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{193742,
        author = {H  Teja and C Manasa and A Lekhana Sai and Bagirannagari Anil and Polagangu Bharath Narasimha Rao},
        title = {Nail Disease Detection using Convolutional Neural Networks : A Promising approach for Dermatology},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {12},
        number = {10},
        pages = {1685-1693},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=193742},
        abstract = {The aim of this study is to use Deep Learning (DL) techniques to classify and detect human nail diseases. Early and reliable detection is crucial in aiding timely interventions and suitable treatment for nail diseases and their profound impact on a person’s well-being. Using a diverse dataset of nail images, a CNN model was developed and trained to achieve the study’s objectives. For the model to be able to accurately detect and classify different diseases, the dataset was carefully collected to include various types of nail diseases. In order to improve the model’s performance and robustness, the nail images were preprocessed (that includes image normalization, resizing, and noise reduction) and data augmentation techniques (such as rotation, flipping, and rescaling) were applied to overcome dataset limitations and variations in image orientation and lighting conditions. The model’s assessment encompassed 6 distinct nail diseases named as Clubbing, Pitting, Healthy nail, blue finger, onychogryphosis and Acral Lentiginous melanoma resulting in an impressive accuracy rate. The proposed CNN architecture automatically extracts discriminative features through multiple convolutional and pooling layers, followed by fully connected layers for multi-class classification. The dataset was divided into training and testing sets to ensure proper evaluation of the model. Additional evaluation metrics such as precision, recall, and F1-score were also computed, yielding values of 99.22%, 98.44%, and 99.02% respectively. This study emphasizes the potential benefits of DL techniques in enhancing healthcare practices, enhancing dermatological diagnostics, and improving the overall well-being of patients suffering from nail diseases.},
        keywords = {Nail Disease, Deep Learning, Nail abnormalities, Computer-aided diagnosis, Dermatology, Medical imaging, Convolutional Neural Networks (CNN)},
        month = {March},
        }