Jove
Visualize
联系我们
JoVE
x logofacebook logolinkedin logoyoutube logo
关于 JoVE
概览领导团队博客JoVE 帮助中心
作者
出版流程编辑委员会范围与政策同行评审常见问题投稿
图书馆员
用户评价订阅访问资源图书馆顾问委员会常见问题
研究
JoVE JournalMethods CollectionsJoVE Encyclopedia of Experiments存档
教育
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab Manual教师资源中心教师网站
使用条款与条件
隐私政策
政策

相关概念视频

您也可能阅读

相关文章

通过共同作者、期刊和引用图与本文相关的文章。

排序
Same author

Dysfunctional large-scale networks linking PTSD and cognitive impairment.

Journal of psychiatric research·2026
Same author

Relationship between new-onset falls and neuroimaging markers of Alzheimer's disease in the UK Biobank.

Journal of Alzheimer's disease : JAD·2026
Same author

Clinical and Radiographic Outcomes at a Mean of 7 Years Following Primary Transfibular Total Ankle Arthroplasty in Younger and Older Patients.

The Journal of bone and joint surgery. American volume·2026
Same author

Beyond the LUMIR challenge: The pathway to foundational registration models.

Medical image analysis·2026
Same author

Karnofsky Performance Status Is Associated with Patient and Graft Survival After Liver Retransplantation.

Transplantation proceedings·2026
Same author

Multi-scale Radiomic Fingerprint: Quantifying Spatial Changes in Biology.

Journal of imaging informatics in medicine·2026

相关实验视频

Updated: Jul 26, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.1K

脑瘤细分用于多模态MRI缺失信息的脑瘤细分.

Xue Feng1,2, Kanchan Ghimire2, Daniel D Kim3,4

  • 1Biomedical Engineering, University of Virginia, 22903, Charlottesville, VA, USA.

Journal of digital imaging
|June 20, 2023
PubMed
概括

这项研究引入了深层卷积神经网络的序列丢失技术,以改善当MRI序列缺失时大脑瘤细分的准确性. 当所有序列都存在时,该方法提高了稳定性,而不会牺牲性能.

关键词:
3D U-Net 是一个 3D U-Net.大脑瘤的细分 脑瘤的细分深度学习是一种深度学习.多对比的MRI是多对比的MRI序列中断 序列中断

更多相关视频

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.0K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K

相关实验视频

Last Updated: Jul 26, 2025

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

48.1K
Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images
06:48

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

9.0K
Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies
04:25

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

2.5K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 神经瘤学神经瘤学

背景情况:

  • 深层卷积神经网络 (DCNNs) 显示出使用多模态MRI进行脑瘤细分的潜力.
  • 瘤细分受到缺失或不寻常的MRI序列的挑战,需要强大的模型.
  • 训练所有MRI序列组合的单独模型是不切实际的.

研究的目的:

  • 开发一个DCNN框架,在缺少MRI序列的情况下进行强大的脑瘤细分.
  • 引入一种新的序列丢失技术,以训练DCNN对数据变化的弹性.
  • 为了评估拟议的方法在BraTS 2021数据集上的表现.

主要方法:

  • 实现了一个DCNN框架,使用了序列丢失技术.
  • 训练有素的网络能够对缺失的MRI序列进行强大处理,同时利用可用的MRI序列.
  • 在RSNA-ASNR-MICCAI BraTS 2021挑战数据集上验证的性能.

主要成果:

  • 当所有MRI序列都可用时,没有观察到具有或没有序列中断的显著性能差异 (p > 0.05).
  • 序列丢失在关键MRI序列无法使用时显著改善了细分性能.
  • 例如,当使用T1,T2和FLAIR时,增强瘤 (ET) 的子相似系数 (DSC) 从0.143增加到0.486.

结论:

  • 序列脱落是一种有效和简单的方法,用于增强脑瘤细分的稳定性,缺少MRI数据.
  • 拟议的方法在完整的数据中保持高性能,同时在不完整的数据中显著改进.
  • 这种技术为MRI数据可能变化的临床环境提供了实用解决方案.