Application of deep learning reconstruction in abdominal magnetic resonance cholangiopancreatography for image quality improvement and acquisition time reduction.

IF 2.6 3区 医学 Q1 MEDICINE, GENERAL & INTERNAL
Po-Ting Chen, Chen-Ya Yeh, Yu-Chien Chang, Pohua Chen, Chia-Wei Lee, Charng-Chyi Shieh, Chien-Yuan Lin, Kao-Lang Liu
{"title":"Application of deep learning reconstruction in abdominal magnetic resonance cholangiopancreatography for image quality improvement and acquisition time reduction.","authors":"Po-Ting Chen, Chen-Ya Yeh, Yu-Chien Chang, Pohua Chen, Chia-Wei Lee, Charng-Chyi Shieh, Chien-Yuan Lin, Kao-Lang Liu","doi":"10.1016/j.jfma.2024.10.017","DOIUrl":null,"url":null,"abstract":"<p><strong>Purpose: </strong>To compare deep learning (DL)-based and conventional reconstruction through subjective and objective analysis and ascertain whether DL-based reconstruction improves the quality and acquisition speed of clinical abdominal magnetic resonance imaging (MRI).</p><p><strong>Methods: </strong>The 124 patients who underwent abdominal MRI between January and July 2021 were retrospectively studied. For each patient, two-dimensional axial T<sub>2</sub>-weighted single-shot fast spin-echo MRI images with or without fat saturation were reconstructed using DL-based and conventional methods. The subjective image quality scores and objective metrics, including signal-to-noise ratios (SNRs) and contrast-to-noise ratios (CNRs) of the images were analysed. An explorative analysis was performed to compare 20 patients' MRI images with site routine settings, high-resolution settings and high-speed settings. Paired t tests and Wilcoxon signed-rank tests were used for subjective and objective comparisons.</p><p><strong>Results: </strong>A total of 144 patients were evaluated (mean age, 62.2 ± 14.1 years; 83 men). The MRI images reconstructed using DL-based methods had higher SNRs and CNRs than did those reconstructed using conventional methods (all p < 0.01). The subjective scores of the images reconstructed using DL-based methods were higher than those of the images reconstructed using conventional methods (p < 0.01), with significantly lower variation (p < 0.01). Exploratory analysis revealed that the DL-based reconstructions with thin slice thickness and higher temporal resolution had the highest image quality and were associated with the shortest scan times.</p><p><strong>Conclusions: </strong>DL-based reconstruction methods can be used to improve the quality with higher stability and accelerate the acquisition of abdominal MRI.</p>","PeriodicalId":17305,"journal":{"name":"Journal of the Formosan Medical Association","volume":" ","pages":""},"PeriodicalIF":2.6000,"publicationDate":"2024-10-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Journal of the Formosan Medical Association","FirstCategoryId":"3","ListUrlMain":"https://doi.org/10.1016/j.jfma.2024.10.017","RegionNum":3,"RegionCategory":"医学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"MEDICINE, GENERAL & INTERNAL","Score":null,"Total":0}
引用次数: 0

Abstract

Purpose: To compare deep learning (DL)-based and conventional reconstruction through subjective and objective analysis and ascertain whether DL-based reconstruction improves the quality and acquisition speed of clinical abdominal magnetic resonance imaging (MRI).

Methods: The 124 patients who underwent abdominal MRI between January and July 2021 were retrospectively studied. For each patient, two-dimensional axial T2-weighted single-shot fast spin-echo MRI images with or without fat saturation were reconstructed using DL-based and conventional methods. The subjective image quality scores and objective metrics, including signal-to-noise ratios (SNRs) and contrast-to-noise ratios (CNRs) of the images were analysed. An explorative analysis was performed to compare 20 patients' MRI images with site routine settings, high-resolution settings and high-speed settings. Paired t tests and Wilcoxon signed-rank tests were used for subjective and objective comparisons.

Results: A total of 144 patients were evaluated (mean age, 62.2 ± 14.1 years; 83 men). The MRI images reconstructed using DL-based methods had higher SNRs and CNRs than did those reconstructed using conventional methods (all p < 0.01). The subjective scores of the images reconstructed using DL-based methods were higher than those of the images reconstructed using conventional methods (p < 0.01), with significantly lower variation (p < 0.01). Exploratory analysis revealed that the DL-based reconstructions with thin slice thickness and higher temporal resolution had the highest image quality and were associated with the shortest scan times.

Conclusions: DL-based reconstruction methods can be used to improve the quality with higher stability and accelerate the acquisition of abdominal MRI.

在腹部磁共振胰胆管造影术中应用深度学习重建技术,以提高图像质量并缩短采集时间。
目的:通过主观和客观分析,比较基于深度学习(DL)的重建和传统重建,确定基于DL的重建是否能提高临床腹部磁共振成像(MRI)的质量和采集速度:对2021年1月至7月期间接受腹部磁共振成像的124名患者进行回顾性研究。采用基于 DL 的方法和传统方法对每位患者有无脂肪饱和的二维轴向 T2 加权单次快速自旋回波 MRI 图像进行重建。分析了主观图像质量评分和客观指标,包括图像的信噪比(SNR)和对比噪比(CNR)。对 20 名患者的磁共振成像进行了探索性分析,比较了现场常规设置、高分辨率设置和高速设置。主观和客观比较采用了配对 t 检验和 Wilcoxon 符号秩检验:共评估了 144 名患者(平均年龄为 62.2 ± 14.1 岁;83 名男性)。使用基于 DL 的方法重建的 MRI 图像比使用传统方法重建的图像具有更高的 SNR 和 CNR(均为 p):基于 DL 的重建方法能以更高的稳定性提高质量,并加快腹部 MRI 的采集。
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
6.50
自引率
6.20%
发文量
381
审稿时长
57 days
期刊介绍: Journal of the Formosan Medical Association (JFMA), published continuously since 1902, is an open access international general medical journal of the Formosan Medical Association based in Taipei, Taiwan. It is indexed in Current Contents/ Clinical Medicine, Medline, ciSearch, CAB Abstracts, Embase, SIIC Data Bases, Research Alert, BIOSIS, Biological Abstracts, Scopus and ScienceDirect. As a general medical journal, research related to clinical practice and research in all fields of medicine and related disciplines are considered for publication. Article types considered include perspectives, reviews, original papers, case reports, brief communications, correspondence and letters to the editor.
×
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