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{176033,
        author = {LALAM MOHANKUMAR and Kanaparthi Lakshmi Saraswathi and Dr. Kondapalli Venkata Ramana},
        title = {SKIN CANCER DETECTION BY USING DEEP LEARNING},
        journal = {International Journal of Innovative Research in Technology},
        year = {2025},
        volume = {11},
        number = {11},
        pages = {4775-4779},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=176033},
        abstract = {Melanoma is a highly aggressive skin cancer, making early and accurate detection crucial for improving patient survival rates. Traditional diagnostic methods require expert dermatologists and can be time-consuming, leading to delayed treatment. Our project proposes an AI-driven classification system for benign and malignant skin lesions using deep learning techniques to enhance diagnostic efficiency. We utilized the Melanoma Skin Cancer Dataset with 10,000 dermoscopic images to train a VGG19-based model, alongside MobileNetV2 for computational efficiency. Both models incorporate pre-trained ImageNet weights and are fine-tuned with Dense, Dropout, and Batch Normalization layers. Bayesian Optimization is used for hyperparameter tuning, optimizing learning rates, dropout rates, and architecture configurations. Our approach improves classification accuracy over traditional methods while maintaining computational efficiency. Implemented with a Flask backend, the system provides real-time predictions via a web-based interface and supports PDF report generation for structured documentation. Experimental results show 95% training accuracy and 92% validation accuracy, ensuring high sensitivity for malignant cases. This low-cost, AI powered solution aids dermatologists in mass screening programs and offers a second opinion for clinical decisions.},
        keywords = {Melanoma, Skin cancer, Deep learning, VGG19, MobileNetV2},
        month = {April},
        }