Towards automatization of organoid analysis: A deep learning approach to localize and quantify organoid images

Abstract

The interest in the use of organoids in the biomedical field has increased exponentially in the past years. Organoids, or three-dimensional “mini-organs”, have the ability to proliferate and self-organize in-vitro, while displaying varying morphologies. When in culture, these structures can overlap with each other making the quantification and morphological characterization a challenging task. Quick and reliable analysis of organoid images could help in precisely modeling disease phenotypes as well as provide information on organ development. Therefore, automatization of the quantification and measurements is an important step towards an easier, faster, and less biased workflow.

In order to accomplish this, a free e-Science service (OrganelX) has been developed for localization and quantification of organoid size based on deep learning methods. The ability of the system was tested on murine liver organoids, and the data are made publicly available. The OrganelX e-Science free service is available at https://organelx.hpc.rug.nl/organoid/.