Saha Anup, Adeola Joseph, Ferrera Nuria, Mothershaw Adam, Rezze Gisele, Gaborit Séraphin, D'Alessandro Brian, Voskanyan Robert, Szabó Gyula, Pataki Balázs, Rajani Hayat, Nazari Sana, Hayat Hassan, Serra-García Laura, Primiero Clare, Bonin Serena, Zalaudek Iris, Soyer H Peter, Malvehy Josep, Garcia Rafael
Computer Vision and Robotics Research Institute, University of Girona, Girona, Spain.
Dermatology Department, Hospital Clínic Barcelona, Universitat de Barcelona, Barcelona, Spain.
Sci Data. 2025 Aug 18;12(1):1442. doi: 10.1038/s41597-025-05483-x.
Artificial intelligence has significantly advanced skin cancer diagnosis by enabling rapid and accurate detection of malignant lesions. In this domain, most publicly available image datasets consist of single, isolated skin lesions positioned at the centre of the image. While these lesion-centric datasets have been fundamental for developing diagnostic algorithms, they lack the context of the surrounding skin, which is critical for improving lesion detection. The iToBoS dataset was created to address this challenge. It includes 16,954 images of skin regions from 100 participants, captured using 3D total body photography. Each image roughly corresponds to a 7 × 9 cm section of skin with all suspicious lesions annotated using bounding boxes. Additionally, the dataset provides metadata such as anatomical location, age group, and sun damage score for each image. This dataset was designed with the aim of facilitating the training and benchmarking of algorithms, in order to enable early detection of skin cancer and deployment of this technology in non-clinical environments.
人工智能通过实现对恶性病变的快速准确检测，显著推动了皮肤癌诊断的发展。在这一领域，大多数公开可用的图像数据集都由位于图像中心的单个孤立皮肤病变组成。虽然这些以病变为中心的数据集对于开发诊断算法至关重要，但它们缺乏周围皮肤的背景信息，而这对于改进病变检测至关重要。iToBoS数据集就是为应对这一挑战而创建的。它包含来自100名参与者的16954张皮肤区域图像，这些图像是使用3D全身摄影技术拍摄的。每张图像大致对应于7×9厘米的皮肤区域，所有可疑病变均使用边界框进行标注。此外，该数据集还为每张图像提供了诸如解剖位置、年龄组和阳光损伤评分等元数据。该数据集的设计目的是促进算法的训练和基准测试，以便能够早期检测皮肤癌并将该技术应用于非临床环境。
