Artificial Intelligence and Modelling in Epidemiology Program, Melbourne Sexual Health Centre, Alfred Health, Melbourne, Australia.
School of Translational Medicine, Faculty of Medicine, Nursing and Health Sciences, Monash University, Melbourne, Australia.
J Med Internet Res. 2024 Sep 13;26:e52490. doi: 10.2196/52490.
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.
We aimed to develop and evaluate an artificial intelligence (AI)-based tool to differentiate mpox lesion images from other skin lesions seen in a sexual health clinic.
We used a data set with 2200 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 6 different deep learning architectures to train our AI models. We subsequently evaluated the performance of each model using a hold-out data set and an external validation data set to determine the optimal model for differentiating between mpox and non-mpox lesions.
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 F-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% (55/70) to 94% (66/70). The effectiveness of this approach was further validated by a visual analysis with gradient-weighted class activation mapping, demonstrating a reduction in false detection within the background of lesion images. On the external validation data set, ResNet-18 and DenseNet-121 achieved the highest performance. ResNet-18 achieved an AUC of 0.990 and an accuracy of 0.947, and DenseNet-121 achieved an AUC of 0.982 and an accuracy of 0.926.
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.
2022 年全球猴痘爆发对卫生机构造成了重大影响，需要采取额外的感染预防和控制措施，并改变诊所流程。早期识别疑似猴痘病例将有助于减轻这些影响。
我们旨在开发和评估一种基于人工智能（AI）的工具，以区分性健康诊所中看到的猴痘病变图像与其他皮肤病变图像。
我们使用了一个包含 2200 张图像的数据集，其中包括从墨尔本性健康中心和网络资源收集的猴痘和非猴痘病变图像。我们采用了深度学习方法，涉及 6 种不同的深度学习架构来训练我们的 AI 模型。然后，我们使用预留数据集中评估每个模型的性能，并使用外部验证数据集来确定区分猴痘和非猴痘病变的最佳模型。
DenseNet-121 模型的表现优于其他模型，整体受试者工作特征曲线（ROC）下面积（AUC）为 0.928，准确率为 0.848，精密度为 0.942，召回率为 0.742，F1 得分为 0.834。实施感兴趣区域（ROI）方法显著提高了所有模型的性能，DenseNet-121 模型的 AUC 增加到 0.982。这种方法使正确分类的猴痘图像从 79%（55/70）增加到 94%（66/70）。通过使用梯度加权类激活映射的视觉分析进一步验证了该方法的有效性，表明在病变图像的背景中减少了误检。在外部验证数据集中，ResNet-18 和 DenseNet-121 表现最佳。ResNet-18 的 AUC 为 0.990，准确率为 0.947，DenseNet-121 的 AUC 为 0.982，准确率为 0.926。
我们的研究表明，使用基于人工智能的图像识别算法可以准确地区分猴痘和常见皮肤病变。我们的研究结果为进一步研究该算法并确定该技术在性健康诊所中的应用提供了基础。
