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 COVID-19 and Monkeypox (mpox). 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.

Figure 1

Confusion matrices of (a) CNN, (b) VGG-19, (c) Inception v3. and (d) Autoencoder.

Figure 2

Accuracy, AUC, and loss curve of CNN, VGG-19, Inception v3, and Autoencoder models.

Figure 3

ROC curves for the test DL models.

Figure 4

Samples of the considered images after data set preprocessing.

Figure 5

Architecture used in the study: the skin sensor senses the mpox skin lesion, and patient data is stored in the cloud. Then the application data are processed using a digital (computer) platform using python open-source software. Deep learning models are implemented on the mpox skin lesion database to extract the features of the lesion, and then, the DL model classifies the skin lesion as mpox or others. If there is an mpox skin lesion, a notification is sent directly to the clinician’s mobile. In case of an emergency, the concerned doctor prescribes medicine to the patient through a mobile app. If it is a skin lesion other than mpox (like chickenpox and measles), then the notification is sent automatically to the patient’s mobile and the patient takes therapeutic prescriptions from the doctor accordingly. The cloud system is used to store huge (big) patient data. An “emergency” patient with mpox skin lesion is treated immediately this way without a need to visit a hospital while the misdiagnosis rate is reduced.