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

Survival Tree01:19

Survival Tree

73
Survival trees are a non-parametric method used in survival analysis to model the relationship between a set of covariates and the time until an event of interest occurs, often referred to as the "time-to-event" or "survival time." This method is particularly useful when dealing with censored data, where the event has not occurred for some individuals by the end of the study period, or when the exact time of the event is unknown.
 Building a Survival Tree
Constructing a...
73

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

Geographic access as a modifiable determinant of cancer care: perspectives on hub-and-spoke oncology networks, travel burden and time toxicity.

Clinical & translational oncology : official publication of the Federation of Spanish Oncology Societies and of the National Cancer Institute of Mexico·2026
Same author

Hemopericardium Due to Atrioventricular Disruption After Mitral Valve Replacement With Nonemergent Left Ventricular Pseudoaneurysm Repair.

Annals of thoracic surgery short reports·2026
Same author

A Randomized, Phase II Clinical Trial of FLT-PET and FDG-PET for Early Response Assessment of Neoadjuvant Systemic Therapy in Triple Negative Breast Cancer.

Clinical cancer research : an official journal of the American Association for Cancer Research·2026
Same author

In silico modelling of changes in spinal cord blood flow after endovascular aortic aneurysm repair.

Computer methods and programs in biomedicine·2026
Same author

Development and User-Centered Evaluation of Smart Systems for Loneliness Monitoring in Older Adults: Mixed Methods Study.

Journal of medical Internet research·2026
Same author

The role of multimodality imaging in selection, response assessment, and follow-up of patients receiving <sup>177</sup>Lutetium-PSMA-therapy.

Insights into imaging·2026

相关实验视频

Updated: Jun 14, 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

从异常训练数据中自主监督异常检测,通过代潜伏令牌掩盖.

Ashay Patel1, Petru-Daniel Tudosiu1, Walter H L Pinaya1

  • 1King's College London.

... IEEE International Conference on Computer Vision workshops. IEEE International Conference on Computer Vision
|August 29, 2024
PubMed
概括

本研究介绍了Iterative Latent Token Masking,这是一种用于异常检测的新型自我监督框架. 它可以在具有异常图像的数据集上训练模型,优于计算机视觉和医学成像中的现有方法.

更多相关视频

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

523
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 14, 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
Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness
03:14

Augmenting Large Language Models via Vector Embeddings to Improve Domain-Specific Responsiveness

Published on: December 6, 2024

523
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:

  • 计算机视觉 计算机视觉
  • 机器学习 机器学习
  • 医学成像分析 医学成像分析

背景情况:

  • 异常检测在各种领域至关重要,包括医学成像和工业质量控制.
  • 当训练数据中存在异常时,现有的无监督方法通常会失败,这是医学成像中的一个常见问题.
  • 当前最先进的模型在自主监督培训期间,即使是很小比例的异常数据也很难处理.

研究的目的:

  • 提出一种自我监督的异常检测框架,能够对具有异常图像的数据集进行训练.
  • 克服当前无监督和自我监督的异常检测方法的局限性,当面对受污染的训练数据时.
  • 适应强大的统计学原理,特别是M估计器,用于反复模型适应异常检测.

主要方法:

  • 引入了代潜伏令牌掩盖,这是一个自我监督的框架,利用变压器和矢量量化变量自动编码器.
  • 利用变形金刚的令牌掩盖功能,在训练集中代过异常令牌.
  • 适应的代模型与来自强大的统计数据的M估计器相匹配,用于无监督异常检测.

主要成果:

  • 在全身PET数据和MVTec数据集上表现出高于最先进的模型的性能.
  • 展示了框架在训练集中不同级别异常数据的有效性.
  • 强调了当前自我监督,自我训练和无监督模型的局限性,这些模型具有异常的训练数据.

结论:

  • 代潜伏令牌掩盖有效地解决了在受污染的数据集上训练异常检测模型的挑战.
  • 拟议的方法为无监督异常检测提供了一个强大的替代方案,特别是在不可避免异常的场景中.
  • 这种方法显示出在医学成像和计算机视觉应用中推进异常检测的巨大潜力.