks (NN) for measuring T2 in the prostate.

Materials and methods: Large physics-based synthetic datasets simulating T2 mapping acquisitions were generated for training NNs and for quantitative performance comparisons. Four combinations of different NN architectures and training corpora were implemented and compared with four different curve fitting strategies. All methods were compared quantitatively using synthetic data with known ground truth, and further compared on in vivo test data, with and without noise augmentation, to evaluate feasibility and noise robustness.

Results: In the evaluation on synthetic data, a convolutional neural network (CNN), trained in a supervised fashion using synthetic data generated from naturalistic images, showed the highest overall accuracy and precision amongst the methods. On in vivo data, this best performing method produced low-noise T2 maps and showed the least deterioration with increasing input noise levels.

Discussion: This study showed that a CNN, trained with synthetic data in a supervised manner, may provide superior T2 estimation performance compared to conventional curve fitting, especially in low signal-to-noise regions.

Abstract Image

利用卷积神经网络改进前列腺 T2 弛豫测量的定量参数估计。
目的:定量参数绘图传统上依靠曲线拟合技术从磁共振图像序列中估算参数。本研究将传统的曲线拟合技术与使用神经网络(NN)测量前列腺 T2 的方法进行了比较:为训练神经网络和进行定量性能比较,生成了模拟 T2 映射采集的大型物理合成数据集。采用了四种不同的 NN 架构和训练数据集组合,并与四种不同的曲线拟合策略进行了比较。所有方法都使用已知地面实况的合成数据进行了定量比较,并在体内测试数据上进行了进一步比较,包括有噪声增强和无噪声增强,以评估可行性和噪声鲁棒性:在对合成数据的评估中,使用自然图像生成的合成数据以监督方式训练的卷积神经网络(CNN)在各种方法中显示出最高的总体准确度和精确度。在活体数据上,这种性能最佳的方法能生成低噪声 T2 图,而且随着输入噪声水平的增加,其恶化程度最小:本研究表明,与传统的曲线拟合相比,使用合成数据以监督方式训练的 CNN 可提供更优越的 T2 估算性能,尤其是在低信噪比区域。
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
CiteScore
4.60
自引率
0.00%
发文量
58
审稿时长
>12 weeks
期刊介绍: MAGMA is a multidisciplinary international journal devoted to the publication of articles on all aspects of magnetic resonance techniques and their applications in medicine and biology. MAGMA currently publishes research papers, reviews, letters to the editor, and commentaries, six times a year. The subject areas covered by MAGMA include: advances in materials, hardware and software in magnetic resonance technology, new developments and results in research and practical applications of magnetic resonance imaging and spectroscopy related to biology and medicine, study of animal models and intact cells using magnetic resonance, reports of clinical trials on humans and clinical validation of magnetic resonance protocols.
×
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