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

Association of breastfeeding duration with cardiac structure and function in 4 years old.

European journal of clinical nutrition·2025
Same author

Synergistic Effects of Flower Color and Mechanical Barriers on Pollinator Selection Within the Papilionoideae of Fabaceae.

Plants (Basel, Switzerland)·2025
Same author

Protective effects of metformin against volatile organic compounds-induced developmental toxicity in zebrafish embryos.

Comparative biochemistry and physiology. Toxicology & pharmacology : CBP·2025
Same author

Analysis of anatomical characteristics of congenital pulmonary airway malformation lesions based on CT images.

Frontiers in pediatrics·2025
Same author

Maternal exposure factors in pregnancy that affect fetal CHD risk: a case-control study.

Cardiology in the young·2025
Same author

ELABELA-32 Alleviates Doxorubicin-Induced Chronic Cardiotoxicity by Inhibiting the TGF-β/Smad Signaling Pathway.

Cardiovascular toxicology·2025

相关实验视频

Updated: Jul 11, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

435

基于RSP-SA Unet网络的视网膜血管细分方法.

Kun Sun1,2, Yang Chen1,2, Fuxuan Dong1,2

  • 1The Higher Educational Key Laboratory for Measuring & Control Technology and Instrumentation of Heilongjiang Province, Harbin University of Science and Technology, Harbin, China.

Medical & biological engineering & computing
|November 14, 2023
PubMed
概括

一个新的深度学习模型,Residual SimAM Pyramid-Spatial Attention Unet (RSP-SA Unet),通过改进特征提取和边缘细节保存以进行 fundus 图像分析,有效地分割视网膜血管.

关键词:
没有参数的注意力.视网膜血管细分 视网膜血管细分空间注意力空间注意力

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

7.6K
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

2.8K

相关实验视频

Last Updated: Jul 11, 2025

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

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

435
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

7.6K
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

2.8K

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:

  • 视网膜血管细分对于诊断底部疾病至关重要.
  • 现有的方法难以提取细粒度的容器特征并保存边缘细节.

研究的目的:

  • 引入一种基于Unet的新型模型,RSP-SA Unet,以解决视网膜血管细分的局限性.
  • 为了提高精细的船舶特征的提取和船舶边缘检测的准确性.

主要方法:

  • 拟议的RSP-SA Unet在编码/解码层中结合了剩余SimAM金字塔空间注意力 (RSP) 结构,用于多级特征提取.
  • 空间注意力 (SA) 集成到上采样层中,以改善低对比度,小血管的细分.
  • 该模型在CHASE_DB1,DRIVE和STARE数据集上进行了评估.

主要成果:

  • 在测试的数据集上,RSP-SA Unet实现了0.9763,0.9704和0.9724的高细分精度 (ACC).
  • 该模型表现出强的性能,ROC曲线下的面积 (AUC) 达到0.9896,0.9858和0.9906.
  • 总体表现超过了现有的比较方法.

结论:

  • 与以前的方法相比,RSP-SA Unet模型显著改善了视网膜血管细分.
  • 增强的特征提取和注意力机制有助于在识别细血管及其边缘方面获得更高的准确性.
  • 这种模型对改善 fundus 相关疾病的自动诊断非常有希望.