乳腺癌诊断数据集|医学AI数据集

CBIS-DDSM数据集是用于乳腺癌AI诊断研究的标准化医学影像数据集，为数字乳腺筛查数据库（DDSM）的更新版。数据集包含6775次检查、10239张DICOM格式图像，涵盖1566名参与者，标注了良性、恶性和正常病例，并提供经病理验证的ROI分割、边界框及诊断信息。其规模大、标注权威，适用于开发和评估乳腺癌辅助诊断模型，广泛应用于医学影像分析、深度学习等场景。CBIS-DDSM is a standardized medical imaging dataset for breast cancer AI diagnosis research, serving as an updated iteration of the Digital Database for Screening Mammography (DDSM). The dataset comprises 6,775 examinations and 10,239 DICOM-format images, encompassing 1,566 participants. It is annotated with benign, malignant, and normal clinical cases, and provides pathologically validated ROI segmentations, bounding boxes, and diagnostic information. Boasting a large scale and authoritative annotations, this dataset is suitable for developing and evaluating breast cancer auxiliary diagnosis models, and has been widely utilized in scenarios including medical image analysis and deep learning.

搜集汇总

背景与挑战

背景概述

CBIS-DDSM数据集是一个用于乳腺癌AI诊断研究的标准化医学影像数据集，包含6775次检查、10239张DICOM格式图像，涵盖1566名参与者，标注了良性、恶性和正常病例，并提供经病理验证的标注。该数据集为英文，格式包括csv和jpg，总容量为4.95GB，适用于医学AI研究和模型训练。