< Back to previous page
Organoid painting: Unbiased cellular phenotyping of human tissue mimics using deep learning-enhanced imaging and analysis.
Identification of novel therapeutic compounds relies on the use of cell culture and animal models. While the former are overly simplified, the latter are not human and ethically contested. Suboptimal models at the discovery side will inevitably lead to a steep loss of leads in clinical trials. With the advent of human induced pluripotent stem cell (iPSC) technology, it has now become possible to generate organoids that more faithfully capture part of the heterogeneity and three-dimensional context of human tissue. However, the complexity and optical inaccessibility of such tissue mimics hamper their adoption in a routine screening setting. We intend to develop a pipeline that will allow in-depth characterization of organoids. Concretely, we will combine our expertise in advanced microscopy anddeep learning to enable ultrafast, high-quality imaging and subsequent cellular phenotyping of organoids. As two case studies with industrial relevance, we will use this pipeline to discriminate cell states in tumor spheroids and cell types in neuro-organoids. Once established, our approach will find a ready market with pharmaceutical and clinical R&D laboratories that wish to test their compound libraries on a physiologically relevant model, in particular in the oncology and neuroscience fields. In addition, it will foster an improved quality control of tissue mimics in the context of regenerative medicine.
Date:1 Oct 2021 → Today
Keywords:LIGHT SHEET MICROSCOPY, DEEP LEARNING, DRUG SCREENING
Disciplines:Biomedical image processing, Pattern recognition and neural networks, Data visualisation and high-throughput image analysis