Intelligent image-activated cell sorting
I present a machine intelligence technology called “Intelligent Image-Activated Cell Sorting” [Cell 175, 266 (2018)] that achieves real-time image-based sorting of single cells on a microfluidic chip at a high throughput of ~100 events per second. This technology builds on a seamless integration of high-throughput cell microscopy, focusing, and sorting techniques with a deep neural network on a software-hardware platform, enabling fully automated operation for data acquisition, data processing, intelligent decision making, and actuation. Also, I introduce a few unique applications in microbiology and hematology enabled by the technology and discuss how the technology will help us make machine-based scientific discoveries.
Keisuke Goda is a professor of chemistry at the University of Tokyo. He obtained a B.A. degree summa cum laude from UC Berkeley and a Ph.D. from MIT, both in physics. At MIT, he worked on the development of the LIGO detectors, which led to the Nobel Prize in Physics in 2017. He joined the University of Tokyo in 2012 and launched a startup in 2018. His research group currently focuses on molecular imaging and spectroscopy together with computational analytics for life sciences and medicine. He has published numerous papers in top journals such as Nature, Cell, and Nature Photonics and has been awarded WIRED Audi Innovation Award, JSPS Prize, Japan Academy Medal, to name a few.