PoxNet22: A Fine-Tuned Model for the Classification of Monkeypox Disease Using Transfer Learning

Amidst the ongoing COVID-19 pandemic, the emergence of a monkeypox outbreak poses a significant public health concern. Leveraging deep learning methodologies, particularly the PoxNet22 model, originally based on Modified InceptionV3, has shown promise in monkeypox diagnosis with high precision, recall, and accuracy. However, in this study, we sought to further enhance diagnostic capabilities by exploring detection techniques using YOLOv5 and YOLOv8 architectures. Our analysis revealed that these models achieved exceptional performance in detecting monkeypox, complementing the classification capabilities of existing models. By integrating detection techniques alongside classification, we can significantly improve the efficiency and accuracy of monkeypox diagnosis, facilitating prompt intervention and containment efforts. These findings hold significant implications for public health, offering a comprehensive approach to monkeypox outbreak management amidst the challenges posed by concurrent infectious disease epidemics. Through the fusion of deep learning and image processing techniques, we provide a robust framework for rapid and accurate monkeypox diagnosis, ultimately aiding in mitigating the spread of this infectious disease.