BRACS
收藏资源简介:
BRACS数据集是由意大利国家研究委员会高性能计算与网络研究所和IBM苏黎世研究实验室合作创建的,专注于乳腺癌亚型分类。该数据集包含547个全玻片图像(WSIs)和4539个感兴趣区域(RoIs),涵盖了良性、恶性和非典型三种病变类型,以及多种亚型。数据集的创建过程涉及多位认证病理学家的共识标注,确保了数据的高质量和准确性。BRACS数据集的应用领域主要集中在通过人工智能技术辅助病理诊断,提高乳腺癌诊断的准确性和效率。
The BRACS dataset was developed in collaboration between the Institute of High Performance Computing and Networking of the Italian National Research Council and IBM Research Zurich, focusing on breast cancer subtyping. This dataset includes 547 whole-slide images (WSIs) and 4,539 regions of interest (RoIs), covering three major lesion types: benign, malignant, and atypical, as well as multiple subtypes. The dataset's development involved consensus annotation from multiple certified pathologists, ensuring the high quality and accuracy of the data. The main application areas of the BRACS dataset focus on assisting pathological diagnosis via artificial intelligence technologies to improve the accuracy and efficiency of breast cancer diagnosis.




