Monkeypox Lesion and Rash Stage Classification Using Deep Learning Technique

Timely identification of Monkeypox symptoms stands as a key goal in averting a global pandemic. Furthermore, accurately assessing the disease stage and duration of Monkeypox rashes is imperative. The utilization of deep learning algorithms has become increasingly popular for the efficient diagnosis of diseases through medical imaging. In this research, the classification of Monkeypox lesions and rash stages is suggested through the application of deep learning techniques. The dataset comprises pictures of skin lesions and different stages of rashes. In the experiment, data augmentation methods were utilized to augment the sample size in both the training and testing sets. By employing a MobileNetV2 model, the outcome demonstrated an accuracy of 90.68% for pox and 90.62% for the pox rash stage. This approach aids healthcare professionals in crafting precise treatments tailored to the unique disease stage, offering accurate recommendations based on early-stage rash characteristics for each patient. Furthermore, it improves overall life expectancy by enabling more effective treatment strategies.