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

Decoding the association between microorganisms and autoimmunity: a multifaceted review of evidence on specific pathogens that trigger autoimmune diseases.

Clinical and experimental medicine·2026

Same author

Lung cancer multimodal auxiliary diagnosis based on entropy weight decision fusion.

Biomedical engineering online·2026

Same author

From Exploration to Production: A Systematic Review of Natural Gas Hydrate Technologies.

ACS omega·2026

Same author

Preliminary study on symptoms and signs of patients with laryngopharyngeal reflux disease infected with <i>Helicobacter pylori</i>.

Experimental and therapeutic medicine·2026

Same author

DUSP26: Unveiling a critical molecular mediator and therapeutic target in developmental dysplasia of the hip‑associated secondary osteoarthritis.

International journal of molecular medicine·2026

Same author

The impact of type 1 diabetes mellitus on intellectual status: A Mendelian randomization study.

Journal of education and health promotion·2026

Search research articles

相关实验视频

Updated: May 31, 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

基于频率域的半监督医疗图像细分意识到稳定的一致性规范化

Yihao Ouyang^1,2, Peipei Li^3,4, Haixiang Zhang^5,6

¹Key Laboratory of Knowledge Engineering with Big Data (the Ministry of Education of China), Hefei University of Technology, Hefei, 230009, Anhui, China.

Journal of imaging informatics in medicine

|January 22, 2025

概括

此摘要是机器生成的。

本研究引入了一种新的半监督医疗图像细分方法,使用频域信息进行稳定的一致性规范化. 它通过结合编码器监督和利用图像频率来增强模型训练,克服人工干扰的局限性.

关键词:

一致性规范化规范化频率域是一个频率域.医疗图像细分医疗图像细分半监督半监督半监督半监督半监督

更多相关视频

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

相关实验视频

Last Updated: May 31, 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

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping

Published on: September 25, 2019

科学领域:

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

背景情况:

半监督学习对于医疗图像细分至关重要,因为注释数据有限.
一致性规范化方法可以改善训练,但经常使用人工扰动,引入偏差.
现有的方法忽视了编码器阶段监督和空间频率信息,阻碍了初始学习和整体性能.

研究的目的:

提出一种新的半监督医疗图像细分方法.
为了解决当前方法中人工干扰和编码器监督缺乏限制的问题.
利用固有的空间频率信息进行更稳定,更有效的模型训练.

主要方法:

开发了一种频域意识稳定一致性规范化技术.
使用固有的图像频率组件 (高和低) 作为一致性约束,避免人工干扰.
在编码器阶段内置监督,以在训练期间保持功能空间完整性.

主要成果:

拟议的方法有效地克服了人工扰动引入的偏差.
编码器监督确保了强大的初始特征学习,防止混乱的学习阶段.
实验验证证证实了频域意识方法在半监督医疗图像细分方面的有效性.

结论:

频域意识稳定一致性规范化为半监督医疗图像细分提供了一个有希望的方向.
整合编码器监督和利用内在图像属性可以提高模型的稳定性和准确性.
这种方法为传统的一致性规范化方法提供了更稳定,更少偏差的替代方案.