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

Distinct Chemical Profiles and Gut Microbiota Modulation of Ancha Tea Compared with Green and Black Teas from the Same Cultivar.

Journal of agricultural and food chemistry·2026

Same author

[Research progress on intervention of active components of Bupleuri Radix in metabolic dysfunction-associated fatty liver disease based on multiple parallel strike theory].

Zhongguo Zhong yao za zhi = Zhongguo zhongyao zazhi = China journal of Chinese materia medica·2026

Same author

Nature's nano-shield: plant-based essential oil nano-emulsions as potent defenders against microbial invaders and skin wounds.

Chinese journal of natural medicines·2026

Same author

Butyrate Ameliorates ISO-Induced Cardiac and Intestinal Injury in Rats via Modulation of Bitter Taste Receptors (Tas2rs) and GPR41/43 to Inhibit NLRP3 Activation.

Nutrients·2026

Same author

Research Advances of Neuroregulatory Effects of Dietary Polyphenols on Obesity Complications.

Nutrients·2026

Same author

Construction of a Prognostic Risk Model for Helicobacter pylori Infection in Gastric Cancer Patients and Immunological Analysis.

Cancer reports (Hoboken, N.J.)·2026

Search research articles

相关实验视频

Updated: May 6, 2026

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

MSPDD-net:Mamba语义感知双解码网络用于视网膜图像血管细分.

Daxiang Li¹, Miao Su², Ying Liu¹

¹School of Telecommunication and Information Engineering, Xi'an University of Posts and Telecommunications, Xi'an, 710121, China; Research Center for Wireless Communication and Information Processing Technology of Shaanxi Province, Xi'an, 710121, China.

Computers in biology and medicine

|May 20, 2025

概括

本研究介绍了Mamba语义感知双解码网络 (MSPDD-Net),以提高视网膜图像血管细分的准确性. 这种新型网络有效地捕捉了全球上下文和边缘特征,在公共数据集上实现了高细分性能.

关键词:

马姆巴·马姆巴是什么意思医疗图像细分医疗图像细分视网膜图像容器视网膜图像容器波形边缘的注意力注意力

更多相关视频

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

相关实验视频

Last Updated: May 6, 2026

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

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

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:

准确的视网膜图像血管细分对于诊断眼睛疾病至关重要.
视网膜图像中的低对比度毛细血管对现有的细分方法构成重大挑战,导致精度降低.

研究的目的:

通过建模全球上下文信息和挖掘边缘特征,提高视网膜图像血管 (RIV) 分段的准确性.
引入一个新的深度学习网络,即Mamba语义感知双解码网络 (MSPDD-Net),以改善RIV细分.

主要方法:

为特征提取开发了一种具有位置敏感交叉层交互 (PSCLI) 策略的双编码路径.
一个Mamba全尺度语义感知 (M-FSSP) 模块被集成到瓶中,以捕获全面的语义特征.
设计了一种结合全尺度语义注入 (FSSI) 和波纹边缘注意 (WEA) 的双解码路径,以完善细分和突出显示容器边缘.

主要成果:

在MSPDD-Net实现高细分精度的97.45% (驱动),97.76% (STARE) 和97.88% (CHASEDB1).
与基线方法相比,该网络在STARE数据集上显示出显著的1.59%的改进.
实验结果证实了拟议网络在应对低对比度毛细血管所带来的挑战方面的有效性.

结论:

该MSPDD-Net提供了一个有效的解决方案,用于准确的视网膜图像血管细分.
整合基于Mamba的模块和注意力机制显著改善了对上下文和边缘信息的建模.
拟议的网络显示了眼科临床应用的巨大潜力.