Scholarlink

Melanoma skin cancer early detection is a time-consuming and challenging process. In this study, we proposed a fully automated segmentation and classification method using convolutional neural networks (CNNs). On images from the International Skin Imaging Collaboration (ISIC) archive, the segmentation performance using DeepLab V3+ in terms of mean Intersection Over Union was 94%, while the suggested technique of classification using Renet50 achieved 98% accuracy and F1 Score.

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

Automated Skin Cancer Segmentation and Classification Based on Deep Learning

  • 会议论文

  • 发表日期：

    2025年

查看全文
  • Noor Ul Ain,
  • Faisal Bukhari,
  • Waheed Iqbal

摘要

Melanoma skin cancer early detection is a time-consuming and challenging process. In this study, we proposed a fully automated segmentation and classification method using convolutional neural networks (CNNs). On images from the International Skin Imaging Collaboration (ISIC) archive, the segmentation performance using DeepLab V3+ in terms of mean Intersection Over Union was 94%, while the suggested technique of classification using Renet50 achieved 98% accuracy and F1 Score.