Abstract
Biomedical research often relies on identification and isolation of specific cell types using molecular biomarkers and sorting methods such as fluorescence or magnetic activated cell sorting. Labelling processes potentially alter the cells’ properties and should be avoided, especially when purifying cells for clinical applications. A promising alternative is the label-free identification of cells based on their physical properties. Sorting real-time deformability and fluorescence cytometry (soRT-FDC) is a microfluidic technique for label-free analysis and sorting of single cells. In soRT-FDC, bright-field images of cells are analyzed by a deep neural net (DNN) to obtain a sorting decision, but sorting was so far only demonstrated for blood cells which show clear morphological differences and are naturally in suspension. Most cells, however, grow in tissues, requiring dissociation before cell sorting which is associated with additional challenges including survival, changes in morphology, or presence of aggregates. Here, we introduce methods for robust analysis and sorting of single cells from mammalian nervous tissue and provide DNNs which are capable of distinguishing visually similar cells. Exemplarily, we employ the DNN for image-based sorting to enrich photoreceptor cells from dissociated retina for transplantation into the mouse eye. Results provide evidence that the combination of machine learning and soRT-FDC allows label-free enrichment of target cells from dissociated tissues.
Competing Interest Statement
The authors have declared no competing interest.