Abstract
Patient-derived organoids are invaluable for fundamental and translational cancer research and holds great promise for personalized medicine. However, the shortage of available analysis methods, which are often single-time point, severely impede the potential and routine use of organoids for basic research, clinical practise, and pharmaceutical and industrial applications. Here, we report the development of a high-throughput automated organoid analysis platform that allows for kinetic monitoring of organoids, named Organoid Brightfield Identification-based Therapy Screening (OrBITS). The combination of computer vision with a convolutional network machine learning approach allowed for the detection and tracking of organoids in routine extracellular matrix domes, advanced Gri3D®-96 well plates, and high-throughput 384-well microplates, solely based on brightfield imaging. We used OrBITS to screen chemotherapeutics and targeted therapies, and incorporation of a fluorescent cell death marker, revealed further insight into the mechanistic action of the drug, a feature not achievable with the current gold standard ATP-assay. This manuscript describes the validation of the OrBITS deep learning analysis approach against current standard assays for kinetic imaging and automated analysis of organoids. OrBITS, as a scalable, high-throughput technology, would facilitate the use of patient-derived organoids for drug development, therapy screening, and guided clinical decisions for personalized medicine. The developed platform also provides a launching point for further brightfield-based assay development to be used for fundamental research.
Competing Interest Statement
The authors have declared no competing interest.
