• 文献检索
  • 文档翻译
  • 深度研究
  • 学术资讯
  • Suppr Zotero 插件Zotero 插件
  • 邀请有礼
  • 套餐&价格
  • 历史记录
应用&插件
Suppr Zotero 插件Zotero 插件浏览器插件Mac 客户端Windows 客户端微信小程序
定价
高级版会员购买积分包购买API积分包
服务
文献检索文档翻译深度研究API 文档MCP 服务
关于我们
关于 Suppr公司介绍联系我们用户协议隐私条款
关注我们

Suppr 超能文献

核心技术专利:CN118964589B侵权必究
粤ICP备2023148730 号-1Suppr @ 2026

文献检索

告别复杂PubMed语法,用中文像聊天一样搜索,搜遍4000万医学文献。AI智能推荐,让科研检索更轻松。

立即免费搜索

文件翻译

保留排版,准确专业,支持PDF/Word/PPT等文件格式,支持 12+语言互译。

免费翻译文档

深度研究

AI帮你快速写综述,25分钟生成高质量综述,智能提取关键信息,辅助科研写作。

立即免费体验

颞下颌关节磁共振成像的深度学习重建:诊断互换性、图像质量及扫描时间缩短

Deep learning reconstruction for temporomandibular joint MRI: diagnostic interchangeability, image quality, and scan time reduction.

作者信息

Jo Gyu-Dong, Jeon Kug Jin, Choi Yoon Joo, Lee Chena, Han Sang-Sun

机构信息

Department of Oral and Maxillofacial Radiology, College of Dentistry, Yonsei University, Seoul, Republic of Korea.

Oral Science Research Center, College of Dentistry, Yonsei University, Seoul, Republic of Korea.

出版信息

Eur Radiol. 2025 Sep 25. doi: 10.1007/s00330-025-12029-7.

DOI:10.1007/s00330-025-12029-7
PMID:40996510
Abstract

OBJECTIVES

To evaluate the diagnostic interchangeability, image quality, and scan time of deep learning (DL)-reconstructed magnetic resonance imaging (MRI) compared with conventional MRI for the temporomandibular joint (TMJ).

MATERIALS AND METHODS

Patients with suspected TMJ disorder underwent sagittal proton density-weighted (PDW) and T2-weighted fat-suppressed (T2W FS) MRI using both conventional and DL reconstruction protocols in a single session. Three oral radiologists independently assessed disc shape, disc position, and joint effusion. Diagnostic interchangeability for these findings was evaluated by comparing interobserver agreement, with equivalence defined as a 95% confidence interval (CI) within ±5%. Qualitative image quality (sharpness, noise, artifacts, overall) was rated on a 5-point scale. Quantitative image quality was assessed by measuring the signal-to-noise ratio (SNR) and contrast-to-noise ratio (CNR) in the condyle, disc, and background air. Image quality scores were compared using the Wilcoxon signed-rank test, and SNR/CNR using paired t-tests. Scan times were directly compared.

RESULTS

A total of 176 TMJs from 88 patients (mean age, 37 ± 16 years; 43 men) were analyzed. DL-reconstructed MRI demonstrated diagnostic equivalence to conventional MRI for disc shape, position, and effusion (equivalence indices < 3%; 95% CIs within ±5%). DL reconstruction significantly reduced noise in PDW and T2W FS sequences (p < 0.05) while maintaining sharpness and artifact levels. SNR and CNR were significantly improved (p < 0.05), except for disc SNR in PDW (p = 0.189). Scan time was reduced by 49.2%.

CONCLUSION

DL-reconstructed TMJ MRI is diagnostically interchangeable with conventional MRI, offering improved image quality with a shorter scan time.

KEY POINTS

Question Long MRI scan times in patients with temporomandibular disorders can increase pain and motion-related artifacts, often compromising image quality in diagnostic settings. Findings DL reconstruction is diagnostically interchangeable with conventional MRI for assessing disc shape, disc position, and effusion, while improving image quality and reducing scan time. Clinical relevance DL reconstruction enables faster and more tolerable TMJ MRI workflows without compromising diagnostic accuracy, facilitating broader adoption in clinical settings where long scan times and motion artifacts often limit diagnostic efficiency.

摘要

目的

评估深度学习(DL)重建的磁共振成像(MRI)与传统MRI在颞下颌关节(TMJ)成像中的诊断互换性、图像质量和扫描时间。

材料与方法

疑似颞下颌关节紊乱的患者在同一次检查中分别采用传统和DL重建协议进行矢状面质子密度加权(PDW)和T2加权脂肪抑制(T2W FS)MRI检查。三名口腔放射科医生独立评估盘状形态、盘状位置和关节积液情况。通过比较观察者间的一致性来评估这些发现的诊断互换性,一致性定义为95%置信区间(CI)在±5%以内。定性图像质量(清晰度、噪声、伪影、总体)采用5分制进行评分。通过测量髁突、关节盘和背景空气的信噪比(SNR)和对比噪声比(CNR)来评估定量图像质量。图像质量得分采用Wilcoxon符号秩检验进行比较,SNR/CNR采用配对t检验进行比较。直接比较扫描时间。

结果

共分析了88例患者(平均年龄37±16岁;43名男性)的176个颞下颌关节。DL重建的MRI在盘状形态、位置和积液方面显示出与传统MRI诊断等效(等效指数<3%;95%CI在±5%以内)。DL重建在保持清晰度和伪影水平的同时,显著降低了PDW和T2W FS序列中的噪声(p<0.05)。SNR和CNR显著提高(p<0.05),PDW序列中关节盘SNR除外(p = 0.189)。扫描时间减少了49.2%。

结论

DL重建的颞下颌关节MRI在诊断上可与传统MRI互换,图像质量更高且扫描时间更短。

关键点

问题 颞下颌关节紊乱患者长时间的MRI扫描会增加疼痛和与运动相关的伪影,常影响诊断时的图像质量。发现 DL重建在评估盘状形态、盘状位置和积液方面与传统MRI诊断等效,同时提高了图像质量并缩短了扫描时间。临床意义 DL重建能够实现更快且更易耐受的颞下颌关节MRI检查流程,而不影响诊断准确性,便于在长时间扫描和运动伪影常限制诊断效率的临床环境中更广泛地应用。

相似文献

1
Deep learning reconstruction for temporomandibular joint MRI: diagnostic interchangeability, image quality, and scan time reduction.颞下颌关节磁共振成像的深度学习重建:诊断互换性、图像质量及扫描时间缩短
Eur Radiol. 2025 Sep 25. doi: 10.1007/s00330-025-12029-7.
2
Deep learning-based denoising image reconstruction of body magnetic resonance imaging in children.基于深度学习的儿童身体磁共振成像去噪图像重建
Pediatr Radiol. 2025 May;55(6):1235-1244. doi: 10.1007/s00247-025-06230-5. Epub 2025 Apr 5.
3
Evaluation of deep learning reconstruction in accelerated knee MRI: comparison of visual and diagnostic performance metrics.加速膝关节磁共振成像中深度学习重建的评估:视觉与诊断性能指标的比较
Radiologie (Heidelb). 2025 Jun 23. doi: 10.1007/s00117-025-01464-8.
4
Dual-Network Deep Learning for Accelerated Head and Neck MRI: Enhanced Image Quality and Reduced Scan Time.用于加速头颈磁共振成像的双网络深度学习:提高图像质量并缩短扫描时间。
Head Neck. 2025 Jul 22. doi: 10.1002/hed.28255.
5
Accelerated single-shot T2-weighted fat-suppressed (FS) MRI of the liver with deep learning-based image reconstruction: qualitative and quantitative comparison of image quality with conventional T2-weighted FS sequence.基于深度学习的图像重建的肝脏加速单次激发 T2 加权脂肪抑制(FS)MRI:与常规 T2 加权 FS 序列的图像质量的定性和定量比较。
Eur Radiol. 2021 Nov;31(11):8447-8457. doi: 10.1007/s00330-021-08008-3. Epub 2021 May 7.
6
Accelerated MRI in temporomandibular joints using AI-assisted compressed sensing technique: a feasibility study.使用人工智能辅助压缩感知技术的颞下颌关节快速磁共振成像:一项可行性研究。
Eur Radiol. 2025 Jun 12. doi: 10.1007/s00330-025-11734-7.
7
Application of deep learning-based image reconstruction in MR imaging of the shoulder joint to improve image quality and reduce scan time.基于深度学习的图像重建在肩关节磁共振成像中的应用,以提高图像质量并减少扫描时间。
Eur Radiol. 2023 Mar;33(3):1513-1525. doi: 10.1007/s00330-022-09151-1. Epub 2022 Sep 27.
8
Optimizing hip MRI: enhancing image quality and elevating inter-observer consistency using deep learning-powered reconstruction.优化髋关节磁共振成像:利用深度学习驱动的重建技术提高图像质量并提升观察者间的一致性
BMC Med Imaging. 2025 Jan 13;25(1):17. doi: 10.1186/s12880-025-01554-y.
9
Deep Learning Reconstruction of Diffusion-weighted MRI Enables Shorter Examination Times While Maintaining Image Quality in Head and Neck Imaging.
Clin Neuroradiol. 2026 Jan 7. doi: 10.1007/s00062-025-01604-6.
10
Diagnostic interchangeability of deep-learning based Synth-STIR images generated from T1 and T2 weighted spine images.基于深度学习从T1加权和T2加权脊柱图像生成的Synth-STIR图像的诊断互换性。
Eur Radiol. 2025 Jul 18. doi: 10.1007/s00330-025-11827-3.

本文引用的文献

1
An automatic tracking method to measure the mandibula movement during real time MRI.一种实时 MRI 下测量下颌运动的自动跟踪方法。
Sci Rep. 2024 Oct 15;14(1):24125. doi: 10.1038/s41598-024-74285-9.
2
Comparative analysis of image quality and interchangeability between standard and deep learning-reconstructed T2-weighted spine MRI.标准和深度学习重建 T2 加权脊柱 MRI 之间的图像质量和可互换性的比较分析。
Magn Reson Imaging. 2024 Jun;109:211-220. doi: 10.1016/j.mri.2024.03.022. Epub 2024 Mar 19.
3
Reconstruction of shoulder MRI using deep learning and compressed sensing: a validation study on healthy volunteers.
深度学习和压缩感知在肩部 MRI 重建中的应用:一项对健康志愿者的验证研究。
Eur Radiol Exp. 2023 Oct 26;7(1):66. doi: 10.1186/s41747-023-00377-2.
4
Deep learning-based reconstruction for acceleration of lumbar spine MRI: a prospective comparison with standard MRI.基于深度学习的加速腰椎磁共振成像重建:与标准磁共振成像的前瞻性比较。
Eur Radiol. 2023 Dec;33(12):8656-8668. doi: 10.1007/s00330-023-09918-0. Epub 2023 Jul 27.
5
Reconstructed magnetic resonance image-based effusion volume assessment for temporomandibular joint arthralgia.基于磁共振图像重建的颞下颌关节疼痛性积液量评估
J Oral Rehabil. 2023 Nov;50(11):1202-1210. doi: 10.1111/joor.13551. Epub 2023 Aug 2.
6
Clinical Impact of Deep Learning Reconstruction in MRI.深度学习重建在 MRI 中的临床影响。
Radiographics. 2023 Jun;43(6):e220133. doi: 10.1148/rg.220133.
7
Artificial Intelligence-Driven Ultra-Fast Superresolution MRI: 10-Fold Accelerated Musculoskeletal Turbo Spin Echo MRI Within Reach.人工智能驱动的超快速超分辨率磁共振成像:10倍加速的肌肉骨骼快速自旋回波磁共振成像指日可待。
Invest Radiol. 2023 Jan 1;58(1):28-42. doi: 10.1097/RLI.0000000000000928. Epub 2022 Nov 2.
8
Deep Learning Reconstruction for Accelerated Spine MRI: Prospective Analysis of Interchangeability.深度学习加速脊柱 MRI 重建:可交换性的前瞻性分析。
Radiology. 2023 Mar;306(3):e212922. doi: 10.1148/radiol.212922. Epub 2022 Nov 1.
9
Application of deep learning-based image reconstruction in MR imaging of the shoulder joint to improve image quality and reduce scan time.基于深度学习的图像重建在肩关节磁共振成像中的应用,以提高图像质量并减少扫描时间。
Eur Radiol. 2023 Mar;33(3):1513-1525. doi: 10.1007/s00330-022-09151-1. Epub 2022 Sep 27.
10
MRI-based observation of the size and morphology of temporomandibular joint articular disc and condyle in young asymptomatic adults.基于 MRI 的年轻无症状成年人颞下颌关节关节盘和髁突大小及形态的观察。
Dentomaxillofac Radiol. 2022 Mar 1;51(3):20210272. doi: 10.1259/dmfr.20210272. Epub 2021 Oct 13.