An Efficient Technique for Classifying Multiple Skin Diseases Using Convolutional Neural Networks
Summary
No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.
Summarise with VIRAT Free to try with your Science Catalogs account.Abstract
Monkeypox (Mpox) virus infection along with other viral and malign skin diseases is still posing formidable challenges in terms of their visually similar characteristics and class imbalance in clinical data sets. Proper classification of such diseases is considered equally importantin order to take early actions towards rapid interventions to achieve good results in clinical settings. The proposed work utilizes the framework of Dense Convolutional Neural Network (DCNN) to implement multi-class classification of clinical dermoscopy images of human skin to properly classify such diseases. The proposed methodology uses image normalization, image resizing, along with Random Over-sampling to cure class imbalance problems in clinical data sets. A proposed deep CNN model is trained to compete against other renowned transfer learning methodologies such as VGG16, VGG19, DenseNet121, DenseNet201, along with MobileNetV2 to measure their proficiency using accuracy, recall, precision, F1 measure, specificity, along with area under Curve (AUC). The proposed model delivers out-and-out results in terms of attaining accuracy of 98.5% along with AUC of 99.92%, outshining all other contemporaries in this field utilizing similar data sets.
Fields of Study & Subjects
Cutaneous Melanoma Detection and Management
AI in cancer detection
Advanced Neural Network Applications
Publication details
- Journal / source
- International Conference on Power Electronics & IoT Applications in Renewable Energy and its Control (PARC)
- Pages
- 8–14
- Publication date
- 20 February 2026
- Language
- EN