ISIC Melanoma Dataset

This robust dataset is extracted from the International Skin Imaging Collaboration (ISIC). Similar datasets are used for the annual ISIC Challenge, presenting an opportunity for the computer science community to produce algorithms that can outperform professional dermatology. The submitted dataset contains approximately 1,000 images of malignant melanomas, as well as approximately 1,000 images of benign melanomas. The general purpose of the dataset is to present an opportunity for cutting-edge image classification algorithms to find patterns between the respective groups of images, both for the advancement of deep learning solutions as well as to build potential life-saving applications in the field of medical imaging.

本数据集乃由国际皮肤影像协作组织（International Skin Imaging Collaboration，简称ISIC）精心提炼而成，具有坚实的质量。此类数据集常用于年度ISIC挑战赛，为计算机科学界提供了一个展示其算法超越专业皮肤病学水平的舞台。提交的数据集中包含大约1,000张恶性黑色素瘤的图像，以及大约1,000张良性黑色素瘤的图像。本数据集的宗旨在于，为前沿的图像分类算法提供机会，以探索不同图像组之间的模式，这不仅有助于深化深度学习解决方案的发展，亦有望在医学影像领域构建出可能拯救生命的应用。