遇见数据集

Annotated mouse intestinal organoid dataset (YOLO format)

收藏
Zenodo2023-02-20 更新2026-05-26 收录
数据链接:
官方服务:

资源简介:

Dataset of 840 light-transmitted images taken with EVOS FL microscope (Thermo Fisher) at objective 4X of mouse intestinal organoids grown at different densities and from multiple stages of culture. The dataset has a total of 23066 annotations<strong>. </strong>The images were manually annotated using the python library labelImg and exported for Yolo format as text files. The four classes of organoids in the text files are coded with integers: 0 for organoid0, 1 for organoid1, 2 for organoid3, and 3 for spheroid. The dataset images were split into a training and validation set consisting of 756 and 84 images using the python library module splitfolders. See publication ( doi:10.1242/dmm.049756) for more details. <strong>Annotations</strong> <strong>Class </strong> <strong>Description</strong> <strong> Label</strong> Cystic organoid Very early stage, small, cystic, non-budding organoids with thick walls <em>Organoid0</em> Early organoid Early, budding organoids with 1-2 crypts <em>Organoid1</em> Late organoid Large, budding organoids with 3 or more crypt units <em>Organoid3</em> Spheroid Large, circular, thin-walled organoids representing, e.g. fetal, regenerating, tumorigenic, or hyperstimulated organoids <em>Spheroid</em>

提供机构:
Zenodo
创建时间:
2023-02-20
二维码
社区交流群
二维码
科研交流群
商业服务