Skin Disease Detection and Classification of Actinic Keratosis and Psoriasis Utilizing Deep Transfer Learning

TL;DR

This paper presents a deep transfer learning approach using a modified VGG16 CNN model for accurate classification of skin diseases like Actinic Keratosis and Psoriasis, achieving over 90% accuracy with data augmentation techniques.

Contribution

The study introduces a novel application of a modified VGG16 model with data augmentation for skin disease classification, demonstrating high accuracy and potential for practical use.

Findings

Achieved 90.67% classification accuracy.

Utilized data augmentation techniques such as rotation, shifting, and zooming.

Validated the effectiveness of transfer learning in dermatological diagnosis.

Abstract

Skin diseases can arise from infections, allergies, genetic factors, autoimmune disorders, hormonal imbalances, or environmental triggers such as sun damage and pollution. Some skin diseases, such as Actinic Keratosis and Psoriasis, can be fatal if not treated in time. Early identification is crucial, but the diagnostic methods for these conditions are often expensive and not widely accessible. In this study, we propose a novel and efficient method for diagnosing skin diseases using deep learning techniques. This approach employs a modified VGG16 Convolutional Neural Network (CNN) model. The model includes several convolutional layers and utilizes ImageNet weights with modified top layers. The top layer is updated with fully connected layers and a final softmax activation layer to classify skin diseases. The dataset used, titled "Skin Disease Dataset," is publicly available. While the VGG16 architecture does not include data augmentation by default, preprocessing techniques such as rotation, shifting, and zooming were applied to augment the data prior to model training. The proposed methodology achieved 90.67% accuracy using the modified VGG16 model, demonstrating its reliability in classifying skin diseases. The promising results highlight the potential of this approach for real-world applications.