Monkeypox Disease Diagnosis using Machine Learning Approach
Ajay Gairola, Vidit Kumar
Abstract
A public health crisis has been declared due to the rapid spread of monkeypox in more than 90 nations. Early-stage monkeypox is hard to identify since it looks the same as chickenpox and measles. If confirmatory Polymerase Chain Reaction (PCR) tests are not readily available, computer-assisted detection of monkeypox lesions could be useful for surveillance and early identification of suspected cases. Applications of machine learning to image-based diagnostics, such as those used to detect cancer, tumors, and COVID-19, have shown significant gains in recent years. So, a similar technique might be used to detect monkeypox-related illness in the diagnosis process. Given this, we present a machine learning-based method for analyzing RGB images for signs of monkey pox. For this study, we used one open-source dataset. For this study, we employed 3 convolutional neural network (CNN) models and 6 machine learning classifiers (MLCs). In this work, our main contributions. First, we examine the performance of pre-trained CNN features that use a variety of MLCs. And finally, a fusion-based strategy is presented to further improve the accuracy of the diagnosis.