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

Generative Principal Component Regression via Variational Inference.

IEEE transactions on signal processing : a publication of the IEEE Signal Processing Society·2026
Same author

A widespread internal brain state for fentanyl withdrawal.

bioRxiv : the preprint server for biology·2026
Same author

The NERVE-ML (neural engineering reproducibility and validity essentials for machine learning) checklist: ensuring machine learning advances neural engineering<sup></sup>.

Journal of neural engineering·2025
Same author

Genomic Signatures of Adaptation to Stress Reveal Shared Evolutionary Trends Between Tetrahymena utriculariae and Its Algal Endosymbiont, Micractinium tetrahymenae.

Molecular biology and evolution·2025
Same author

Model selection to achieve reproducible associations between resting state EEG features and autism.

Scientific reports·2024
Same author

A widespread electrical brain network encodes anxiety in health and depressive states.

bioRxiv : the preprint server for biology·2024

相关实验视频

Updated: Jun 13, 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

2.7K

通过自我监督的变异自编码器进行高效的少数镜头医疗图像细分.

Yanjie Zhou1, Feng Zhou1, Fengjun Xi2

  • 1School of Artificial Intelligence, Beijing University of Posts and Telecommunications, Beijing, 100876, China.

Medical image analysis
|May 31, 2025
PubMed
概括

通过数据增强和自我监督学习,EFS-MedSeg改善了少数镜头医疗图像细分. 这种新的方法提高了准确性和稳定性,实现了与完全监督的方法可比的性能.

关键词:
有几次射击学习学习.图像重建 图像重建医疗图像细分 医疗图像细分变量自动编码器变量自动编码器

更多相关视频

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

378
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

相关实验视频

Last Updated: Jun 13, 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

2.7K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

378
Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application
05:56

Objectification of Tongue Diagnosis in Traditional Medicine, Data Analysis, and Study Application

Published on: April 14, 2023

2.4K

科学领域:

  • 医疗成像医学成像
  • 计算机视觉 计算机视觉
  • 机器学习 机器学习

背景情况:

  • 少数拍摄的医疗图像细分通常采用联合注册和细分模型.
  • 登记中的空间错位可能会损害细分的准确性和质量.

研究的目的:

  • 开发一个端到端的模型,EFS-MedSeg,用于增强少数镜头医疗图像细分.
  • 用数据增强和自我监督学习来解决注册错位导致的不准确性.

主要方法:

  • EFS-MedSeg使用了两个有标签的地图集和一些没有标签的图像.
  • 采用3D随机区域切换策略来增强地图库,以提高概括性和防止过度拟合.
  • 包含一个变化自编码器用于加权重建和一个自我对比模块,用于以解剖学先验为指导的特征提取.

主要成果:

  • 在多模式医疗图像数据集上,EFS-MedSeg的性能与完全监督的方法相美.
  • 超过第二最佳方法的1.4% (OASIS),9.1% (BCV) 和1.1% (BCH).
  • 突出了各种医学成像数据集的稳定性和适应性.

结论:

  • EFS-MedSeg提供了一个强大而准确的解决方案,用于为数次拍摄的医疗图像细分.
  • 该模型在数据增强和自我监督学习方面的改进有助于提高细分精度和边界流性.
  • 该方法显示了在低数据系统中推进医疗图像分析的巨大潜力.