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

TGF-β controls developmental fate and functional identity of thymic γδ T cells.

Journal of immunology (Baltimore, Md. : 1950)·2026
Same author

Lightweight dual-backbone network with attentional fusion for wound image classification.

Scientific reports·2026
Same author

Cardiovascular Safety of Next-Generation Antibody-Drug Conjugates in HER2-Low and Triple-Negative Breast Cancer: A Narrative Review (2020-2025).

Cureus·2026
Same author

Magnetic resonance imaging use in pediatric deep brain stimulation: a systematic review and call for standardization.

Neuroradiology·2026
Same author

Analysis of Fall and Jump Behaviors in Freely Moving <i>Drosophila melanogaster</i> Using 58 fps Video.

Insects·2026
Same author

Improved Microplastic Identification from Simultaneously Collected Photothermal Infrared and Raman Spectra Using Multiview Conformal Prediction.

ACS measurement science au·2026

相关实验视频

Updated: Jun 29, 2025

Digital Planimetry for Assessing Wound Closure Kinetics in a Mouse Model
07:56

Digital Planimetry for Assessing Wound Closure Kinetics in a Mouse Model

Published on: January 10, 2025

499

综合图像和位置分析用于伤口分类:一种深度学习方法

Yash Patel1, Tirth Shah1, Mrinal Kanti Dhar1

  • 1Department of Computer Science, University of Wisconsin-Milwaukee, Milwaukee, WI, USA.

Scientific reports
|March 26, 2024
PubMed
概括

这项研究引入了一种新的深度学习网络,用于使用图像和身体位置数据对四种常见的伤口类型进行分类. 先进的多模式网络显著提高了伤口分类的准确性,有助于临床诊断.

关键词:
身体地图 身体地图组合图像位置分析.卷积神经网络是一种卷积神经网络.深度学习是一种深度学习.多模式伤口图像分类多模式伤口图像分类转移学习转移学习伤口位置信息 信息 伤口位置信息

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Human Ex vivo Wound Model and Whole-Mount Staining Approach to Accurately Evaluate Skin Repair
07:32

Human Ex vivo Wound Model and Whole-Mount Staining Approach to Accurately Evaluate Skin Repair

Published on: February 17, 2021

7.2K

相关实验视频

Last Updated: Jun 29, 2025

Digital Planimetry for Assessing Wound Closure Kinetics in a Mouse Model
07:56

Digital Planimetry for Assessing Wound Closure Kinetics in a Mouse Model

Published on: January 10, 2025

499
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.7K
Human Ex vivo Wound Model and Whole-Mount Staining Approach to Accurately Evaluate Skin Repair
07:32

Human Ex vivo Wound Model and Whole-Mount Staining Approach to Accurately Evaluate Skin Repair

Published on: February 17, 2021

7.2K

科学领域:

  • 医学成像分析分析 医学成像分析
  • 医疗保健中的人工智能
  • 伤口护理诊断 伤口护理诊断

背景情况:

  • 全球急性和慢性伤口的流行需要改进诊断和治疗策略.
  • 目前的伤口分类方法往往缺乏精度,影响患者的护理.
  • 准确的伤口分类对于有效的临床决策至关重要.

研究的目的:

  • 开发和评估一个创新的多模式深卷积神经网络,用于分类糖尿病,压力,手术和静脉.
  • 通过将伤口图像与相应的身体位置数据集成来增强伤口图像分类.
  • 通过一种新的架构和身体地图系统,改进传统的伤口分类技术.

主要方法:

  • 开发一个集成VGG16,ResNet152和EfficientNet模型的多式联网.
  • 整合了空间和通道智能的挤压和激发模块,轴向注意力和自适应式门式多层感知器.
  • 使用人体地图系统进行准确的伤口位置标记,并与图像数据一起用于在两个不同的数据集上进行训练和评估.

主要成果:

  • 拟议的多式联网实现了高分类准确度:74.79-100% (没有位置的ROI),73.98-100% (带有位置的ROI) 和78.10-100% (整个图像).
  • 性能明显超过传统的伤口图像分类方法.
  • 与文献中先前报告的指标相比,证明了更高的准确性.

结论:

  • 开发的多模式网络显示出作为伤口图像分类的有效决策支持工具的巨大潜力.
  • 伤口图像和位置数据的整合提高了分类精度.
  • 这种方法为临床伤口评估和管理提供了有希望的进步.