Monkeypox Disease Detection From Skin Images Using Deep Learning

Abstract

Monkeypox is a viral zoonotic disease that presents with skin lesions similar to other dermatological conditions such as chickenpox, measles, and smallpox, making early and accurate diagnosis challenging. Delayed diagnosis can lead to disease spread and complications, highlighting the need for automated and reliable detection systems. This study proposes a deep learning–based approach for the detection of monkeypox from skin lesion images using convolutional neural networks (CNNs). Skin image datasets are collected and preprocessed through resizing, normalization, and augmentation to improve model generalization and reduce overfitting. Pre-trained deep learning models such as VGG16, VGG19, MobileNetV2, and ResNet50 are utilized through transfer learning to improve classification performance with limited medical image data. The models are trained to classify images into monkeypox and non-monkeypox categories. Performance evaluation is conducted using metrics such as accuracy, precision, recall, F1-score, and confusion matrix. Experimental results demonstrate that deep learning models, particularly transfer learning architectures, achieve high classification accuracy and can effectively assist in early monkeypox detection. The proposed system can support healthcare professionals by providing a fast, cost-effective, and automated diagnostic tool for preliminary screening and outbreak control..