Voxel51/deeplesion-balanced-2k

这是一个从DeepLesion数据集精心挑选的子集，用于演示和基准测试。它包含2000个CT病变样本，均匀分布在8种粗略的病变类型中，并筛选出短直径大于10mm的病变。数据集来源于国家卫生研究院临床中心，所有切片均使用DICOM参数窗宽并转换为8位PNG格式。

This dataset is a curated subset of the DeepLesion dataset, prepared for demonstration and benchmarking purposes. It consists of 2,000 CT lesion samples, balanced across 8 coarse lesion types, and filtered to include lesions with a short diameter > 10mm. The dataset is sourced from the National Institutes of Health Clinical Center, with all slices windowed using DICOM parameters and converted to 8-bit PNG format.