Scholarlink

The rising incidence of melanoma and other skin malignancies emphasizes the critical need for accurate and efficient skin cancer detection. This study presents Dermalytics, an advanced deep learning framework utilizing Convolutional Neural Networks (CNNs) such as Xception, DenseNet201, DenseNet169, ResNet50, and VGG16 to enhance skin cancer classification. Through complex data augmentation and image processing techniques, Dermalytics achieves high accuracy rates, distinguishing benign from malignant lesions effectively. The integration of a Flask framework with SQLite/MySQL facilitates seamless user interaction, improving accessibility and usability. This system streamlines skin cancer diagnosis, aiding in early detection and timely treatment, ultimately enhancing patient outcomes and public health.

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

Dermalytics High-Performance CNN Models for Skin Cancer Diagnosis

  • 会议论文

  • 发表日期：

    2026年

查看全文
  • D. Sattibabu,
  • M. Dafia Anjum,
  • M. D. S. Sahithi,
  • A. Ashish Kumar,
  • P. V. S. S. M. Surya Teja

摘要

The rising incidence of melanoma and other skin malignancies emphasizes the critical need for accurate and efficient skin cancer detection. This study presents Dermalytics, an advanced deep learning framework utilizing Convolutional Neural Networks (CNNs) such as Xception, DenseNet201, DenseNet169, ResNet50, and VGG16 to enhance skin cancer classification. Through complex data augmentation and image processing techniques, Dermalytics achieves high accuracy rates, distinguishing benign from malignant lesions effectively. The integration of a Flask framework with SQLite/MySQL facilitates seamless user interaction, improving accessibility and usability. This system streamlines skin cancer diagnosis, aiding in early detection and timely treatment, ultimately enhancing patient outcomes and public health.