Jove
Visualize
联系我们

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

TCRBinder: Unified pre-trained language model with paired-chain synergy for predicting T-cell receptor binding specificity.

PLoS computational biology·2026
Same author

Adaptive feature unlearning for trustworthy medical imaging privacy.

Medical image analysis·2026
Same author

Deep learning-based Breast Imaging Reporting and Data System classification and establishment of diagnostic model in breast cancer diagnosis with automated breast ultrasound.

Quantitative imaging in medicine and surgery·2026
Same author

Anatomy-Guided Spatiotemporal Affinity Learning for Unsupervised Domain Adaptation in Echocardiography Segmentation.

IEEE journal of biomedical and health informatics·2026
Same author

Performance Evaluation of SmartBrain: A Wearable PET System for Human Brain Imaging.

Journal of nuclear medicine : official publication, Society of Nuclear Medicine·2026
Same author

CT-based AI system for quantitative and integrated management of acute respiratory distress syndrome in critical care.

NPJ digital medicine·2026
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

相关实验视频

Updated: Sep 17, 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

3.0K

为域连续医疗图像细分进行因果性调整的数据增量.

Zhanshi Zhu, Qing Dong, Gongning Luo

    IEEE journal of biomedical and health informatics
    |June 27, 2025
    PubMed
    概括

    因果调整数据增强 (CauAug) 减少了持续医疗图像细分中的偏差. 这一框架改善了模型的概括和知识的保留,优于现有的方法.

    科学领域:

    • 医学图像分析 医学图像分析
    • 计算机视觉 计算机视觉
    • 机器学习 机器学习

    背景情况:

    • 基于蒸的方法在域内持续医疗图像细分的目的是防止灾难性的遗忘.
    • 由于混因素,现有的方法往往会对新旧知识产生偏见,影响细分性能.

    研究的目的:

    • 引入一个新的框架,因果调整数据增强 (CauAug),以减轻域内持续医疗图像细分方面的偏差.
    • 改善在持续学习过程中的模型概括和知识保留.

    主要方法:

    • 提出了因果调整数据增量 (CauAug) 框架.
    • 引入了因果干预的纹理域调整混合方案 (TDAHS).
    • 开发了两种以因果关系为目标的数据增强方法:交叉内核网络 (CKNet) 和富里埃变压器生成器 (FTGen).

    主要成果:

    • CauAug有效地识别和解决由无关的局部纹理 (L) 和域特定特征 (D) 引起的知识偏差.
    • CKNet减少了对局部纹理的依赖,加强了对解剖结构的关注,并改善了概括性.
    • FTGen恢复了特定领域的特征,有助于全面提炼旧知识.
    • 实验结果表明,灾难性遗忘的显著缓解和优越的性能比现有方法.

    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

    529
    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
    14:08

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

    Published on: April 13, 2013

    42.8K

    相关实验视频

    Last Updated: Sep 17, 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

    3.0K
    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
    04:48

    Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

    Published on: July 5, 2024

    529
    Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
    14:08

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

    Published on: April 13, 2013

    42.8K

    结论:

    • CauAug框架通过解决固有的知识偏差,为域持续医学图像细分提供了强大的解决方案.
    • CauAug通过提高概括性和有效地保存旧知识来提高模型性能.
    • 提出的方法,TDAHS,CKNet和FTGen,有助于推进医学图像细分中的因果推理.