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

Skin Cancer01:30

Skin Cancer

4.1K
Skin cancer is a type of cancer that occurs when there is an abnormal growth of skin cells, usually triggered by damage to the DNA within the skin cells. It is primarily caused by exposure to ultraviolet (UV) radiation from the sun or artificial sources like tanning beds. Skin cancer is the most common type of cancer worldwide, and its incidence continues to rise.
Basal Cell Carcinoma (BCC): BCC is the most common type of skin cancer, accounting for about 80% of cases. It typically develops in...
4.1K

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

Experimental Characterization of a Silicon Nitride Asymmetric Loop-Terminated Mach-Zehnder Interferometer with a Refractive Index-Engineered Sensing Arm.

Nanomaterials (Basel, Switzerland)·2025
Same author

Early-Stage Melanoma Benchmark Dataset.

Cancers·2025
Same author

Demonstration of Directly Nanoimprinted Silica-Titania Large-Size Vertical Grating Couplers for Multichannel Photonic Sensor Development.

Materials (Basel, Switzerland)·2025
Same author

Deep pixel-wise supervision for skin lesion classification.

Computers in biology and medicine·2025
Same author

Investigation of Modal Characteristics of Silicon Nitride Ridge Waveguides for Enhanced Refractive Index Sensing.

Micromachines·2025
Same author

Mid-Infrared Photonic Sensors: Exploring Fundamentals, Advanced Materials, and Cutting-Edge Applications.

Sensors (Basel, Switzerland)·2025

相关实验视频

Updated: Jun 29, 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

通过自我训练改善皮肤损伤细分.

Aleksandra Dzieniszewska1, Piotr Garbat1, Ryszard Piramidowicz1

  • 1Institute of Microelectronics and Optoelectronics, Warsaw University of Technology, 00-662 Warsaw, Poland.

Cancers
|March 28, 2024
PubMed
概括
此摘要是机器生成的。

本研究引入了一种半监督学习方法,用于使用杂学生方法对皮肤病变进行细分. 它在有限的标记数据下显著提高了细分精度,有助于皮肤癌诊断.

关键词:
深度学习是一种深度学习.皮肤显微镜图像 皮肤显微镜图像半监督学习 半监督学习皮肤癌是皮肤癌.皮肤病变细分 皮肤病变细分

更多相关视频

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
Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.8K

相关实验视频

Last Updated: Jun 29, 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
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
Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging
08:40

Quantitation of Protein Expression and Co-localization Using Multiplexed Immuno-histochemical Staining and Multispectral Imaging

Published on: April 8, 2016

12.8K

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:

  • 皮肤病变细分对于准确的皮肤癌诊断至关重要.
  • 高质量的细分需要广泛的标记数据,这是昂贵的和耗时的获取.
  • 半监督学习通过利用未标记的数据来提高模型性能提供了一个解决方案.

研究的目的:

  • 提出一种新的半监督方法,用于皮肤病变细分,使用与杂学生进行自我训练.
  • 为了减少在医疗图像细分中依赖手动注释的数据.
  • 通过改进细分来提高皮肤癌诊断的准确性.

主要方法:

  • 实施了一种半监督的学习框架,利用噪音学生策略.
  • 在教师和学生模型中采用DeepLabV3架构.
  • 利用了包括教师培训,伪标签生成和代学生培训在内的四步过程.

主要成果:

  • 在ISIC 2018数据集上实现了88.0%的欧盟平均交叉点 (mIoU).
  • 在PH2数据集上获得了87.54%的mIoU.
  • 在有限的标记数据下,证明了更好的细分性能.

结论:

  • 提出的Noisy Student培训方法有效地提高了神经网络的性能,用于皮肤病变细分.
  • 这种方法显著减轻了大量手动注释的需要,使其成为医学图像分析的宝贵工具.
  • 这种方法有望提高皮肤癌诊断的准确性和效率.