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

Liquid biopsy, multi-cancer early detection, and artificial intelligence: new frontiers in cancer screening from a technological and immunological perspective.

Frontiers in immunology·2026
Same author

Research Progress of SGLT2 Inhibitors in the Treatment of Acute Heart Failure: A Narrative Review.

International journal of general medicine·2026
Same author

Waste coconut shell-derived nitrogen-doped porous carbon synergized with Bi<sub>2</sub>MoO<sub>6</sub> for sensitive detection of marbofloxacin in complex matrices.

Mikrochimica acta·2026
Same author

Unsupervised Anomaly Detection in Medical Imaging: A Survey of Methods, Challenges, and Future Directions.

Bioengineering (Basel, Switzerland)·2026
Same author

Exploratory gut microbiota-host interaction in parkinson's disease: integrative multi-omics analysis of metabolic and epigenetic pathways.

AMB Express·2026
Same author

The Combined Predictive Value of the GRACE Score and the ARC-HBR Criteria for Bleeding Risk After Percutaneous Coronary Intervention in STEMI Patients.

International journal of general medicine·2026

相关实验视频

Updated: Jul 12, 2025

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

你需要精确的细节吗? 询问MMDC-Net:用于视网膜血管细分的多层多尺度扩展卷积网络.

Xiang Zhong1, Hongbin Zhang1, Guangli Li2

  • 1School of Software, East China Jiaotong University, China.

Computers in biology and medicine
|October 20, 2023
PubMed
概括

本研究介绍了MMDC-Net,这是一种用于增强视网膜血管细分的新型深度学习模型. 它有效地解决了全球信息捕获和阶级不平衡问题,提高了基金图像的准确性和细节性.

关键词:
多层聚变聚变是多层的.多个尺度扩展卷积.召回损失 召回损失视网膜血管细分 视网膜血管细分挤压和激发的情况.在U-net中,U-net是指U-net网络.

更多相关视频

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

565
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

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

Published on: March 12, 2022

3.6K

相关实验视频

Last Updated: Jul 12, 2025

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
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

565
Quantification of Vascular Parameters in Whole Mount Retinas of Mice with Non-Proliferative and Proliferative Retinopathies
12:28

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

Published on: March 12, 2022

3.6K

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 深度学习 (Deep Learning) 是一种深度学习.

背景情况:

  • 卷积神经网络 (CNN),特别是U形结构,具有先进的视网膜血管细分.
  • 现有的方法往往无法充分利用基底图像中的全球信息,并与背景和血管之间的阶级不平衡作斗争.

研究的目的:

  • 开发一种新的深度学习模型,MMDC-Net,通过解决全球信息捕获和阶级失衡的局限性来改善视网膜血管细分.
  • 为了提高血脉底图像中血管识别的准确性和细节性.

主要方法:

  • 基于U-Net架构设计了一个多层多尺度扩展卷积网络 (MMDC-Net).
  • 整合了一个MMDC模块,通过级联方法在各种受体领域捕获全球信息.
  • 引入了多层融合 (MLF) 模块,以集成补充功能和过噪声后解码器.
  • 使用召回损失函数来缓解类失衡问题.

主要成果:

  • 在多个基底图像数据集 (STARE,CHASEDB1,DRIVE,HRF) 的定性和定量评估中,MMDC-Net表现出卓越的表现.
  • 该模型实现了令人满意的准确性和灵敏性,提高了血管的关键细节.
  • 实验验证了MMDC-Net在不同分辨率的数据集上的有效性和概括能力.

结论:

  • MMDC-Net有效地捕获全球信息并处理类不平衡,从而改善视网膜血管细分.
  • 拟议的MMDC和MLF模块增强了特征表示和细节保存.
  • MMDC-Net为医学成像中准确的视网膜血管细分提供了强大的和可通用的解决方案.