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

Genome-wide Association Studies-GWAS01:11

Genome-wide Association Studies-GWAS

13.5K
Genome-wide association studies or GWAS are used to identify whether common SNPs are associated with certain diseases. Suppose specific SNPs are more frequently observed in individuals with a particular disease than those without the disease. In that case, those SNPs are said to be associated with the disease. Chi-square analysis is performed to check the probability of the allele likely to be associated with the disease.
GWAS does not require the identification of the target gene involved in...
13.5K

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

MR Imaging of the Upper Urinary Tract: Techniques, Diagnostic Performance, and Imaging Biomarkers.

Magnetic resonance in medical sciences : MRMS : an official journal of Japan Society of Magnetic Resonance in Medicine·2026
Same author

The Asian Oceanian Society of Radiology (AOSR) green radiology survey: a catalyst for action.

Japanese journal of radiology·2025
Same author

Future Applications of Cardiothoracic CT.

Radiology·2025
Same author

Advances in Concept and Imaging of Interstitial Lung Disease.

Radiology·2025
Same author

Better Data and Smarter AI: Automated Quality Control for Chest Radiographs.

Radiology. Artificial intelligence·2025
Same author

Framework for Environmentally Sustainable Radiology: Call for Collaborative Action and a Health-Centered Focus.

Radiology·2025

相关实验视频

Updated: Jul 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

564

高质量的半监督异常检测与生成对抗网络的高质量半监督异常检测.

Yuki Sato1, Junya Sato2,3, Noriyuki Tomiyama3

  • 1Systems and Information Engineering Master's Program in Computer Science, University of Tsukuba, 1-1-1 Tenoudai, Tsukuba City, Ibaraki, 305-0821, Japan. s2220599@u.tsukuba.ac.jp.

International journal of computer assisted radiology and surgery
|November 9, 2023
PubMed
概括

这项研究介绍了高质量异常GAN (HQ-AnoGAN),一种用于异常检测的新方法. HQ-AnoGAN在检测异常方面实现了高精度,并提供了清晰的可视化,特别有利于医学成像分析.

关键词:
异常检测检测异常检测胸部X射线 胸部X射线没有了,没有了,没有了.半监督学习 半监督学习

更多相关视频

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.1K

相关实验视频

Last Updated: Jul 11, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

564
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K
Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches
09:47

Author Spotlight: Advancing Alzheimer's Research – Exploring Early Detection and Multi-Omics Approaches

Published on: December 15, 2023

1.1K

科学领域:

  • 人工智能的人工智能
  • 计算机视觉 计算机视觉
  • 医疗成像医学成像

背景情况:

  • 使用生成模型的异常检测方法提供更容易的可视化,但难以准确.
  • 分类模型在准确可视化检测到的异常方面面临着挑战.
  • 生成对抗网络 (GANs) 为结合精度和可视化提供了一个潜在的解决方案.

研究的目的:

  • 开发一种方法,将异常检测准确度和异常区域的清晰可视化结合起来.
  • 利用生成对抗网络 (GANs) 来改进异常检测和可视化.
  • 建立一个强大的方法来识别和呈现数据中的异常.

主要方法:

  • 使用了带有自适应区分器增强的StyleGAN2 (StyleGAN2-ADA),用于生成高质量的图像.
  • 使用像素到样式到像素 (pSp) 编码器将图像转换为中间隐藏变量.
  • 提出了一种使用这些隐性变量的新型异常得分计算方法,称为高质量异常GAN (HQ-AnoGAN).

主要成果:

  • 与现有方法相比,HQ-AnoGAN在三个数据集中显示出同等或更高的异常检测准确度.
  • 使用HQ-AnoGAN对异常区域的可视化比使用现有方法的可视化更准确和自然.
  • 该方法成功地产生了高分辨率,高质量的图像,即使在有限的数据集.

结论:

  • HQ-AnoGAN有效地将高异常检测准确度与异常区域的清晰可视化相结合.
  • 拟议的方法整合了StyleGAN2-ADA和pSp编码器,为医学成像诊断提供了显著的潜力.
  • HQ-AnoGAN解决了在医疗应用中需要清晰的异常解释的可解释AI的需求.