Enhancing Melanoma Diagnostic: Harnessing the Synergy of AI and CNNs for Groundbreaking Advances in Early Melanoma Detection and Treatment Strategies

Sajid, Muhammad, Khan, Ali Haider, Malik, Tauqeer Safdar, Bilal, Anas ORCID: https://orcid.org/0000-0002-7760-3374, Ahmad, Zohaib and Sarwar, Raheem ORCID: https://orcid.org/0000-0002-0640-807X (2025) Enhancing Melanoma Diagnostic: Harnessing the Synergy of AI and CNNs for Groundbreaking Advances in Early Melanoma Detection and Treatment Strategies. International Journal of Imaging Systems and Technology, 35 (1). e70016. ISSN 0899-9457

Preview

Published Version Available under License Creative Commons Attribution. Download (2MB) | Preview

Abstract

Skin cancer is one of the most prevalent and deadly neoplasms globally. Although melanoma constitutes a minor percentage of all skin cancer types, it presently stands as the primary cause of skin cancer‐related deaths. Previous studies indicate that deep learning algorithms may identify subtle patterns and detailed features in medical images for melanoma detection, however, challenges remain due to the scarcity of annotated images and the intricacy of cancer images. The need for early skin cancer detection, particularly melanoma, is an urgent concern due to its potential for high mortality when not identified and treated promptly. This paper introduces a comprehensive method for melanoma detection in medical images through the incorporation of data augmentation approaches. We employed a CNN model for the categorization of melanoma images with data augmentation techniques such as random horizontal flips, random cropping, grayscale conversion, Gaussian blur, and random perspective transformations. Experiments demonstrate that the suggested method surpasses the existing peak performance in melanoma identification within medical imaging. The results indicate the potential of data augmentation techniques in alleviating the issue of insufficient medical images and improving melanoma detection. We attained an overall accuracy of 93.43%, a sensitivity of 99.74%, and a specificity of 88.53% in melanoma detection, surpassing state‐of‐the‐art approaches with the HAM10000 dataset. Our model is beneficial in clinical settings to aid dermatologists in precisely identifying patients, facilitating early intervention, and potentially preserving lives. In the future, we intend to test our algorithm on more skin cancer datasets that may enhance the accuracy of melanoma diagnosis. A crucial component of the design is the ablation study, which seeks to discover and improve the most significant model parameters for computational efficiency and diagnostic precision. The HAM10000 dataset is utilized for ablation tests to assess and validate the efficacy of the suggested method.