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

Bimekizumab efficacy and safety reaffirmed in Chinese patients, with notable safety findings.

Journal of the European Academy of Dermatology and Venereology : JEADV·2026
Same author

Deletion of Mixed Lineage Kinase Domain Like Pseudokinase Aggravates Chronic Alcohol-Induced Liver Injury via Increasing Apoptosis.

Digestive diseases and sciences·2024
Same author

Human papillomavirus detection rates in Bowen disease: correlation with pelvic and digital region involvement and specific p53 immunostaining patterns.

Clinical and experimental dermatology·2024
Same author

Successful Long-Term Multimodality Management of Facial Lesions in Tuberous Sclerosis Complex in an Adult Patient.

Annals of dermatology·2023
Same author

Psoriasis severity classification based on adaptive multi-scale features for multi-severity disease.

Scientific reports·2023
Same author

Ultrasonographic analysis of facial skin thickness in relation to age, site, sex, and body mass index.

Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging (ISSI)·2023

相关实验视频

Updated: Jun 28, 2025

Resolving Water, Proteins, and Lipids from In Vivo Confocal Raman Spectra of Stratum Corneum through a Chemometric Approach
09:32

Resolving Water, Proteins, and Lipids from In Vivo Confocal Raman Spectra of Stratum Corneum through a Chemometric Approach

Published on: September 26, 2019

7.2K

基于参数的转移学习用于使用高光谱成像对亚托皮炎的严重程度进行分类.

Eun Bin Kim1, Yoo Sang Baek2, Onesok Lee1,3

  • 1Department of Software Convergence, Graduate School, Soonchunhyang University, Asan City, Chungcheongnam-do, South Korea.

Skin research and technology : official journal of International Society for Bioengineering and the Skin (ISBS) [and] International Society for Digital Imaging of Skin (ISDIS) [and] International Society for Skin Imaging (ISSI)
|April 17, 2024
PubMed
概括

超光谱成像 (HSI) 有效地使用转移学习对亚托皮炎 (AD) 严重程度进行分类. 在牛皮数据上的训练模型取得了高准确性,证明了HSI.

关键词:
亚托邦性皮肤炎的发生.域名选择 域名选择超光谱成像技术的使用.严重性分类的严重性分类.转移学习转移学习

更多相关视频

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.8K

相关实验视频

Last Updated: Jun 28, 2025

Resolving Water, Proteins, and Lipids from In Vivo Confocal Raman Spectra of Stratum Corneum through a Chemometric Approach
09:32

Resolving Water, Proteins, and Lipids from In Vivo Confocal Raman Spectra of Stratum Corneum through a Chemometric Approach

Published on: September 26, 2019

7.2K
Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters
07:05

Applying Hyperspectral Reflectance Imaging to Investigate the Palettes and the Techniques of Painters

Published on: June 18, 2021

2.4K
Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging
06:08

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

16.8K

科学领域:

  • 皮肤病学 皮肤病学
  • 医疗成像医学成像
  • 机器学习 机器学习

背景情况:

  • 亚托皮炎 (AD) 是一种具有结构变化的慢性炎症性皮肤疾病.
  • 需要使用非侵入性方法来评估AD.
  • 超光谱成像 (HSI) 使用光波长变化捕捉皮肤结构特征.

研究的目的:

  • 使用高光谱成像 (HSI) 来分类亚托皮炎 (AD) 的严重程度.
  • 通过基于参数的转移学习来探索不同的源和目标域数据集来优化分类结果.

主要方法:

  • 使用了牛皮,皮肤癌,湿疹和AD数据集作为源域.
  • 采用超光谱图像作为波长特定AD分类的目标域.
  • 评估了96种来源,模型和严重性分类性能目标的组合.

主要成果:

  • 使用ResNet50训练在增强型牛皮数据集 (来源) 和NIR数据集 (目标) 上实现了83%的分类性能.
  • 使用ResNet50训练在未增强的牛皮数据集 (来源) 和R数据集 (目标) 上获得了81%的准确性.
  • ResNet50显示出作为一个通用模型的潜力,而牛皮数据集被证明是有效的培训.

结论:

  • 使用高光谱图像证明了使用AD严重程度分类的可行性.
  • 展示了高光谱成像和转移学习在AD研究领域探索的可扩展性.