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

Anti-inflammatory compounds of "Qin-Jiao", the roots of Gentiana dahurica (Gentianaceae).

Journal of ethnopharmacology·2013

Same author

Molecular characterization of prolactin receptor (cPRLR) gene in chickens: gene structure, tissue expression, promoter analysis, and its interaction with chicken prolactin (cPRL) and prolactin-like protein (cPRL-L).

Molecular and cellular endocrinology·2013

Same author

Plasma microRNA, a potential biomarker for acute rejection after liver transplantation.

Transplantation·2013

Same author

Significant coronary stenosis in asymptomatic Chinese with different glycemic status.

Diabetes care·2013

Same author

Impaired lung function is associated with increased carotid intima-media thickness in middle-aged and elderly Chinese.

PloS one·2013

Same author

Genetic determinant for amino acid metabolites and changes in body weight and insulin resistance in response to weight-loss diets: the Preventing Overweight Using Novel Dietary Strategies (POUNDS LOST) trial.

Circulation·2013

Search research articles

相关实验视频

Updated: Jan 11, 2026

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

DuetMatch:通过脱分支优化协调半监督的大脑MRI细分通过脱分支优化.

Thanh-Huy Nguyen¹, Hoang-Thien Nguyen², Vi Vu³

¹Carnegie Mellon University, Pittsburgh, 15213, PA, USA.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society

|November 19, 2025

概括

DuetMatch是一个新的双分支半监督学习框架,通过使用异步优化和新的技术来有效处理有限的注释数据,改善了医疗图像细分.

关键词:

异步优化优化异步优化大脑MRI细分的大脑MRI细分这是一个杂的伪标签.半监督学习半监督学习教师与学生的框架.

更多相关视频

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

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: Jan 11, 2026

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Whole-brain Segmentation and Change-point Analysis of Anatomical Brain MRI—Application in Premanifest Huntington's Disease

Published on: June 9, 2018

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

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
人工智能的人工智能
计算机视觉计算机视觉

背景情况:

医学成像中的有限注释数据需要先进的学习技术.
半监督学习 (SSL) 通过利用不完美标记的数据提供了一个解决方案.
教师-学生框架显示出希望,但在复杂的场景中面临着融合挑战.

研究的目的:

介绍DuetMatch,一个新的双分支SSL框架,用于强大的医疗图像细分.
解决现有的教师-学生模式中的稳定性和融合问题.
为了在有限的注释医学成像数据的情况下提高性能.

主要方法:

提出了DuetMatch,一个具有异步优化 (编码器/解码器分支交替优化) 的双分支框架.
引入了解掉落扰动,以在噪音条件下提高一致性.
实施双向CutMix交叉指导和一致性匹配,以增强多样性和减轻确认偏差.

主要成果:

与最先进的方法相比,DuetMatch在基准大脑MRI细分数据集 (ISLES2022,BraTS) 上表现优越.
该框架在各种SSL细分任务中显示出一致的有效性和稳定性.
异步优化和拟议的规范化技术对于具有挑战性的细分场景证明是有益的.

结论:

杜埃马奇为半监督医疗图像细分提供了强大而有效的解决方案.
这些新技术显著提高了模型的稳定性,多样性和准确性.
该框架显示了应用有限的注释医疗成像数据的巨大潜力.