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

Predictors of Repeat Nondiagnostic Cytology in Thyroid Fine-Needle Aspiration.

Canadian Association of Radiologists journal = Journal l'Association canadienne des radiologistes·2026
Same author

Evaluating data heterogeneity's impact on convolutional neural network performance in medical imaging.

International journal of computer assisted radiology and surgery·2026
Same author

Cognitively Biased Prompt Effects on Large Language Model Accuracy for Radiology Board-style Examination Questions.

Radiology. Artificial intelligence·2026
Same author

Deep learning for pediatric synovial recess distension detection in hemophilia: synthetic image augmentation with styleGAN2-ADA.

International journal of computer assisted radiology and surgery·2026
Same author

Evaluating the impact of sex bias on AI models in musculoskeletal ultrasound of joint recess distension.

PloS one·2025
Same author

Promising initial evaluation: the Shock Thyroid Imaging Score (STIS) could predict mortality in hemodynamically unstable trauma patients.

Emergency radiology·2025

相关实验视频

Updated: Jun 23, 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

使用扩散模型生成用于医疗图像细分的合成标记数据.

Daniel G Saragih1, Atsuhiro Hibi1,2, Pascal N Tyrrell3,4,5

  • 1Department of Medical Imaging, University of Toronto, 263 McCaul Street, Toronto, M5T 1W7, ON, Canada.

International journal of computer assisted radiology and surgery
|June 20, 2024
PubMed
概括

由新型管道产生的合成多形象改善了医疗图像细分模型. 这种方法解决了数据稀缺问题,提高了模型性能,减少了机器学习任务的注释需求.

关键词:
数据增强数据增强扩散模型的扩散模型.机器学习是机器学习.多片的图像生成.

更多相关视频

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K

相关实验视频

Last Updated: Jun 23, 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
A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment
10:39

A Label-Free Segmentation Approach for Intravital Imaging of Mammary Tumor Microenvironment

Published on: May 24, 2022

2.3K
From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data
12:08

From Voxels to Knowledge: A Practical Guide to the Segmentation of Complex Electron Microscopy 3D-Data

Published on: August 13, 2014

24.6K

科学领域:

  • 医学成像医学成像
  • 机器学习是机器学习.
  • 计算机视觉 计算机视觉 计算机视觉

背景情况:

  • 机器学习越来越多地应用于医学图像分析.
  • 由于隐私和成本限制,高质量的注释医疗数据的有限可用性阻碍了进展.
  • 合成数据生成为医疗AI中的数据稀缺提供了潜在的解决方案.

研究的目的:

  • 设计和评估一条用于生成合成标记多形象的管道.
  • 增强医疗图像细分模型并解决数据稀缺问题.
  • 减少对人工注释的依赖,以训练机器学习模型.

主要方法:

  • 扩散模型被训练在胃肠片图像的HyperKvasir数据集上.
  • 产生的图像使用定性专家审查,弗雷切开始距离 (FID) 和多尺度结构相似性 (MS-SSIM) 进行了评估.
  • 分段模型使用合成数据进行训练,并使用Dice Score (DS) 和Intersection over Union (IoU) 来评估.

主要成果:

  • 管道生成了与真实图像相似的合成聚图像,如FID分数所示.
  • 使用合成数据训练的细分模型比生成对抗网络 (GAN) 方法表现更好.
  • 即使在对合成数据进行部分培训时,也观察到性能增长,并且证明了跨数据集的可转移性.

结论:

  • 开发的管道有效地产生现实的合成图像-面具对,用于医疗成像任务.
  • 合成数据生成方法可以显著减少对手动数据注释的需求.
  • 完全或部分基于生成的合成数据的培训细分模型提高了性能,Dice和IoU得分证明了这一点.