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

Lymphatic Malformation: Classification, Pathogenesis, and Therapeutic Strategies.

Annals of vascular surgery·2025
Same author

Cardiac magnetic resonance feature tracking evaluates left atrial strain in patients with systemic lupus erythematosus and mitral regurgitation.

Lupus·2025
Same author

A Spatial analysis of chickenpox in Chongqing, China, during 2015-2023.

Scientific reports·2025
Same author

A 14-year influenza reinfection surveillance in Chongqing, China: A retrospective analysis.

Human vaccines & immunotherapeutics·2025
Same author

Urban pertussis epidemiological patterns in a highly vaccinated megacity: Policy impacts and control strategies in Chongqing, China, 2005-2024.

International journal of infectious diseases : IJID : official publication of the International Society for Infectious Diseases·2025
Same author

Disrupted interhemispheric functional and structural connectivity in patients with major depressive disorder.

Progress in neuro-psychopharmacology & biological psychiatry·2025

相关实验视频

Updated: Sep 17, 2025

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

3.0K

DMSU-Net++:一种基于改进的U-Net+的双重多尺度视网膜血管细分方法.

Liu Ming1, Li Qi1

  • 1School of Electronic and Information Engineering, University of Science and Technology Liaoning, Anshan, Liaoning, China.

PloS one
|July 2, 2025
PubMed
概括

我们开发了DMSU-Net++,这是一种用于视网膜血管细分的改进方法. 这种方法提高了识别细毛细血管和不同大小的血管的准确性,优于现有方法.

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 生物医学工程 生物医学工程

背景情况:

  • 由于不同大小,形状和复杂的毛细血管结构,视网膜血管的准确细分具有挑战性.
  • 现有的方法难以处理视网膜血管结构中存在的细致形态细节和尺度变化.

研究的目的:

  • 提出一个改进的视网膜血管细分方法,DMSU-Net++ (双多尺度U-Net++),以解决当前技术的局限性.
  • 为了提高视网膜血管细分的准确性和稳定性,特别是细毛细血管和不同尺度.

主要方法:

  • 开发了DMSU-Net++,一个增强的U-Net++架构,采用了使用波形变换的新型多尺度特征提取模块 (WTSAFM).
  • 通过级联MFE模块实现双重多尺度特征提取模块,以有效地捕获频率和空间信息.
  • 在两个公共数据集上对该方法进行了评估:DRIVE和CHASE-DB1.

主要成果:

  • DMSU-Net++在DRIVE上获得了82.75%的F1评分,在CHASE-DB1.1上获得了82.81%.
  • 该方法显示了高灵敏度 (83.74%在驱动器上,85%在CHASE-DB1) 和AUC (97.86%在驱动器上,98.36%在CHASE-DB1).
  • 实验结果表明,与其他现有方法相比,细分性能优越.

更多相关视频

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

529
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K

相关实验视频

Last Updated: Sep 17, 2025

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

3.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

529
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.6K

结论:

  • 通过利用多级特征提取,DMSU-Net++有效地分割视网膜血管,包括细毛细血管.
  • 拟议的方法为视网膜图像分析提供了更好的准确性和上下文理解.
  • 在诊断视网膜疾病方面,DMSU-Net++显示出临床应用的巨大潜力.