Copyright © 2026 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{174536,
        author = {Y.Durga Bhavani and S.Palavelli and B.Venkata Praveen Kumar and P.Sai Kiran and Ch.Prudhvi Raj},
        title = {Classification of melanoma detection using XceptionNet,DenseNet121 and VGG16},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {300-305},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=174536},
        abstract = {Melanoma is a type of skin cancer that originates in melanocytes, the cells responsible for producing pigment (melanin) in the skin. It is one of the most aggressive forms of skin cancer and has a high potential to metastasize, making early detection crucial for improving patient survival rates. If detected and treated early, melanoma is highly curable, but once it spreads to other organs, the prognosis becomes significantly worse.Traditional methods of diagnosing melanoma involve clinical evaluation by a dermatologist, who visually inspects suspicious skin lesions and may conduct a biopsy to confirm the diagnosis. However, these methods can be subjective, relying heavily on the experience of the clinician, and they may not always catch melanomas in their early stages. Consequently, there is a growing need for automated melanoma detection systems that can assist dermatologists by providing more objective, reliable, and faster analyses of skin lesions. For Melanoma detection using XceptionNet, DenseNet121 and VGG-16 are employed as feature extractors, capturing intricate patterns and features from skin lesion images. Transfer learning techniques are utilized to fine-tune the pretrained models on the melanoma dataset, enhancing classification performance. Extensive experimentation and evaluation on benchmark datasets demonstrate the superior performance of the proposed approach compared to traditional methods and standalone CNN architectures. These models are employed as feature extractors, capturing intricate patterns and features from skin lesion images. This project for melanoma detection using XceptionNet, DenseNet121 and VGG-16 introduces a novel deep learning-based approach aimed at improving the accuracy and efficiency of melanoma classification.},
        keywords = {Deep learning XceptionNet, DenseNet121, VGG16, Machine Learning},
        month = {March},
        }