Copyright © 2025 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{182723,
        author = {Devi  B},
        title = {Advanced Deep Learning Technique for Skin Cancer Classification Enhanced by Grad-CAM Visualization},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {12},
        number = {2},
        pages = {3237-3243},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=182723},
        abstract = {Skin cancer, especially melanoma, is a major chal- lenge in medical diagnosis because of its rapid progression and the utmost necessity for early diagnosis. In this research, a new deep learning model for automatic skin cancer classification is proposed with the DenseNet121 architecture coupled with Gradient-weighted Class Activation Mapping (Grad-CAM). The model increases transparency by producing visual explanations that point out important areas in dermoscopic images that affect its predictions, thus agreeing with clinical observations and promoting trust. Employing datasets such as HAM10000 and ISIC, the model includes sophisticated preprocessing methods like artifact removal, data augmentation, and lesion segmentation to deal with class imbalance and improve training. Experimental testing proves that the suggested model is very accurate and explainable and can be used as an important diagnostic tool in dermatology. By addressing at the same time the demand for accuracy and clarity, the suggested model is an important leap toward trustworthy AI-based solutions in skin cancer diagnosis.},
        keywords = {Skin Cancer, Densenet, Grad-CAM, HAM10000},
        month = {July},
        }