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

Corrigendum to "4D Flow cardiovascular magnetic resonance consensus statement: 2023 update" [Journal of Cardiovascular Magnetic Resonance 25 (2023) 40].

Journal of cardiovascular magnetic resonance : official journal of the Society for Cardiovascular Magnetic Resonance·2026
Same author

AUTOMATED MEASUREMENTS OF MITRAL AND TRICUSPID ANNULAR DIMENSIONS IN CARDIOVASCULAR MAGNETIC RESONANCE.

Proceedings. IEEE International Symposium on Biomedical Imaging·2026
Same author

TVnet: Automated Time-Resolved Tracking of the Tricuspid Valve Plane in MRI Long-Axis Cine Images with a Dual-Stage Deep Learning Pipeline.

Medical image computing and computer-assisted intervention : MICCAI ... International Conference on Medical Image Computing and Computer-Assisted Intervention·2026
Same author

Atrioventricular area difference assessed by exercise cardiovascular magnetic resonance shows impaired diastolic filling in patients with heart failure.

Journal of applied physiology (Bethesda, Md. : 1985)·2026
Same author

Retrospectively synchronized time-resolved ventricular cine images from 2D real-time exercise cardiac magnetic resonance imaging.

Clinical physiology and functional imaging·2025
Same author

Neural networks with personalized training for improved MOLLI T<sub>1</sub> mapping.

BMC medical imaging·2025

相关实验视频

Updated: Jun 18, 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

训练期间的随机效应:对基于深度学习的医疗图像细分的影响.

Julius Åkesson1, Johannes Töger1, Einar Heiberg2

  • 1Clinical Physiology, Department of Clinical Sciences Lund, Lund University, Lund, Sweden; Department of Biomedical Engineering, Faculty of Engineering, Lund University, Lund, Sweden.

Computers in biology and medicine
|August 3, 2024
PubMed
概括

训练期间的随机变化在深度学习细分模型中产生了显著的性能差异. 统计学意义是同一算法的模型之间的真实性能差异的不可靠指标.

关键词:
深度学习是一种深度学习.医疗图像细分 医疗图像细分性能比较 性能比较随机种子 随机种子随机性是一种随机性.

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

380
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 18, 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

380
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:

  • 医疗图像分析 医学图像分析
  • 深度学习是一种深度学习.
  • 计算神经科学是一种计算神经科学.

背景情况:

  • 图像细分的深度学习模型由于随机训练效应而表现出性能变化.
  • 这种变化可能会影响标准模型比较方法的可靠性.

研究的目的:

  • 评估随机培训对比较深度学习细分模型可靠性的影响.
  • 评估常用统计方法在检测真实绩效差异方面的有效性.

主要方法:

  • 利用nnU-Net与50个随机种子在三个3D医学图像细分任务 (脑瘤,海马,心脏).
  • 通过保留验证和5倍交叉验证评估细分性能.
  • 员工配对t测试和威尔科克森签名的等级测试对子得分来衡量统计学意义.

主要成果:

  • 性能最好的种子显著超过其他具有保留验证的种子的0-76%.
  • 经过5倍的交叉验证,顶级种子的表现超过其他种子的10-38%.
  • 在使用相同算法训练的模型之间观察到高比例的统计学显著差异.

结论:

  • 随机训练效应可以导致频繁的统计学上显著的绩效差异.
  • 统计学意义是同一个深度学习算法的模型之间真正的性能优越性的弱而不可靠的指标.