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

Hybrid deep learning and feature selection approach for autism detection from rs-fMRI data.

PloS one·2026
Same author

Aerial image segmentation using multilevel thresholding based on multi strategy Osprey optimization algorithm.

Scientific reports·2026
Same author

Enhancing particle swarm optimization based on optical computing mechanism: application to dyslexia detection.

Frontiers in artificial intelligence·2026
Same author

Enhanced generalized normal distribution optimizer with Gaussian distribution repair method and cauchy reverse learning for features selection.

Scientific reports·2026
Same author

Deep learning-based feature selection for detection of autism spectrum disorder.

Frontiers in artificial intelligence·2025
Same author

The Predictive Value of Dry Brain Sign for Open Spina Bifida at First Trimester Anomaly Scan: A Case-Control study.

Academic radiology·2025

相关实验视频

Updated: May 9, 2025

Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction
09:14

Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction

Published on: September 28, 2019

11.3K

一种深度学习方法用于神经损伤的分类在手臂病使用磁共振神经学与修改的徒步旅行优化算法的神经损伤分类.

Abdelghani Dahou1, Mohamed Abd Elaziz2, Mohamed G Khattap3

  • 1School of Computer Science and Technology, Zhejiang Normal University, Jinhua321004, China (A.D.); Mathematics and Computer Science department, University of Ahmed DRAIA, 01000, Adrar, Algeria (A.D.).

Academic radiology
|April 29, 2025
PubMed
概括

使用深度学习和优化的人工智能框架从MRN扫描中显著改进了手臂病的诊断,准确地分类了神经损伤的严重程度,并帮助临床决策.

关键词:
臂病变 (BP) 是一种手臂病变.综合学习 (CL) 是指全面的学习.深度学习 (DL) 是指深度学习.功能选择 (FS) 功能选择徒步旅行优化算法 (HOA)磁共振神经图 (MRN) 是一种磁共振神经图.移动网络V4 移动网络V4

更多相关视频

A Mouse Model of Direct Anastomosis via the Prespinal Route for Crossing Nerve Transfer Surgery
05:56

A Mouse Model of Direct Anastomosis via the Prespinal Route for Crossing Nerve Transfer Surgery

Published on: October 19, 2021

1.8K
Automated Gait Analysis to Assess Functional Recovery in Rodents with Peripheral Nerve or Spinal Cord Contusion Injury
06:31

Automated Gait Analysis to Assess Functional Recovery in Rodents with Peripheral Nerve or Spinal Cord Contusion Injury

Published on: October 6, 2020

6.0K

相关实验视频

Last Updated: May 9, 2025

Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction
09:14

Surface Electromyographic Biofeedback as a Rehabilitation Tool for Patients with Global Brachial Plexus Injury Receiving Bionic Reconstruction

Published on: September 28, 2019

11.3K
A Mouse Model of Direct Anastomosis via the Prespinal Route for Crossing Nerve Transfer Surgery
05:56

A Mouse Model of Direct Anastomosis via the Prespinal Route for Crossing Nerve Transfer Surgery

Published on: October 19, 2021

1.8K
Automated Gait Analysis to Assess Functional Recovery in Rodents with Peripheral Nerve or Spinal Cord Contusion Injury
06:31

Automated Gait Analysis to Assess Functional Recovery in Rodents with Peripheral Nerve or Spinal Cord Contusion Injury

Published on: October 6, 2020

6.0K

科学领域:

  • 医疗成像医学成像
  • 人工智能的人工智能
  • 神经学 神经学

背景情况:

  • 由于复杂的解剖学和重叠的症状,手臂病 (BPs) 存在诊断挑战.
  • 磁共振神经图 (MRN) 提供先进的成像,但需要专门的解释.
  • 精确地分类神经损伤的严重程度 (神经不良,轴突损伤,神经损伤) 对于有效的治疗至关重要.

研究的目的:

  • 开发和验证基于人工智能的框架,以使用MRN数据改进手臂病的分类.
  • 将深度学习 (DL) 与优化功能选择算法集成,以提高诊断准确度.
  • 为了区分正常和异常的神经状况,并对损伤严重程度进行分类.

主要方法:

  • 一个框架,将MobileNetV4用于特征提取和修改的徒步旅行优化算法 (MHOA) 与综合学习 (CL) 结合在一起,用于特征选择.
  • 利用了来自39名手臂病患者的MRN数据,跨越STIR,T2,T1和DWI序列.
  • 根据Seddon的标准对受伤进行分类,区分正常/异常状态和受伤严重程度.

主要成果:

  • 在使用STIR和T2序列区分正常和异常条件时,获得了1.0000的准确性.
  • 在使用STIR对伤害严重程度进行分类时,证明了高精度 (0.9820),优于其他元启发算法.
  • 在DWI序列上报告了高分类准确性 (0.9667),具有整体高灵敏度和特异性.

结论:

  • 人工智能框架通过准确地分类神经损伤类型,显著提高了手臂病的诊断.
  • 整合DL和优化技术可以减少诊断的变化,为临床环境提供了有价值的工具.
  • 这个框架有可能通过精确的诊断来改善临床决策和患者的结果.