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

XLSTM transformer based quality prediction for tobacco cut rag in intermittent processing.

Scientific reports·2026

Same author

WTAP Deficiency Promotes Podocyte PANoptosis and FSGS via SPP1 Signaling.

Circulation research·2026

Same author

Polarity Inversion-Driven Band Structure Modulation, Strain Engineering, and Electrical Property Analysis on GaN/4H-SiC Heterojunctions.

ACS omega·2026

Same author

Mimosa-inspired dual-responsive flocculant with controllable hydrophobicity/hydrophilicity reconstruction for the purification of triclosan containing emulsified wastewater.

Water research·2026

Same author

Recombinant myonectin ameliorates sepsis‑induced cardiomyopathy by alleviating mitochondrial dysfunction via the AdipoR1/AMPK pathway.

International journal of molecular medicine·2026

Same author

Nano-Antenna Reactors With Spatially Coordinated Microenvironments Enable Atmospheric CO<sub>2</sub> Photoreduction to C<sub>2</sub>H<sub>6</sub>.

Advanced materials (Deerfield Beach, Fla.)·2026

Search research articles

相关实验视频

Updated: Jul 15, 2025

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

多尺度瓶残留网络用于视网膜血管细分.

Peipei Li¹, Zhao Qiu², Yuefu Zhan³

¹School of Computer Science and Technology, Hainan University, Haikou, 570228, China.

Journal of medical systems

|September 30, 2023

概括

本研究介绍了MBRNet,这是一个新的深度学习模型,用于在扫描激光眼镜镜 (SLO) 图像中对视网膜血管进行细分. 通过更少的参数,MBRNet实现了高精度,改善了眼科疾病的诊断.

关键词:

注意力机制注意力机制瓶残留模块的瓶问题深度学习是一种深度学习.视网膜血管细分视网膜血管细分扫描激光眼镜镜 (SLO) 是一种扫描激光眼镜.这就是U-Net.

更多相关视频

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

相关实验视频

Last Updated: Jul 15, 2025

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Retinal Vascular Reactivity as Assessed by Optical Coherence Tomography Angiography

Published on: March 26, 2020

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

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:

精确的视网膜血管细分对于诊断眼科疾病至关重要.
深度学习在使用彩色底部图像进行细分方面表现出色,但对扫描激光眼镜镜 (SLO) 图像的研究有限.
现有的SLO细分方法难以平衡准确性和模型复杂性.

研究的目的:

提出一个高效和准确的深度学习模型,用于SLO图像中的视网膜血管细分.
为了解决研究的稀缺性和SLO图像分析现有方法的局限性.

主要方法:

开发了MBRNet,一种基于U-Net的轻量级架构,用于SLO图像细分.
整合了一个多尺度瓶残留 (MBR) 模块,以增强接收场并以成本有效的方式保留细节.
使用注意力门 (AG) 模块专注于血管特征并减少噪音干扰.

主要成果:

与现有方法相比,MBRNet在两个公共SLO数据集上表现出优异的细分性能.
拟议的模型通过显著减少参数数量来实现更高的准确性.
MBR模块有效地扩大了受体场,而AG模块则改善了对相关血管结构的关注.

结论:

在SLO图像中,MBRNet为视网膜血管细分提供了一种有效的解决方案,其性能优于目前的方法.
该模型的轻量级设计和提高的准确性使其成为眼科疾病诊断的有希望的工具.
这项研究有助于推进眼科SLO图像分析的深度学习应用.