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

Beyond auto-segmentation: the case for planning and dosimetry AI in head and neck radiation oncology.

BMJ oncology·2026
Same author

LEARNABLE HIERARCHICAL VISUAL CONTEXTS FOR TUMOR SEGMENTATION IN COMPUTED TOMOGRAPHY IMAGES.

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

Tumor-anchored deep feature random forests for out-of-distribution detection in lung cancer segmentation.

Transactions on machine learning research·2026
Same author

MHub.ai: A Standardized Platform for Reproducible AI Research in Medical Imaging.

Research square·2026
Same author

DUAL CROSS-ATTENTION SIAMESE TRANSFORMER FOR RECTAL TUMOR REGROWTH ASSESSMENT IN WATCH-AND-WAIT ENDOSCOPY.

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

Transformer-based cardiac substructure segmentation from contrast and non-contrast computed tomography for radiotherapy planning.

Physics and imaging in radiation oncology·2026

相关实验视频

Updated: Jun 5, 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

自主监督学习提高了深度学习肺瘤细分模型与CT成像差异的稳定性.

Jue Jiang1, Aneesh Rangnekar1, Harini Veeraraghavan1

  • 1Department of Medical Physics, Memorial Sloan Kettering Cancer Center, New York, New York, USA.

Medical physics
|December 5, 2024
PubMed
概括

野生预训练的Swin模型显示,与自我预训练的模型相比,CT扫描对肺癌细分的稳定性有所改善. 像ViT和CNN这样的其他架构没有显示出野生预训练的明显优势.

科学领域:

  • 人工智能的人工智能
  • 医学成像分析 医学成像分析
  • 计算机视觉 计算机视觉

背景情况:

  • 自主监督学习 (SSL) 从未标记的数据中提取功能,用于下游任务.
  • 自主预训练使用精心策划的数据集,用于预训练和微调.
  • 未经精确的公共医疗图像通过"野生"SSL提供了强大的基础模型的潜力.

研究的目的:

  • 在非小细胞肺癌 (NSCLC) 细分方面,比较野生与自我预训练模型 (CNN,ViT,Swin) 的强度.
  • 评估3D计算机断层扫描 (CT) 扫描上的模型.
  • 评估不同预训练策略对模型性能的影响.

主要方法:

  • 野生预训练和自我预训练应用于CNN,ViT和Swin模型,使用未标记和策划的NSCLCCT数据集.
  • 在两种预训练方法中都使用了掩面图像转换器借口任务.
  • 在各种NSCLC数据集上微调和测试模型,评估准确性,对成像变异的稳定性和功能重复使用.

主要成果:

  • 野生预训练的Swin模型表现出更高的功能重复使用,并且表现优于自我预训练的模型.
  • 在ViT和CNN模型中,野生预训练与自我预训练没有显著的益处.
关键词:
计算机断层扫描 (CT) 是一种计算机断层扫描.图像采集的稳定性 图像的稳定性肺癌的细分 肺癌的细分自主监督学习学习

更多相关视频

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.1K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.5K

相关实验视频

Last Updated: Jun 5, 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
Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia
08:05

Lung CT Segmentation to Identify Consolidations and Ground Glass Areas for Quantitative Assesment of SARS-CoV Pneumonia

Published on: December 19, 2020

14.1K
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

8.5K
  • 蒙面图像预测借口任务的准确性高于对比任务.

    • 结论:

    • 野生预训练的Swin网络在肺瘤细分方面表现出优越的稳定性,与CT成像变异相对抗.
    • 与自我预训练相比,ViT和CNN模型没有从野外预训练中获得明显的优势.
    • 架构和预训练策略的选择会影响医疗图像分析的稳定性.