Monkeypox Diagnosis With Interpretable Deep Learning

Abstract

As the world gradually recovers from the impacts of COVID-19, the recent global spread of Monkeypox disease has raised concerns about another potential pandemic, highlighting the urgency of early detection and intervention to curb its transmission. Deep Learning (DL)-based disease prediction presents a promising solution, offering affordable and accessible diagnostic services. In this study, we harnessed Transfer Learning (TL) techniques to tweak and assess the performance of an array of six different DL models, encompassing VGG16, InceptionResNetV2, ResNet50, ResNet101, MobileNetV2, VGG19, and Vision Transformer (ViT). Among this diverse collection, it was the modified versions of the VGG19 and MobileNetV2 models that outshone the others, boasting striking accuracy rates ranging from an impressive 93% to an astounding 99%. Our results echo the findings of recent research endeavors that similarly showcase enhanced performance when developing disease diagnostic models armed with the power of TL. To add to this, we used Local Interpretable Model Agnostic Explanations (LIME) to lend a sense of transparency to our model’s predictions and identify the crucial features correlating with the onset of Monkeypox disease. These findings offer significant implications for disease prevention and control efforts, particularly in remote and resource-limited areas.

Keywords

• Deep learning
• monkeypox
• disease diagnosis
• transfer learning
• image processing
• LIME