JMIR Publications

ABSTRACT

Background:

The 2022 global outbreak of mpox has significantly impacted health facilities, and necessitated additional infection prevention and control measures and alterations to clinic processes. Early identification of suspected mpox cases will assist in mitigating these impacts.

Objective:

We aimed to develop an AI-based tool to differentiate mpox lesion images from other skin lesions seen in a sexual health clinic.

Methods:

We used a dataset with 2,200 images, that included mpox and non-mpox lesions images, collected from Melbourne Sexual Health Centre and web resources. We adopted deep learning approaches which involved six different deep learning architectures to train our AI models. We subsequently evaluated the performance of each model to determine the best model for differentiating between mpox and non-mpox lesions.

Results:

The denseNet-121 model outperformed other models with an overall Area Under the Receiver Operating Characteristic Curve (AUC) of 0·928, an accuracy of 0·848, a precision of 0·942, a recall of 0·742, and an F1-score of 0·834. Implementation of a region-of-interest approach significantly improved the performance of all models, with the AUC for the DenseNet-121 model increasing to 0·982. This approach resulted in an increase in the correct classification of mpox images from 79% to 94%. The effectiveness of this approach was further validated by a visual analysis with Grad-CAM, demonstrating a reduction in the false detection within the background of lesion images.

Conclusions:

Our study demonstrated it was possible to use an AI-based image recognition algorithm to accurately differentiate between mpox and common skin lesions. Our findings provide a foundation for future investigations aimed at refining the algorithm and establishing the place of such technology in a sexual health clinic.