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

Magnetic Resonance Imaging01:24

Magnetic Resonance Imaging

Magnetic resonance imaging (MRI) is a noninvasive medical imaging technique based on a phenomenon of nuclear physics discovered in the 1930s, in which matter exposed to magnetic fields and radio waves was found to emit radio signals. In 1970, a physician and researcher named Raymond Damadian noticed that malignant (cancerous) tissue gave off different signals than normal body tissue. He applied for a patent for the first MRI scanning device in clinical use by the early 1980s. The early MRI...

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

MAD-MT Score: A Tool to Optimize Patient Selection for Mechanical Thrombectomy in Distal Vessel Occlusions.

Stroke·2026
Same author

Neuroradiology Leads NIH Funding Among Clinician Diagnostic Radiologists: A 14-Year National Analysis.

AJNR. American journal of neuroradiology·2026
Same author

A Systematic Evaluation of Image Preprocessing in Deep Learning Detection and Segmentation of Intracranial Metastatic Disease.

AJNR. American journal of neuroradiology·2026
Same author

Gender Trends in Authorship Across Neuroradiology Journals (2016-2025).

AJNR. American journal of neuroradiology·2026
Same author

GLP-1 receptor agonists in obstructive sleep apnea: A propensity score-matched real-world analysis.

Respiratory medicine·2026
Same author

Ischemic Lesion Net Water Uptake Outperforms ASPECTS and CBF Less Than 30% in Predicting Futile Recanalization after Mechanical Thrombectomy.

Radiology·2026

相关实验视频

Updated: May 13, 2026

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.2K

使用深度学习优化MRI上的急性中风细分:自配置神经网络仅使用DWI序列提供高性能.

Peter Kamel1,2, Adway Kanhere3,4, Pranav Kulkarni3,4

  • 1Department of Diagnostic Radiology and Nuclear Medicine, University of Maryland School of Medicine, Baltimore, MD, USA. pkamel@som.umaryland.edu.

Journal of imaging informatics in medicine
|August 14, 2024
PubMed
概括

像nnU-Net这样的自我配置的深度学习模型只使用DWI MRI序列来实现出色的缺血性中风细分. 这些先进的模型显著优于传统的U-Net架构,证明了对外部临床数据的强大通用性.

关键词:
深度学习是一种深度学习.在心脏病发作.这就是为什么MRI是MRI.分段化 分段化 分段化 分段化一次性中风,中风.在 nnU-Net 网络上.

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

8.9K
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

47.9K

相关实验视频

Last Updated: May 13, 2026

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.2K
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

8.9K
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

47.9K

科学领域:

  • 放射学和医学成像学 医学成像学
  • 人工智能在医学中的应用
  • 神经学 神经学

背景情况:

  • 准确的心脏病细分对于管理缺血性中风和预测结果至关重要.
  • 将扩散加权成像 (DWI),ADC和FLAIRMRI序列结合起来,用于基于深度学习的心脏病细分的作用仍然不清楚.
  • 通过自配置技术实现自动化模型优化,有望提高性能和通用性.

研究的目的:

  • 通过深度学习评估DWI,ADC和FLAIRMRI序列对缺血性中风细分的实用性.
  • 将自配置nnU-Net模型与传统U-Net模型的性能进行比较.
  • 在外部临床数据集上评估表现最好的模型的概括性.

主要方法:

  • 在200次心脏病发作中使用MONAI训练了3D自配置nnU-Net和标准3DU-Net模型.
  • 使用DWI,ADC和FLAIR序列,单独或组合使用.
  • 通过对对 t 试验对50个病例的保留组进行细分结果的比较,并对50个MRI进行外部验证.

主要成果:

  • 使用DWI序列的nnU-Net实现了0.810 ± 0.155.5的子得分.
  • 用ADC和FLAIR序列补充DWI并没有产生统计学上显著的改善 (Dice得分0.813±0.150,p=0.15).
  • 在所有序列组合中,nnU-Net模型的性能明显优于标准U-Net模型 (p < 0.001).
  • 在50个MRI的外部验证中,阳性病例的Dice分数为0.704±0.199,在内出血病例中有一些虚假阳性.

结论:

  • 高度优化的神经网络,如nnU-Net,只使用DWI图像提供了出色的中风细分性能.
  • 在使用nnU-Net.net时,添加ADC和FLAIR序列并没有显著的性能提升.
  • 与标准U-Net架构相比,nnU-Net的卓越性能和通用性为在临床MRI环境中优化急性中风细分提供了坚实的基础.