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{197845,
        author = {Mrs. Muthyala Suryakumari and Vadla Shreeja and Vutturu Goutham and Suraj neemkar and Mojarla Rishi Teja},
        title = {Medical Image Analysis for Skin Cancer and Melanoma Detection Using Deep Learning},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {6883-6889},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=197845},
        abstract = {Skin cancer represents a major global health concern, with melanoma being the most aggressive variant due to its rapid metastasis potential. Early-stage identification is critical for effective treatment; however, conventional diagnostic practices rely heavily on manual examination, which is subjective and dependent on clinical expertise. This study introduces a deep learning-based framework for automated classification of skin lesions using transfer learning. The proposed system employs a modified convolutional neural network architecture derived from ResNet50, complemented with additional regularization and feature refinement layers. Image data is standardized through resizing and normalization, while augmentation strategies are applied to enhance variability and reduce model bias. Instead of training from scratch, the model leverages pre-trained weights to accelerate convergence and improve generalization on limited medical datasets. Experimental evaluation demonstrates that the system achieves classification accuracy exceeding 94%, with consistent performance across validation samples. The model also maintains balanced precision and recall, minimizing diagnostic errors. The developed system provides rapid inference along with confidence estimation, enabling its use as a supportive diagnostic tool. This approach highlights the effectiveness of transfer learning in medical image analysis and offers a scalable solution for assisting early skin cancer detection in clinical environments.},
        keywords = {Skin Lesion Classification, Deep Neural Networks, Transfer Learning, ResNet-Based Model, Medical Imaging AI, Automated Diagnosis, Image Augmentation, CNN Optimization.},
        month = {April},
        }