A large and diverse brain organoid dataset of 1,400 cross-laboratory images of 64 trackable brain organoids from four different clones

This dataset is presented in the paper A large and diverse brain organoid dataset of 1,400 cross-laboratory images of 64 trackable brain organoids from four different clones

This dataset encompasses two sources of data:

1. A comma-separated values ('CSV') file. This file serves as a key to our dataset with one image per row. Each image is represented by its image identifier ('img_id') with the format [org_id]_[clone]_d[imaging_day]_[imaging_lab]. For each image, the CSV file also specifies the organoid size for convenience. Alternatively, the organoid size can be calculated using the ground truth organoid segmentation (org_segGT). 
2. For each row of the CSV file, we provide the image and org_segGT. For Lab A, the images are in JPEG format. For lab B, the images are in TIF format. Org_segGT is a manually created binary 2D NumPy array with the same size as the image (1024 x 768 for lab A, 1388 x 1040 for lab B). A value of 1 in org_segGT at position (x, y) means that the same position (x, y) in the corresponding image is covered by the organoid. The image file and the org_segGT file have the following format: [img_id].[jpg|tif] and [img_id].npy. For day 12, organoids were imaged before and after embedding from 96-well plates in 12-well plates, allowing the investigation of well-specific optical properties.

For segmentation and growth monitoring using this dataset, please see https://github.com/deiluca/robust_monitoring_organoid_growth.