Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

Impact of Postoperative Chronic Back Pain Syndrome on the Incidence of Psychiatric and Brain Disorders, and All-Cause Mortality [Letter].

Journal of pain research·2026

Same author

Laser-Induced Irregular Hierarchical Interface Structures Offering High Sensitivity and Broad Detection Range of Flexible Pressure Sensors.

ACS applied materials & interfaces·2026

Same author

Biofilm mediated arsenic migration and transformation in groundwater under the influence of dissolved organic matter.

Journal of hazardous materials·2026

Same author

Clinical Research Progress in the Treatment and Prognosis of Comorbid Coronary Heart Disease and Lung Cancer.

Reviews in cardiovascular medicine·2026

Same author

Disruption of Pik3r1 promotes muscle hyperplasia and lipolysis in grass carp (Ctenopharyngodon idella).

Comparative biochemistry and physiology. Part A, Molecular & integrative physiology·2026

Same author

Association between achievement motivation and anxiety symptoms among college students.

Frontiers in psychology·2026

Search research articles

相关实验视频

Updated: Jul 23, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

标志性-辅助解剖-敏感视网膜血管细分网络

Haifeng Zhang¹, Yunlong Qiu¹, Chonghui Song¹

¹College of Information Science and Engineering, Northeastern University, Shenyang 110819, China.

Diagnostics (Basel, Switzerland)

|July 14, 2023

概括

这项研究引入了针对视网膜血管细分的解剖学敏感深度学习框架,改善了薄血管检测和连接性. 这种新的方法提高了眼科疾病的诊断准确度.

科学领域:

医疗成像医学成像
计算机视觉计算机视觉
眼科医生眼科眼科

背景情况:

自动视网膜血管细分对于诊断眼睛疾病至关重要.
目前的深度学习方法在薄型容器细分和保持容器连接方面扎.

研究的目的:

为增强视网膜血管细分开发一种新的解剖敏感框架.
为了改善细血管的检测,并保持血管系统的拓连续性.

主要方法:

使用TransUNet作为骨干架构.
集成的自我监督提取的解剖学地标,以对比学习为指导.
采用对解剖结构敏感的框架进行网络指导.

主要成果:

在DRIVE和CHASE-DB1数据集上实现了卓越的性能,超过了最先进的方法.
在STARE数据集上证明了竞争性结果.
视觉化证实了改善的拓连续性和薄型容器识别.

结论:

拟议的解剖学敏感框架有效地解决了当前视网膜血管细分的局限性.
该方法显示出在眼科疾病诊断中临床应用的巨大潜力.

关键词:

在TransUNet的自我监督里程碑.相反的学习学习学习.视网膜血管细分器的细分

更多相关视频

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

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

Published on: March 12, 2022

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

相关实验视频

Last Updated: Jul 23, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

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

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

Published on: March 12, 2022

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Efficient and Consistent Generation of Retinal Pigment Epithelium/Choroid Flatmounts from Human Eyes for Histological Analysis

Published on: October 28, 2022

自主监督的地标指导增强了形态特征的学习,以提高细分精度.