OrganoID: A versatile deep learning platform for tracking and analysis of single-organoid dynamics.

Organoids have immense potential as ex vivo disease models for drug discovery and personalized drug screening. Dynamic changes in individual organoid morphology, number, and size can indicate important drug responses. However, these metrics are difficult and labor-intensive to obtain for high-throughput image datasets. Here, we present OrganoID, a robust image analysis platform that automatically recognizes, labels, and tracks single organoids, pixel-by-pixel, in brightfield and phase-contrast microscopy experiments. The platform was trained on images of pancreatic cancer organoids and validated on separate images of pancreatic, lung, colon, and adenoid cystic carcinoma organoids, which showed excellent agreement with manual measurements of organoid count (95%) and size (97%) without any parameter adjustments. Single-organoid tracking accuracy remained above 89% over a four-day time-lapse microscopy study. Automated single-organoid morphology analysis of a chemotherapy dose-response experiment identified strong dose effect sizes on organoid circularity, solidity, and eccentricity. OrganoID enables straightforward, detailed, and accurate image analysis to accelerate the use of organoids in high-throughput, data-intensive biomedical applications. Author summary: A recent advance in biomedical research is the use of connective tissue gels to grow cells into microscopic structures, called organoids, that preserve and exhibit the physical and molecular traits of a particular organ. Organoids have enabled researchers to study complex phenomena, such as the beating of the heart or the folds of the intestines, and the effects of drugs on these properties. Changes in the size and shape of organoids are important indicators of drug response, but these are tedious to measure in large drug screening experiments, where thousands of microscopy images must be analyzed. We developed a software tool named OrganoID that automatically traces the exact shape of individual organoids in an image, even when multiple organoids are clumped together, and measures organoid changes over time. To show our tool in action, we used OrganoID to analyze pancreatic cancer organoids and their response to chemotherapy. We also showed that our tool can handle images of many different types of organoids, even those derived from mouse cells. With this software, researchers will be able to easily analyze immense quantities of organoid images in large-scale experiments to discover new drug treatments for a range of diseases. [ABSTRACT FROM AUTHOR]