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

MRI acute/sub-acute ischemic stroke segmentation with deep learning: A comprehensive review.

International review of cell and molecular biology·2026
Same author

Synergistic fusion of a multilevel visual transformer in CNN for variable-length volumetric radiographic data analysis and content-based retrieval.

Scientific reports·2026
Same author

A Benchmark Dataset for Concealed Improvised Explosive Device Detection in X-ray Security Imaging.

Scientific data·2026
Same author

Pharmacotherapeutic landscape for the management of agitation associated with Alzheimer's disease.

Expert opinion on pharmacotherapy·2026
Same author

Multi-representation thermal features for enhanced defect analysis in pulse thermography.

Scientific reports·2026
Same author

HBID24K: A New Benchmark Dataset for Vulnerable Houbara Bustard and Intruder Detection in Wildlife Monitoring.

Scientific data·2026

相关实验视频

Updated: Jun 4, 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

基于视网膜血管细分的动态统计注意力轻量级模型:DyStA-RetNet.

Amit Bhati1, Samir Jain1, Neha Gour2

  • 1PDPM Indian Institute of Information Technology, Design and Manufacturing, Jabalpur 482005, India.

Computers in biology and medicine
|December 28, 2024
PubMed
概括

一个新的轻量级深度学习模型,DyStA-RetNet,在视网膜底图像中准确地划分视网膜血管. 这种计算效率高的方法改善了对眼睛疾病的诊断,即使在资源有限的环境中也是如此.

关键词:
编码器 解码器轻量级的CNN 轻量级的CNN多个尺度的动态注意力 (MDA)视网膜血管细分 视网膜血管细分统计空间注意力 (SSA) 统计空间注意力

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

2.7K
Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model
10:32

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model

Published on: April 2, 2021

3.4K

相关实验视频

Last Updated: Jun 4, 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
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
Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model
10:32

Monitoring Dynamic Growth of Retinal Vessels in Oxygen-Induced Retinopathy Mouse Model

Published on: April 2, 2021

3.4K

科学领域:

  • 眼科医生 眼科 眼科
  • 医疗成像医学成像
  • 计算机视觉 计算机视觉

背景情况:

  • 准确的视网膜血管细分对于诊断和治疗眼睛疾病至关重要.
  • 现有的深度学习模型与复杂的容器结构,假阳性和计算需求作斗争.
  • 在资源有限的环境中部署受到模型复杂性的阻碍.

研究的目的:

  • 开发基于注意力的,计算高效的架构,以改善视网膜血管细分.
  • 解决现有模型在准确性和部署性方面的局限性.

主要方法:

  • 拟议的DyStA-RetNet:一个浅层的CNN编码器解码器架构.
  • 嵌入部分解码器用于高级语义传输和单独的分支用于低级信息.
  • 利用多尺度的动态注意力和统计空间注意力块来增强特征学习.

主要成果:

  • 在四个基准数据集 (DRIVE,STARE,CHASEDB,HRF) 中,DyStA-RetNet表现出卓越的细分性能.
  • 获得的可训练参数 (37.19K) 和GFLOPS (0.75) 显著减少.
  • 展示了适应临床应用的适应性.

结论:

  • 轻量级的DyStA-RetNet可以有效地提取复杂的视网膜血管组件.
  • 该模型在计算上高效,适用于资源有限的环境.
  • 能够提高视网膜疾病的诊断能力.