Principles and applications of intelligent image-activated cell sorting 2.0
Akihiro Isozaki
Department of Chemistry, The University of Tokyo, Tokyo, JAPAN (E-mail: a_isozaki@chem.s.u-tokyo.ac.jp)
Abstract
We recently proposed a new term, AI on a chip, for a growing research field of a combination of artificial intelligence (AI) technology and lab-on-a-chip technology [Isozaki et al., Lab on a Chip 20, 3074 (2020)]. In this invited talk, I introduce an AI-on-a-chip technology we previously reported as “Intelligent Image-Activated Cell Sorting (iIACS)” [Nitta et al., Cell 175, 266 (2018); Isozaki et al., Nature Protocols 14, 2370 (2019)]. The iIACS machine builds on a fundamentally new architecture that makes image-based intelligent cell sorting possible at an ultra-high throughput manner. This technology integrates four components on a hybrid software-hardware data-management infrastructure: a homemade high-speed microscope, cell focuser, high-speed sorter, and deep learning-based image processer, which enables real-time automated operation for data acquisition, data processing, intelligent decision-making, and actuation. Recently, we improved the state-of-the-art iIACS machine and, at the beginning of this year, reported an upgraded version of the iIACS machine that shows higher system performance, expanding the range of applications and discoveries enabled by the technology [Isozaki et al., Lab on a Chip 20, 2263, (2020)]. Specifically, the upgraded iIACS machine gives a high sensitivity of ~50 molecules of equivalent soluble fluorophores (MESFs) and a high throughput of 2,000 events per second. I introduce the details of its principles in this invited talk. Furthermore, we are applying this technology to a diverse range of applications (e.g., immunology, cancer biology, hematology, microbiology, and synthetic biology). I introduce some of these applications conducted in our laboratory.
Short Bio
Akihiro Isozaki received his B.S. in mechanical engineering from Meiji University in 2006, and his M.S. in mechano-informatics from the University of Tokyo in 2008. From 2008-2010 he conducted studies at Panasonic Corporation prior to receiving his Ph.D. in mechano-informatics from the University of Tokyo in 2014. He then conducted postdoctoral studies in the Department of Chemistry of the University of Tokyo until 2019 and took his current position as an assistant professor in the same year. He is currently engaged in the development of novel high-throughput cell sorting devices and their applications.