Search research articles

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 Journal Methods Collections JoVE Encyclopedia of Experiments 存档

教育

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual 教师资源中心教师网站

使用条款与条件

相关概念视频

Skin Cancer

Skin Cancer

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...

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

Transport of enzymatic activity across liquid-liquid interfaces using dynamic assemblies of magnetic particles via field-modulated interactions.

Nature communications·2026

Same author

A portable modular acoustic streaming vortex platform for flexible and robust fabrication of monodisperse micromaterials.

Lab on a chip·2026

Same author

Diffusion Model-Based Design of Bionic Bone Scaffolds with Tunable Microstructures.

Annals of biomedical engineering·2025

Same author

Lego-Inspired Splicing of Modularized Vascular Channels.

Small methods·2025

Same author

Converting a probe-based fluorescence system into an easy-to-use adjunct for the detection of parathyroid glands accidentally resected intraoperatively.

Langenbeck's archives of surgery·2023

Same author

Preparation of Anisotropic Micro-Hydrogels with Tunable Structural and Topographic Features by Compound Interfacial Shearing.

ACS applied materials & interfaces·2021

Search research articles

相关实验视频

Updated: Jul 13, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

基于深度学习的皮肤损伤分类的低成本高性能数据增强.

Shuwei Shen^1,2, Mengjuan Xu³, Fan Zhang³

¹First Affiliated Hospital, University of Science and Technology of China, Hefei 230031, China.

|October 18, 2023

概括

此摘要是机器生成的。

一种新的,低成本的数据增强策略提高了AI皮肤癌查准确度,改善了服务不足地区的早期检测. 这种plug-and-play方法优化了各种医疗应用的性能,降低了计算成本.

更多相关视频

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Enhancing Skin Model Diversity with Cost-Effective 3D Cellular Models

Author Spotlight: Enhancing Skin Model Diversity with Cost-Effective 3D Cellular Models

Published on: October 20, 2023

相关实验视频

Last Updated: Jul 13, 2025

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Quantitative Visualization and Detection of Skin Cancer Using Dynamic Thermal Imaging

Published on: May 5, 2011

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

Author Spotlight: Enhancing Skin Model Diversity with Cost-Effective 3D Cellular Models

Author Spotlight: Enhancing Skin Model Diversity with Cost-Effective 3D Cellular Models

Published on: October 20, 2023

科学领域:

人工智能在医学中的应用
医学成像分析医学成像分析
计算皮肤病学计算皮肤病学

背景情况:

智能皮肤癌查需要高性能,低成本的数据增强,特别是在农村部署.
当前的方法在资源有限的环境中可能不高效或难以使用.

研究的目的:

开发一种高性能,低成本的数据增强战略,用于基于人工智能的皮肤癌查.
改善分类性能,并突出显示临床医生感兴趣的区域.
为了在缺乏资源的环境中能够对各种疾病进行早期查和诊断.

主要方法:

建议采用一个plug-and-play数据增强策略,搜索空间为10^1.
该策略使用EfficientNets作为医疗数据库的基线进行了测试.
使用Grad-CAM++生成热图以实现模型可解释性.

主要成果:

在HAM10000上实现了0.853的最佳BACC,优于现有的单模型方法.
在ISIC 2017上获得了0.909的平均AUC,超过了组合和外部数据库模型.
在Derm7pt上达到0.735的最佳BACC,超过了所有相关研究. 格拉德-CAM++热图证实了精确的特征选择.

结论:

拟议的数据增强策略显著降低了智能皮肤病变诊断的计算成本.
这种方法支持开发具有成本效益的便携式人工智能设备,用于皮肤癌查和治疗指导.
该策略在各种临床环境中对早期疾病查和诊断具有广泛的适用性.