Scholarlink

<p>Skin cancer is a major worldwide health concern, emphasizing the importance of early and precise detection to enhance patient outcomes. Accurate identification of skin lesions is essential in determining effective treatment strategies and increasing the probability of survival. While dermoscopic imaging aids in diagnosing dermatological conditions, its interpretation can be subjective and error-prone. This study introduces a deep learning-based approach that combines Convolutional Neural Networks (CNNs) and Vision Transformers with Explainable AI (XAI) techniques to enhance both classification accuracy and interpretability. Utilizing datasets such as HAM10000, ISIC 2017, and ISIC 2018, the model demonstrates strong performance in distinguishing various skin lesion types. The integration of Grad-CAM++ improves decision transparency, allowing clinicians to assess AI-driven predictions better. This approach strengthens diagnostic reliability and fosters greater trust in AI-assisted medical decision-making.</p>

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

A comprehensive deep learning approach for skin cancer diagnosis: integrating interpretability and advanced techniques

  • 期刊论文

  • 发表日期：

    2025年5月2日

查看全文
  • Asha S,
  • Sreeraj R,
  • Sindhya K Nambiar,
  • Aswathy K Cherian

摘要

Skin cancer is a major worldwide health concern, emphasizing the importance of early and precise detection to enhance patient outcomes. Accurate identification of skin lesions is essential in determining effective treatment strategies and increasing the probability of survival. While dermoscopic imaging aids in diagnosing dermatological conditions, its interpretation can be subjective and error-prone. This study introduces a deep learning-based approach that combines Convolutional Neural Networks (CNNs) and Vision Transformers with Explainable AI (XAI) techniques to enhance both classification accuracy and interpretability. Utilizing datasets such as HAM10000, ISIC 2017, and ISIC 2018, the model demonstrates strong performance in distinguishing various skin lesion types. The integration of Grad-CAM++ improves decision transparency, allowing clinicians to assess AI-driven predictions better. This approach strengthens diagnostic reliability and fosters greater trust in AI-assisted medical decision-making.