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

Content-based image retrieval for Lung Nodule Classification Using Texture Features and Learned Distance Metric.

Journal of medical systems·2017
Same author

[Association between the ALK Gene Status and the Efficacy of First-line 
Pemetrexed Chemotherapy in Patients with Advanced Lung Adenocarcinoma].

Zhongguo fei ai za zhi = Chinese journal of lung cancer·2017
Same author

3D hole-transporting materials based on coplanar quinolizino acridine for highly efficient perovskite solar cells.

Chemical science·2017
Same author

ITGBL1 Predicts a Poor Prognosis and Correlates EMT Phenotype in Gastric Cancer.

Journal of Cancer·2017
Same author

The collective influence of 1, 25-dihydroxyvitamin D<sub>3</sub> with physiological fluid shear stress on osteoblasts.

Steroids·2017
Same author

A new analytical model for the changes of vascular endothelial growth factor in ischemic diseases.

Medical hypotheses·2017

相关实验视频

Updated: May 17, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

333

MDEU-Net:基于多头多尺度跨轴的医疗图像细分网络.

Shengxian Yan1, Yuyang Lei1, Jing Zhang1

  • 1Shaanxi Key Laboratory of Ultrasonics, School of Physics and Information Technology, Shanxi Normal University, Xi'an 710062, China.

Sensors (Basel, Switzerland)
|May 14, 2025
PubMed
概括

本研究介绍了MDEU-Net,这是一个用于医疗图像细分的新型深度学习模型. 它增强了复杂的医疗图像的特征提取和细节捕获,优于现有的方法.

关键词:
跨轴的注意力集中.功能融合功能融合功能医疗图像细分 医疗图像细分多个尺度的特征是多个尺度的特征.多项式的注意力

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

2.6K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.4K

相关实验视频

Last Updated: May 17, 2025

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

333
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

2.6K
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

42.4K

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 人工智能的人工智能

背景情况:

  • 注意力机制,特别是交叉轴注意力,已经推进了医疗图像细分.
  • 在复杂的医学图像的多尺度特征提取和细节捕获方面仍然存在挑战.

研究的目的:

  • 引入一个新的网络架构,MDEU-Net,以改善医疗图像细分.
  • 为了解决处理复杂图像,多尺度特征提取和细节捕获的局限性.

主要方法:

  • 提出了一个多头多尺度跨轴关注的MDEU-Net架构.
  • 采用多头注意力机制进行并行特征处理.
  • 集成了一个封闭的注意力机制,以实现高效的特征融合和选择性强调.
  • 嵌入剩余连接以减轻梯度消失并增强复杂结构捕获.

主要成果:

  • MDEU-Net架构有效地捕获了本地和全球信息.
  • 该模型擅长在各种空间尺度中提取特征.
  • 关闭的注意力和剩余的连接提高了关键细节和复杂结构的捕获.
  • 实验结果显示,与传统架构相比,性能优越.

结论:

  • MDEU-Net为医疗图像细分挑战提供了有效的解决方案.
  • 拟议的架构提高了计算效率和处理速度.
  • MDEU-Net在医疗图像细分任务中显示出显著的性能改进.