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{195777,
        author = {Korapaka Kavya and Neelakantam Rohith and Guppi Sandeep and Meesala Tharun Naidu and Dr. B. V. A. Swamy},
        title = {Real Time Detection Of Skin Cancer Using CNN},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {11},
        pages = {773-776},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=195777},
        abstract = {Skin cancer and dermatological disorders constitute a growing global health concern due to their high prevalence and potential severity. Timely and accurate diagnosis remains challenging, particularly in regions where specialist access is limited. This paper presents Dermal AI, an intelligent web-based platform integrating deep learning image classification with generative conversational AI for automated skin disease analysis and personalized guidance. The system employs a DenseNet-based Convolutional Neural Network (CNN) trained on a HAM10000-derived dataset spanning nine clinically significant skin conditions melanoma, basal cell carcinoma, squamous cell carcinoma, actinic keratosis, nevus, dermatofibroma, seborrheic keratosis, pigmented benign keratosis, and vascular lesions. The model achieves 99.53% classification accuracy with precision, recall, and F1-score values of 0.9953, and a Cohen's Kappa of 0.9948, substantially surpassing existing approaches. An Ollama-powered large language model (LLM) chatbot provides context-aware guidance on symptoms, skincare, diet, and medication. Implemented using the Flask framework, the system delivers real-time image analysis and interactive dermatological support in a user-friendly interface.},
        keywords = {skin disease classification, DenseNet, deep learning, conversational AI, dermatological guidance, HAM10000},
        month = {April},
        }