Mpox Close Skin Images

The Mpox Close Skin Images dataset (MCSI) is a collection of skin images obtained from diverse public sources, that we accurately pre-processed (i.e., cropped and zoomed) in order to focus the skin lesion (if present), and to evaluate Machine Learning models aimed at detecting different pathologies from skin lesion pictures taken with smartphone cameras. It includes a total of 400 pictures homogeneously divided in 4 different classes: mpox, which contains samples of mpox (formerly Monkeypox) skin lesions; chickenpox, with samples of chickenpox cases; acne, containing samples of acne at different severity levels; and healthy, which contains samples of skin without any evident symptoms. This repository is part of the supplementary material accompanying the paper named: A Transfer Learning and Explainable Solution to Detect mpox from Smartphones images. Please, refer to the README.md file for more details. Version 2 includes the addition of the file skin_tone_labels.csv. This file comprises the classification of skin images into Light and Dark skin tone classes. These classifications are instrumental in assessing the model's prediction fairness across various skin pigments.

Mpox近距离皮肤图像数据集（Mpox Close Skin Images, MCSI）是从多种公开来源采集的皮肤图像集合，我们对其进行了精准预处理（即裁剪与放大操作），以聚焦图像中的皮肤皮损（若存在），并用于评估旨在通过智能手机拍摄的皮肤皮损图像识别多种皮肤病症的机器学习模型。该数据集总计包含400张图像，均匀划分为4个类别：猴痘（Mpox，原称Monkeypox）皮损样本类、水痘样本类、不同严重程度的痤疮样本类，以及无任何明显症状的健康皮肤样本类。本仓库为题为《基于迁移学习与可解释方法的智能手机图像猴痘检测方案》的论文配套补充材料之一，更多细节请参阅README.md文件。版本2新增了skin_tone_labels.csv文件，该文件将皮肤图像划分为浅肤色与深肤色两个类别，该分类体系可用于评估模型在不同肤色人群中的预测公平性。