Monkeypox Detection Using Hyper-Parameter Tuned Based Transferable CNN Model

Abstract

The reemergence of Monkeypox, a communicable illness resulting from the Monkeypox virus, has raised apprehensions about a potential swift global pandemic similar to the COVID-19 epidemic as COVID-19 infections diminish globally. The prompt emphasizes the criticality of prompt action within communities to mitigate the development of the phenomenon. The timely identification and accurate categorization of Monkeypox cutaneous manifestations are crucial for the successful implementation of containment strategies. This paper presents a novel methodology for detecting Monkeypox by utilizing a transferrable Convolutional Neural Network (CNN) model that has been optimized utilizing hyper-parameter tuning techniques. The proposed methodology initiates by improving the quality of the original Monkeypox images, with a specific emphasis on boosting edge details to increase visual clarity. Texture qualities are obtained through an energy layer, enhancing distinctive traits. Our methodology's cornerstone is utilizing the Hyper-parameter-based transferable Convolutional Neural Network (HPT-TCNN), specifically designed to enhance classification accuracy.
 In contrast to traditional methods, we enhance the architectural design by replacing the pooling layer with a configuration comprising three convolutional layers and one energy layer. The hyper-parameter tuning procedure is optimized by employing the Optimisation Algorithm known as MGS-ROA. In order to enhance the process of model training and validation, we have assembled the "Monkeypox Skin Lesion Dataset (MSLD)," which consists of a collection of images depicting human skin lesions produced by Monkeypox. The dataset in question is vital in evaluating and improving our methodology. In a comparison analysis conducted on other deep learning models, the suggested model has superior performance compared to other models, obtaining a notable accuracy, sensitivity, and specificity, all reaching a value of 93.60%. The outstanding performance shown in this study highlights the methodology's effectiveness in adequately classifying skin lesions associated with Monkeypox. This approach shows potential for physicians and healthcare workers since it facilitates early detection, a crucial factor in preventing the spread of Monkeypox.