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

相关实验视频

Updated: Jan 13, 2026

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

2.5K

一个可解释的混合深度学习框架,用于精确的皮肤病变细分和多类分类.

Muhammad Fiaz1,2, Muhammad Bilal Shoaib Khan1, Abdul Hannan Khan1

  • 1Department of Computer Science, Green International University, Lahore, Pakistan.

Frontiers in medicine
|October 29, 2025
PubMed
概括

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

Intelligent predictive neural network analysis on two phase bioconvection flow of dusty hybrid nanofluid with Cattaneo Christov flux model and melting phenomena.

Discover nano·2026
Same author

Secure task offloading framework for industrial edge computing using reconfigurable intelligent surfaces and spectrum agility.

Scientific reports·2026
Same author

Correction: Technical advances in robotic retinal surgery: a systematic review and future research directions.

Journal of robotic surgery·2026
Same author

Machine learning surface plasmon resonance biosensor for simultaneous detection of glucose and Plasmodium falciparum biomarkers.

Analytical biochemistry·2026
Same author

Joint UAV trajectory and offloading optimization with robust secrecy for intelligent mining.

Scientific reports·2026
Same author

A blockchain-assisted secure federated learning architecture for intrusion detection in internet of things networks.

Scientific reports·2026
Same journal

Family cohesion and adaptability in heart failure: an APIMeM analysis of symptom perception and spousal caregiving on patient self-care.

Frontiers in medicine·2026
Same journal

Prognostic factors analysis of surgical resection after conversion therapy for isolated pleural metastatic lung cancer: a retrospective analysis.

Frontiers in medicine·2026
Same journal

Case Report: a novel non-canonical splice site variant in COL4A5 in a patient with Alport syndrome.

Frontiers in medicine·2026
Same journal

Minimally invasive percutaneous cannulated screw fixation for pelvic fractures: a retrospective case cohort study of clinical and radiological outcomes.

Frontiers in medicine·2026
Same journal

A case analysis of Gitelman syndrome complicated with Sjögren's disease.

Frontiers in medicine·2026
Same journal

Inflammatory phenotyping by latent class analysis and machine learning-based prediction of postoperative complications in pediatric appendicitis: a retrospective cohort study.

Frontiers in medicine·2026
查看所有相关文章
此摘要是机器生成的。

本研究引入了一种混合深度学习模型,用于从皮肤镜图像中对皮肤病变进行细分和分类. 人工智能工具实现了高精度,帮助皮肤科医生诊断皮肤疾病.

科学领域:

  • 皮肤病学 皮肤病学
  • 人工智能的人工智能
  • 医疗成像医学成像

背景情况:

  • 皮肤疾病的诊断是具有挑战性的,因为视觉复杂性和主观的手动检查.
  • 像黑色素瘤这样的恶性瘤需要准确和及时的诊断.
  • 深度学习为客观和准确的皮肤病变分析提供了潜力.

研究的目的:

  • 开发一种混合深度学习框架,同时对皮肤病变进行细分和多类分类.
  • 使用可解释AI (XAI) 增强模型解释性和临床信任.
  • 用皮肤镜图像来提高各种皮肤病的诊断准确度.

主要方法:

  • 开发了一个双任务架构,将U-Net用于细分和EfficientNet-B0用于分类.
  • 梯度加权类激活映射 (Grad-CAM) 为模型的可解释性而集成.
  • 该模型在HAM10000数据集上进行了训练和验证.

主要成果:

  • 该模型在细分方面实现了0.85以上的Dice系数.
  • 分类准确度达到了大约85%,显示出强大的性能.
  • 在各种皮肤病变类型中获得了可靠的结果,尽管存在阶级不平衡.
关键词:
这是Grad-CAM.这是分类分类的分类.可以解释的人工智能AI细分化 细分化的细分化皮肤疾病 皮肤疾病

更多相关视频

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

3.3K

相关实验视频

Last Updated: Jan 13, 2026

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

2.5K
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

3.3K

结论:

  • 混合深度学习模型显示了对准确的皮肤病变细分和分类的重大前景.
  • 可解释性AI (XAI) 集成提高了透明度,这对于临床采用至关重要.
  • 这种方法可以通过提高诊断效率和准确性来支持皮肤科医生,特别是在资源有限的环境中.