Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

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

PROBAST+AI: an updated quality, risk of bias, and applicability assessment tool for prediction models using regression or artificial intelligence methods.

BMJ (Clinical research ed.)·2025

Same author

Computer-aided detection and abnormality score for the outer retinal layer in optical coherence tomography.

The British journal of ophthalmology·2021

Same author

New digital models of care in ophthalmology, during and beyond the COVID-19 pandemic.

The British journal of ophthalmology·2021

Same author

Is artificial intelligence a solution to the myopia pandemic?

The British journal of ophthalmology·2021

Same author

Detection of features associated with neovascular age-related macular degeneration in ethnically distinct data sets by an optical coherence tomography: trained deep learning algorithm.

The British journal of ophthalmology·2020

Same author

Generative adversarial networks to predict treatment response for neovascular age-related macular degeneration: interesting, but is it useful?

The British journal of ophthalmology·2020

Search research articles

相关实验视频

Updated: Jul 17, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

医疗图像分类的保护隐私的持续学习方法:比较分析

Tanvi Verma¹, Liyuan Jin^2,3, Jun Zhou¹

¹Institute of High Performance Computing, Agency for Science, Technology and Research (A*STAR), Singapore, Singapore.

Frontiers in medicine

|August 30, 2023

概括

保护隐私的持续学习方法对更新医疗保健中的深度学习模型充满希望,解决绩效下降和隐私问题. 脑启发重播 (BIR) 和高效特征转换 (EFT) 分别在视网膜疾病和结肠癌分类中有效.

关键词:

进行比较分析.持续的学习,持续的学习.医学图像分类医学图像分类模型的部署部署.光学连贯性断层扫描 (optical coherence tomography) 是一种光学连贯性断层扫描技术.

更多相关视频

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

相关实验视频

Last Updated: Jul 17, 2025

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Predicting Treatment Response to Image-Guided Therapies Using Machine Learning: An Example for Trans-Arterial Treatment of Hepatocellular Carcinoma

Published on: October 10, 2018

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

科学领域:

人工智能的人工智能
医疗成像医学成像
计算机科学计算机科学

背景情况:

医疗图像分类的深度学习模型面临着性能下降和适应能力有限等挑战.
频繁的再培训是不可行的,并且由于保留患者数据,引发了隐私问题.

研究的目的:

调查保护隐私的持续学习方法,作为频繁再培训的替代方案.
评估这些方法在医学图像分类任务中的有效性.

主要方法:

使用深度学习模型评估了12个保护隐私的非存储持续学习算法.
从光学连贯断层扫描 (OCT) 图像中分类的视网膜疾病,在一个类增量学习场景中.
测试了结肠癌组织学和CIFAR10数据集的算法,用于概念证明和基准比较.

主要成果:

脑启发重播 (BIR) 实现了从OCT图像进行视网膜疾病分类的最高准确率 (62.00%).
有效特征转换 (EFT) 在结肠癌组织学分类中获得了最高的准确性 (66.82%).
没有持续学习的微调模型表现出灾难性的遗忘,而关节再培训模型表现出卓越的性能.

结论:

持续学习方法在缓解灾难性遗忘和实现持续更新模型方面表现有前途.
这些方法对于在医疗保健深度学习模型中保护隐私至关重要.
保护隐私的持续学习是人工智能模型长期临床部署的有希望的解决方案.