Scholarlink

Early melanoma detection is critical in managing skin cancer effectively and preventing its progression. Recent advancements in deep convolutional neural networks (CNNs) have shown promising results in automated skin cancer classification, approaching the accuracy of dermatologists. However, barriers such as high computational costs, the need for specialized hardware, and complex implementation processes have limited their integration into clinical settings. This study explores the use of AlexNet CNN and SqueezeNet as lightweight, accessible, and reproducible models for detecting skin cancer from lesion images. These models achieve an accuracy of 85.2% and 87.9%, respectively, while maintaining low computational requirements. Integrating such AI-driven tools could enhance diagnostic capabilities, potentially improving patient outcomes by enabling timely intervention.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Skin Cancer Detection Through Skin Mole Analysis with MATLAB—Retrained AlexNet and SqueezeNet Convolutional Neuronal Networks

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • Anthony Anrango-Méndez,
  • Dayana Murillo-Guanuchy,
  • Isaac Arias-Serrano,
  • Fernando Villalba-Meneses,
  • Andrés Tirado-Espín,
  • Carolina Cadena-Morejón,
  • Paulina Vizcaíno-Imacaña,
  • Kevin R. Landázuri,
  • Diego Almeida-Galárraga

摘要

Early melanoma detection is critical in managing skin cancer effectively and preventing its progression. Recent advancements in deep convolutional neural networks (CNNs) have shown promising results in automated skin cancer classification, approaching the accuracy of dermatologists. However, barriers such as high computational costs, the need for specialized hardware, and complex implementation processes have limited their integration into clinical settings. This study explores the use of AlexNet CNN and SqueezeNet as lightweight, accessible, and reproducible models for detecting skin cancer from lesion images. These models achieve an accuracy of 85.2% and 87.9%, respectively, while maintaining low computational requirements. Integrating such AI-driven tools could enhance diagnostic capabilities, potentially improving patient outcomes by enabling timely intervention.