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

Search research articles

相关实验视频

Updated: Sep 8, 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

使用双解码器相互教学与平均教师框架进行医学图像细分

Juan Zhang^1,2, Gaoqiang Jiang^1,2, Zhongwen Li³

¹National Engineering Research Center of Ophthalmology and Optometry, Eye Hospital, Wenzhou Medical University, Wenzhou, 325027, China.

Pattern recognition

|August 20, 2025

概括

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

Laser-Based Micro/Nano Additive Manufacturing of Conductive Structures on Transparent Substrates: Technical Approaches, Challenges, and Future Prospects.

Langmuir : the ACS journal of surfaces and colloids·2025

Same author

A deep semi-supervised learning approach to the detection of glaucoma on out-of-distribution retinal fundus image datasets.

BMC ophthalmology·2025

Same author

Adaptive boundary-enhanced Dice loss for image segmentation.

Biomedical signal processing and control·2025

Same author

Parameter Optimization for Laser Peen Forming on 6005A-T6 Aluminum Alloy Plates to Enhance the Constrained Deformation of Integral Stiffened Plates.

Materials (Basel, Switzerland)·2024

Same author

UGLS: an uncertainty guided deep learning strategy for accurate image segmentation.

Frontiers in physiology·2024

Same author

In Situ Synthesis of (M:Nb,Ta)C/Ni35 Composite Coating Cladded on 40Cr Steel.

Materials (Basel, Switzerland)·2021

Same journal

Spatial Coherence Loss: All Objects Matter in Salient and Camouflaged Object Detection.

Pattern recognition·2026

Same journal

LDM-Morph: Latent diffusion model guided deformable image registration.

Pattern recognition·2026

Same journal

Variable Priority for Unsupervised Variable Selection.

Pattern recognition·2026

Same journal

A Deep Spatio-Temporal Architecture for Dynamic ECN Analysis with Granger Causality based Causal Discovery.

Pattern recognition·2025

Same journal

Multi-graph Graph matching for coronary artery semantic labeling in invasive coronary angiograms.

Pattern recognition·2025

Same journal

A graph transformer-based foundation model for brain functional connectivity network.

Pattern recognition·2025

查看所有相关文章

此摘要是机器生成的。

这项研究引入了双解码相互教学 (DDMT),这是一种用于医疗图像细分的新型半监督学习方法. 通过有效使用有限的标记数据和大量的未标记数据,DDMT显著减少了注释工作.

科学领域:

医学图像分析
深度学习
计算机视觉

背景情况:

准确的医学图像细分对于临床应用至关重要.
医疗图像的手动标注需要大量的时间和劳动力.
深度学习模型需要大量的注释数据集以实现最佳性能.

研究的目的:

开发一种新的半监督细分方法,以减少手动注释的费用.
在细分任务中提高深度学习模型的稳定性和形状一致性.
通过有限的标签和大量的无标签图像实现有希望的细分性能.

主要方法:

引入了双解码器相互教学 (DDMT),一种半监督的细分方法.
纳入平滑指数移动平均值 (sEMA),以提高模型的稳定性.
整合形状一致性约束 (SCC) 用于跨解码器的一致形状学习.

主要成果:

在有限的标记数据上,DDMT表现出有前途的细分性能.
这种方法始终优于先进的半监督学习方法.
在左心室,胰腺和视盘数据集上的实验证实了DDMT的有效性.

结论:

关键词:

指数移动平均线图像细分一个坏老师相互教学半监督学习

更多相关视频

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

相关实验视频

Last Updated: Sep 8, 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

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

DDMT提供了一种有效的解决方案,用于减少医疗图像细分中的手动注释.
提出的方法提高了模型的稳定性和形状的一致性.
对于需要精确的图像细分的临床应用,DDMT具有显著的潜力.