Identification of different cell types is an indispensable part in biomedical research and clinical application. During the lastdecades, much attention was put onto molecular characterization and many cell types can now be identified and sortedbased on established markers. The required staining process is a lengthy and costly treatment, which can cause alterationsof cellular properties, contaminate the sample and therefore limit its subsequent use. A promising alternative to molecularmarkers is the label-free identification of cells using mechanical or morphological features. We introduce a microfluidicdevice for active label-free sorting of cells based on their bright field image supported by innovative real-time imageprocessing and deep neural networks (DNNs). A microfluidic chip features a standing surface acoustic wave generator foractively pushing up to 100 cells/sec to a determined outlet for collection. This novel method is successfully applied forenrichment of lymphocytes, granulo-monocytes and red blood cells from human blood. Furthermore, we combined thesetup with lasers and a fluorescence detection unit, allowing to assign a fluorescence signal to each captured bright-fieldimage. Leveraging this tool and common molecular staining, we created a labelled dataset containing thousands of imagesof different blood cells. We used this dataset to train a DNN with optimized latency below 1 ms and used it to sort unstainedneutrophils from human blood, resulting in a target concentration of 90%. The innovative approach to use deep learningfor image-based sorting opens up a wide field of potential applications, for example label-free enrichment of stem-cellsfor transplantation.
展开▼
