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

相关实验视频

Updated: May 28, 2025

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

7.1K

在底部图像中,用于视网膜血管细分的Gabor调制深度可分离卷积.

Radha K1, Yepuganti Karuna2

  • 1School of Electronics Engineering, Vellore Institute of Technology, Vellore, India.

Computers in biology and medicine
|February 13, 2025
PubMed
概括

这项研究引入了一种新的加博尔调制的UNet模型,用于在糖尿病视网膜病变中精确细分视网膜血管. 该模型提高了诊断的准确性,即使在有限的数据和低质量的图像上.

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

Enhanced skin cancer classification for minority classes using Conditional GAN pipeline and CNN-ViT ensemble.

Scientific reports·2026
Same author

Respectful maternity care during childbirth: postnatal women's perspectives. Cross-sectional study from central India: February - December 2023.

Revista colombiana de obstetricia y ginecologia·2025
Same author

Brain tumour segmentation in fused MRI-PET images with permutate U-Net framework.

PloS one·2025
Same author

Histone Deacetylase 2 in Alzheimer's Disease: A Comprehensive Molecular Blueprint for Therapeutic Targeting.

Molecular neurobiology·2025
Same author

Modified energy-based GAN for intensity in homogeneity correction in brain MR images.

Scientific reports·2025
Same author

Latent space autoencoder generative adversarial model for retinal image synthesis and vessel segmentation.

BMC medical imaging·2025

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:

  • 对视网膜血管的准确细分对于诊断和管理糖尿病视网膜病变至关重要.
  • 挑战包括不同的船只大小,分叉,曲线段和不一致的图像质量.
  • 现有的深度学习模型在几何转换方面遇到了困难,需要大量的训练数据.

研究的目的:

  • 开发一个强大而高效的视网膜血管细分模型.
  • 解决当前深度学习方法在处理数据稀缺性和图像质量变化的局限性.
  • 通过增强血管细分,提高糖尿病视网膜病变的诊断准确度.

主要方法:

  • 提出了一个Gabor调制的深度可分离卷积UNet模型.
  • 集成的Gabor过器可提高对船舶方向和空间频率的灵敏度.
  • 结合了Gabor卷积与深度可分离卷积,以提高网络学习能力.

主要成果:

  • 在DRIVE,STARE和CHASE_DB1数据集上证明有效,即使训练数据有限.
  • 实现了卓越的细分性能,特别适用于不同方向和尺寸的船只.
  • 在杂和进展的糖尿病视网膜病变图像上展示了强度,优于其他深度学习模型.

结论:

  • 加博尔调节的UNet模型有效地对视网膜血管进行细分,解决糖尿病视网膜病变的关键挑战.
  • 该模型具有很高的诊断潜力,特别是在数据有限的场景和资源有限的环境中.
  • 它的轻量级架构促进了临床应用和整合到各种医疗保健环境中.
关键词:
深度学习是一种深度学习.糖尿病视网膜病变 - 糖尿病视网膜病变早期诊断 早期诊断 早期诊断基金的图像 基金的图像联合国网络 联合国网络 联合国网络船舶细分 船舶的细分

更多相关视频

Doppler Optical Coherence Tomography of Retinal Circulation
10:46

Doppler Optical Coherence Tomography of Retinal Circulation

Published on: September 18, 2012

18.6K
Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound
07:29

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Published on: October 4, 2021

2.3K

相关实验视频

Last Updated: May 28, 2025

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

7.1K
Doppler Optical Coherence Tomography of Retinal Circulation
10:46

Doppler Optical Coherence Tomography of Retinal Circulation

Published on: September 18, 2012

18.6K
Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound
07:29

Deep Vascular Imaging in the Eye with Flow-Enhanced Ultrasound

Published on: October 4, 2021

2.3K