OrganoLabeling: Quick and accurate annotation tool for organoid images

Organoids are self-assembled 3D cellular structures that resemble organs structurally and functionally, providing in vitro platforms for molecular and therapeutic studies. Generation of organoids from human cells often require long and costly procedures with arguably low efficiency. Prediction and selection of cellular aggregates that result in healthy and functional organoids can be achieved using artificial intelligence-based tools. Transforming images of 3D cellular constructs into digitally processible datasets for training deep learning models require labeling of morphological boundaries, which often is performed manually. Here we report an application named OrganoLabeling, which can create large image-based datasets in consistent, reliable, fast, and user-friendly manner. OrganoLabeling can create segmented versions of images with combinations of contrast adjusting, K-means clustering, CLAHE, binary and Otsu thresholding methods. We created embryoid body and brain organoid datasets, of which segmented images were manually created by human researchers and compared with OrganoLabeling. Validation is performed by training U-Net models, which are deep learning models specialized in image segmentation. U-Net models, that are trained with images segmented by OrganoLabeling, achieved similar or better segmentation accuracies than the ones trained with manually labeled reference images. OrganoLabeling can replace manual labeling, providing faster and more accurate results for organoid research free of charge.