Intelligent image-activated cell sorting and beyond
A fundamental challenge of biology is to understand the vast heterogeneity of cells. The differences in composition, structure, and morphology of cells are strongly linked with their physiological functions. However, conventional technologies have been limited in uncovering these relations. This is due to the trade-off between cell throughput and the complexity of image data. To overcome this trade-off, we developed a machine intelligence technology called “Intelligent Image-Activated Cell Sorting” that achieves real-time fluorescence-image-based intelligent cell sorting with high throughput. This technology builds on a unique integration of high-throughput fluorescence cell imaging, focusing, and sorting techniques on a hybrid software-hardware data management infrastructure with deep learning, allowing high flexibility, high scalability, and real-time automated operation for data acquisition, data processing, and decision making.
- 1 School of Science, The University of Tokyo