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

Letter to the Editor: Magnetic resonance imaging-based deep learning radiomics for preoperative risk stratification in pediatric hepatoblastoma.

World journal of radiology·2026
Same author

Effect of Saroglitazar on Glycemic Status: A Meta-analysis.

Cureus·2026
Same author

Transforming Medical Education to Meet India's Healthcare Demands.

The Journal of the Association of Physicians of India·2025
Same author

Dr Upendranath Brahmachari: A Pioneer in Tropical Medicine and Public Health Advocacy.

The Journal of the Association of Physicians of India..·2025
Same author

Association of Selective VDR Gene Polymorphisms with Diffuse Large B-Cell Lymphoma (DLBCL) in a South Indian Population.

Asian Pacific journal of cancer prevention : APJCP·2025
Same author

Risk factor assessment for post-thrombolytic coronary angiogram normalcy in young myocardial infarction patients.

Journal of basic and clinical physiology and pharmacology·2025

相关实验视频

Updated: Jan 12, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.1K

在MRI中用于神经退行性模式识别的等级图形引导的上下文表示学习.

Shravan Venkatraman1, Joe Dhanith P R1, Muthu Subash Kavitha2

  • 1School of Computer Science and Engineering, Vellore Institute of Technology (VIT), Chennai, Tamil Nadu, India.

Computers in biology and medicine
|November 8, 2025
PubMed
概括

这项研究引入了一个可解释的深度学习模型,RG-ViT,用于从MRI扫描中高精度地诊断自身免疫性神经退行性疾病,如阿尔茨海默症和帕金森症.

关键词:
层次性的特征概况分析.磁共振成像技术 磁共振成像技术ND疾病是ND疾病.剩余的学习学习.空间依赖模型的空间依赖模型.视觉变压器 视觉变压器

更多相关视频

Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.6K
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
09:06

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

12.6K

相关实验视频

Last Updated: Jan 12, 2026

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
14:27

Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data

Published on: June 26, 2013

16.1K
Three-Dimensional Shape Modeling and Analysis of Brain Structures
05:33

Three-Dimensional Shape Modeling and Analysis of Brain Structures

Published on: November 14, 2019

7.6K
Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease
09:06

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

12.6K

科学领域:

  • 神经科学是一个神经科学.
  • 人工智能的人工智能
  • 医疗成像医学成像

背景情况:

  • 神经退行性疾病 (ND) 是影响中枢神经系统的自身免疫性疾病.
  • 深度学习在医学成像中显示出前景,但需要解释性才能获得临床信任.
  • 在ND疾病中的病变呈现出复杂的空间模式,挑战传统模型.

研究的目的:

  • 开发一种可解释的深度学习分类器,用于常见的自身免疫性神经退行性疾病.
  • 改进在脑MRI数据中捕获本地和全球关系以进行诊断.
  • 提高AI在神经退行性疾病诊断中的临床接受度.

主要方法:

  • 开发了一个残余图神经网络增强视觉变换器 (RG-ViT).
  • 磁力共振成像数据以相互连接的贴片的图形表示,用于分析.
  • 剩余的连接被集成到GNN框架中,以保留功能并改善消息传递.

主要成果:

  • 在检测多发性硬化症 (98.7%),帕金森病 (99.6%) 和阿尔茨海默病 (99.1%) 中,RG-ViT实现了高精度.
  • 该模型在全球ND疾病分类的综合数据集上显示出强大的通用性,F1得分为99.2%.
  • 该方法有效地解决了基于补丁的MRI分析中的空间断开问题.

结论:

  • RG-ViT模型为诊断自身免疫性神经退行性疾病提供了一个高度准确和可解释的解决方案.
  • 这种可解释的AI方法可以为临床应用建立医疗专业人员的信心.
  • RG-ViT框架显示了在神经病学中推进人工智能驱动的诊断的巨大潜力.