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

Niche Partitioning and Facilitative Coexistence of Two Sympatric Pheasants Across a Gradient of Human Disturbance.

Ecology and evolution·2026
Same author

Early identification of neoadjuvant therapy non-response via multimodal immune-imaging biomarkers in breast cancer.

Frontiers in immunology·2026
Same author

Thyrotropin/growth hormone co-secreting pituitary adenoma with pancytopenia: a case report.

Journal of medical case reports·2026
Same author

Mesenchymal neoplasms with RAF/BRAF alterations: eight cases revealing novel fusions, V600E mutation and clonal evolution.

Journal of clinical pathology·2026
Same author

Advances in Immunotherapy for Head and Neck Squamous Cell Carcinoma: Focus on PD-1/PD-L1 Blockade and Beyond.

Clinical Medicine Insights. Oncology·2026
Same author

Feedback intensity adjustable half-open-cavity random fiber laser based on erbium-doped fiber.

Optics letters·2026

相关实验视频

Updated: Jan 16, 2026

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

4.2K

有效的视网膜血管细分与78K参数.

Zhigao Zeng1, Jiakai Liu1, Xianming Huang1

  • 1School of Computer Science, Hunan University of Technology, Zhuzhou 412007, China.

Journal of imaging
|September 26, 2025
PubMed
概括
此摘要是机器生成的。

DSAE-Net使用轻量级的双阶段网络为糖尿病视网膜病变诊断提供精确的视网膜血管细分. 这种高效的模型减少了复杂性,同时提高了性能,帮助实时临床应用.

关键词:
深度学习是一种深度学习.图像分割 图像细分 图像细分轻量级网络是轻量级的网络.视网膜血管细分器的细分细分化 细分化的细分化自己注意力自我注意力

更多相关视频

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

8.7K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

22.2K

相关实验视频

Last Updated: Jan 16, 2026

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies

Published on: March 12, 2022

4.2K
Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography
07:23

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

8.7K
Using Retinal Imaging to Study Dementia
09:17

Using Retinal Imaging to Study Dementia

Published on: November 6, 2017

22.2K

科学领域:

  • 医疗成像医学成像
  • 深度学习 (Deep Learning) 是一种深度学习.
  • 眼科医生 眼科 眼科

背景情况:

  • 糖尿病视网膜病变的诊断依赖于视网膜血管细分.
  • 当前的深度学习模型经常面临准确性-复杂性权衡问题.
  • 有效的细分对于临床环境至关重要.

研究的目的:

  • 开发一个轻量级但准确的深度学习模型用于视网膜血管细分.
  • 在计算复杂性和准确性方面解决现有模型的局限性.
  • 为了促进糖尿病视网膜病变的早期诊断.

主要方法:

  • 提出了DSAE-Net,这是一个双阶段网络,具有参数化级联W形架构.
  • 引入了骨架距离损失 (SDL) 来管理阶级不平衡和边界问题.
  • 开发了交叉模式融合注意力 (CMFA) 和协调注意力门 (CAGs) 以提高特征精细化.
  • 使用了DRIVE,CHASE_DB1,HRF和STARE数据集进行评估.

主要成果:

  • 与最先进的轻量级模型相比,DSAE-Net实现了更高的细分精度.
  • 拟议的架构显著降低了计算复杂性 (仅使用1%的U-Net参数).
  • 该模型在多个基准数据集中展示了稳定性.
  • SDL有效地处理了视网膜图像中固有的严重阶级失衡.

结论:

  • DSAE-Net为视网膜血管细分提供了高效准确的解决方案.
  • 该模型的低复杂性和高性能适合实时诊断.
  • 这种方法支持在资源有限的环境中早期检测糖尿病视网膜病变.