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{171524,
        author = {Dhanush and Aqib Ameer and Dheeraj and Sanath Kumar and MS. Prema Jain},
        title = {SKIN CANCER DETECTION USING DEEP LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {8},
        pages = {526-530},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=171524},
        abstract = {Skin cancer is one of the most common and potentially life-threatening conditions. Effective intervention can be produced with early and accurate detection. Traditional methods have always depended on expert dermatological evaluation, which may be subjective and resource-constrained. In the last few years, medical imaging diagnostics have changed their face with deep learning techniques, which are unprecedentedly precise and scalable. This works focuses on designing a state-of-the-art deep learning framework for the skin cancer detection system using high-quality convolutional neural networks and transfer learning methods. The approach proposed in this paper gets thoroughly trained and validated against large, annotated datasets to guarantee its robustness in varying demographics and phenotypic profiles. Advanced data augmentation strategies coupled with fine-tuning hyperparameters allow the model to gain better generalizability and avoid overfitting. Our results emphasize the superiority of deep learning over traditional approaches to reach diagnostic accuracy, especially by attaining better metrics of sensitivity, specificity, and area under the ROC curve. In addition, the present paper emphasizes issues in ethical considerations, computational complexity, and practical deployment challenges in real clinical scenarios using AI-driven diagnosis. The results of this study thus pave the way for more accessible, reliable, and automated solutions to skin cancer screening, which leads to improved patient outcomes and diminished health disparities.},
        keywords = {Skin Cancer Classification, , F1-score, Real-world applicability, Transfer learning, Convolutional Neural Network, Data augmentation, Accuracy, Precision, Recall, Scalability, Fine-tuned, Model generalize.},
        month = {January},
        }