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

Differentiating effective salvage from ineffective delayed compensation in anterior circulation stroke: a dynamic quantitative collateral index.

Frontiers in medicine·2026
Same author

MRI-based radiomics-deep learning model for preoperative pathogen prediction in perianal abscesses.

Frontiers in medicine·2026
Same author

Multimodal Fusion Network with Information Bottleneck Mamba and Intervention Enhancement for Retinal Disease Diagnosis.

IEEE journal of biomedical and health informatics·2026
Same author

Multimodal Magnetic Resonance Imaging in Diabetic Kidney Disease: From Pathophysiological Insights to Clinical Applications.

Diagnostics (Basel, Switzerland)·2026
Same author

Advanced High-Entropy Biomaterials (HEBs).

Small (Weinheim an der Bergstrasse, Germany)·2026
Same author

Evaluation of cartilaginous endplate degeneration with histogram features of multiple parameters in UTE MRI.

BMC medical imaging·2026

相关实验视频

Updated: Jan 6, 2026

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

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

Published on: September 25, 2019

49.2K

对于急性缺血性中风损伤细分的可靠性意识的半监督互助学习.

Shiwei Hu1, Hongqing Zhu2, Ziying Wang1

  • 1School of Information Science and Engineering, East China University of Science and Technology, Shanghai, 200237, China.

Journal of imaging informatics in medicine
|October 7, 2025
PubMed
概括

可靠性意识的相互学习 (RAML) 通过使用新的规范化技术来改进不可靠的预测,从而改善急性缺血性中风的细分. 这种方法提高了医疗成像中的病变定位精度,即使有有限的标记数据.

关键词:
急性缺血性中风病变细分 细分相互学习的相互学习.伪标签是一种伪标签.意识到可靠性的可靠性半监督学习 半监督学习

更多相关视频

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.8K
Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke
06:45

Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke

Published on: June 2, 2023

2.2K

相关实验视频

Last Updated: Jan 6, 2026

Brain Infarct Segmentation and Registration on MRI or CT for Lesion-symptom Mapping
10:25

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

Published on: September 25, 2019

49.2K
Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly
12:50

Lesion Explorer: A Video-guided, Standardized Protocol for Accurate and Reliable MRI-derived Volumetrics in Alzheimer's Disease and Normal Elderly

Published on: April 14, 2014

40.8K
Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke
06:45

Author Spotlight: Integrated Photoacoustic, Ultrasound, and Angiographic Tomography (PAUSAT) for NonInvasive Whole-Brain Imaging of Ischemic Stroke

Published on: June 2, 2023

2.2K

科学领域:

  • 医学图像分析 医学图像分析
  • 人工智能在医学中的应用
  • 神经学 神经学

背景情况:

  • 精确的病变定位对于急性缺血性中风 (AIS) 治疗至关重要.
  • 由于有限的注释医疗数据集,自动的中风病变细分具有挑战性.
  • 半监督学习 (SSL) 是有希望的,但受到不可靠的伪标签的阻碍.

研究的目的:

  • 提出一个新的半监督学习框架,可靠性意识的相互学习 (RAML),以改善中风损伤细分.
  • 用SSL解决医疗图像分割中不可靠的伪标签的挑战.
  • 提高AIS中自动病变检测的准确性和效率.

主要方法:

  • 开发了RAML,这是一个由两个子网络共享编码器并使用主和辅助解码器的框架.
  • 引入了不确定的区域重新学习 (URR),以使用预测不确定性来改进标记数据中的不可靠区域.
  • 实施了可靠性意识的相互伪监督 (RMPS),用于使用可靠的伪标签对未标记的数据进行交叉监督.
  • 整合特征差异学习 (FDL) 以促进子网络之间的预测多样性.

主要成果:

  • 在两个急性缺血性中风数据集上证明了RAML的有效性.
  • 验证了框架在左心室数据集上的表现,展示了它的多功能性.
  • 与现有的方法相比,RAML显著改善了半监督细分任务.

结论:

  • 拉姆提供了一个强大的解决方案,用于半监督医疗图像细分,特别是AIS.
  • 拟议的规范化技术有效地处理不可靠的伪标签,并提高细分精度.
  • 这一框架有可能通过更精确的中风病变识别来改善临床结果.