Deep and Transfer Learning Approaches for Automated Early Detection of Monkeypox (Mpox) Alongside Other Similar Skin Lesions and Their Classification

Abstract

The world faces multiple public health emergencies simultaneously, such as . mpox, from being a neglected disease, has emerged as a global threat that has spread to more than 100 nonendemic countries, even as COVID-19 has been spreading for more than 3 years now. The general mpox symptoms are similar to chickenpox and measles, thus leading to a possible misdiagnosis. This study aimed at facilitating a rapid and high-brevity mpox diagnosis. Reportedly, mpox circulates among particular groups, such as sexually promiscuous gay and bisexuals. Hence, selectively vaccinating, isolating, and treating them seems difficult due to the associated social stigma. Deep learning (DL) has great promise in image-based diagnosis and could help in error-free bulk diagnosis. The novelty proposed, the system adopted, and the methods and approaches are discussed in the article. The present work proposes the use of DL models for automated early mpox diagnosis. The performances of the proposed algorithms were evaluated using the data set available in public domain. The data set adopted for the study was meant for both training and testing, the details of which are elaborated. The performances of CNN, VGG19, ResNet 50, Inception v3, and Autoencoder algorithms were compared. It was concluded that CNN, VGG19, and Inception v3 could help in early detection of mpox skin lesions, and Inception v3 returned the best (96.56%) classification accuracy.

Perceptions and Knowledge of Public Towards Emerging Human Monkeypox in Yemen: A Cross-Sectional Study

“…This contributes significantly to the early and accurate detection of mpox skin lesions. 53 The majority of respondents in the present study showed high levels of confidence in the ability of the general public and the local health authorities to control human mpox, even though it would negatively impact the economy. This confidence could have stemmed from the firsthand experience during the COVID-19 pandemic, where the World Health Organization (WHO) and health authorities have gained significant empowerment over the last three years.…”

Transmission dynamics, complications and mitigation strategies of the current mpox outbreak: A comprehensive review with bibliometric study

“…Nave Bayes algorithm achieved 91% accuracy in sorting mpox from other skin lesions outperforming various CNNs and shallow classifiers including GoogLeNet, AlexNet, VGG‐16, SVM, RF and DT 82 . A very recent study demonstrated that Inception v3 is the best model with 97.48% precision, 95.67% recall, 96.56% F1‐score and 96.56% accuracy in detecting mpox virus 83 . With a unique augmentation approach, this model returned 100% training accuracy and 96.56% validation accuracy.…”

“…82 A very recent study demonstrated that Inception v3 is the best model with 97.48% precision, 95.67% recall, 96.56% F1-score and 96.56% accuracy in detecting mpox virus. 83 With a unique augmentation approach, this model returned 100% training accuracy and 96.56% validation accuracy. As per the study, Inception v3 is a potentially valuable tool for early, automatic and accurate diagnosis of mpox as also other skin lesion diseases such as smallpox, chickenpox, measles, etc.…”

A Streamlined Approach towards Monkeypox Detection

“…For example, S. N. [1] developed a monkeypox skin lesion dataset (MSLD) and tested models like VGG16, ResNet50, and InceptionV3, finding out that at 82.96%, ResNet50 achieved the best accuracy. M. Pal et al (2023) [2] similarly evaluated CNNs on the multiclass classification of monkeypox vs chickenpox and measles, with InceptionV3 reaching 96.56% accuracy.…”