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

3.0K
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...
3.0K

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

Deep exploration and precise identification of key risk factors for diabetic peripheral neuropathy using the random forest algorithm.

Frontiers in endocrinology·2026
Same author

MDMU-Net: 3D multi-dimensional decoupled multi-scale U-Net for pancreatic cancer segmentation.

PeerJ. Computer science·2025
Same author

Prediction analysis of human brucellosis cases in Ili Kazakh Autonomous Prefecture Xinjiang China based on time series.

Scientific reports·2025
Same author

Computer-aided diagnosis of hepatic cystic echinococcosis based on deep transfer learning features from ultrasound images.

Scientific reports·2025
Same author

Development and external validation of a predictive model for type 2 diabetic retinopathy.

Scientific reports·2024
Same author

Training and External Validation of a Predict Nomogram for Type 2 Diabetic Peripheral Neuropathy.

Diagnostics (Basel, Switzerland)·2023

相关实验视频

Updated: May 27, 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

454

一个基于多尺度组合高效道注意模块的皮肤疾病分类模型.

Hui Liu1, Yibo Dou2, Kai Wang3

  • 1College of Medical Engineering and Technology, Xinjiang Medical University, Urumqi City, 830017, Xinjiang Uygur Autonomous Region, China.

Scientific reports
|February 19, 2025
PubMed
概括

这项研究引入了一个深度学习模型,用于使用多尺度道注意力对皮肤疾病进行分类. 这种新方法显著提高了关键数据集的诊断准确性,有助于临床决策.

更多相关视频

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K
Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.2K

相关实验视频

Last Updated: May 27, 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

454
Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances
07:35

Selecting Multiple Biomarker Subsets with Similarly Effective Binary Classification Performances

Published on: October 11, 2018

7.4K
Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition
09:37

Combining Reflectance Confocal Microscopy with Optical Coherence Tomography for Noninvasive Diagnosis of Skin Cancers via Image Acquisition

Published on: August 18, 2022

2.2K

科学领域:

  • 皮肤病学和医学成像学
  • 医疗保健中的人工智能
  • 计算机视觉 计算机视觉

背景情况:

  • 皮肤疾病的诊断是具有挑战性的,往往导致高误诊率.
  • 准确的皮肤疾病分类对于有效的临床治疗至关重要.
  • 深度学习为改善皮肤病学诊断准确度提供了一个有希望的途径.

研究的目的:

  • 开发和验证一种用于皮肤疾病分类的新型深度学习模型.
  • 增强多尺度特征提取,以改善图像分析.
  • 在已建立的皮肤学数据集上评估模型的性能.

主要方法:

  • 设计了一个深度学习模型,该模型包含了一个多级别的道注意力机制.
  • 该架构具有改进的金字塔细分关注模块,用于全面的特征提取.
  • 在骨干网络中采用了反向剩余结构和集成的注意力模块.

主要成果:

  • 该模型在ISIC2019皮肤病数据集上实现了77.6%的准确性.
  • 该模型在HAM10000皮肤病数据集上显示了88.2%的准确性.
  • 外部验证证实了该模型的有效性和稳定性.

结论:

  • 拟议的多级道注意力深度学习模型显示了对精确皮肤疾病分类的巨大潜力.
  • 该模型在ISIC2019和HAM10000数据集上的性能验证了其临床实用性.
  • 这种方法可以帮助临床医生减少误诊率并改善患者护理.