Intelligent Image-Activated Cell Sorting

Citation metadata

From: Cell(Vol. 175, Issue 1)
Publisher: Elsevier B.V.
Document Type: Report
Length: 722 words

Document controls

Main content

Abstract :

To access, purchase, authenticate, or subscribe to the full-text of this article, please visit this link: http://dx.doi.org/10.1016/j.cell.2018.08.028 Byline: Nao Nitta (1,2), Takeaki Sugimura (1,2), Akihiro Isozaki (1), Hideharu Mikami (1), Kei Hiraki (1), Shinya Sakuma (3), Takanori Iino (4), Fumihito Arai (3), Taichiro Endo (5,6), Yasuhiro Fujiwaki (4), Hideya Fukuzawa (7), Misa Hase (1), Takeshi Hayakawa (8), Kotaro Hiramatsu (1), Yu Hoshino (9), Mary Inaba (10), Takuro Ito (1,2), Hiroshi Karakawa (1), Yusuke Kasai (3), Kenichi Koizumi (10), SangWook Lee (1), Cheng Lei (1), Ming Li (11), Takanori Maeno (12), Satoshi Matsusaka (13), Daichi Murakami (10), Atsuhiro Nakagawa (14), Yusuke Oguchi (15), Minoru Oikawa (16), Tadataka Ota (1), Kiyotaka Shiba (17), Hirofumi Shintaku (18), Yoshitaka Shirasaki (15), Kanako Suga (17), Yuta Suzuki (4), Nobutake Suzuki (15), Yo Tanaka (19), Hiroshi Tezuka (10), Chihana Toyokawa (7), Yaxiaer Yalikun (19), Makoto Yamada (5,20), Mai Yamagishi (15), Takashi Yamano (7), Atsushi Yasumoto (21), Yutaka Yatomi (21), Masayuki Yazawa (22), Dino Di Carlo (1,11,23,24), Yoichiroh Hosokawa (25), Sotaro Uemura (15), Yasuyuki Ozeki (4), Keisuke Goda [goda@chem.s.u-tokyo.ac.jp] (1,2,26,27,*) Keywords image-activated cell sorting; high-throughput microscopy; high-throughput screening; deep learning; convolutional neural network; cellular heterogeneity; machine intelligence; cellular morphology Highlights * Demonstration of deep-learning-assisted image-activated cell sorting * Demonstration of the technology's utility to various types and sizes of cells * Image-activated sorting of microalgal cells based on protein localization * Image-activated sorting of blood cells based on cell-cell interaction Summary A fundamental challenge of biology is to understand the vast heterogeneity of cells, particularly how cellular composition, structure, and morphology are linked to cellular physiology. Unfortunately, conventional technologies are limited in uncovering these relations. We present a machine-intelligence technology based on a radically different architecture that realizes real-time image-based intelligent cell sorting at an unprecedented rate. This technology, which we refer to as intelligent image-activated cell sorting, integrates high-throughput cell microscopy, focusing, and sorting on a hybrid software-hardware data-management infrastructure, enabling real-time automated operation for data acquisition, data processing, decision-making, and actuation. We use it to demonstrate real-time sorting of microalgal and blood cells based on intracellular protein localization and cell-cell interaction from large heterogeneous populations for studying photosynthesis and atherothrombosis, respectively. The technology is highly versatile and expected to enable machine-based scientific discovery in biological, pharmaceutical, and medical sciences. Author Affiliation: (1) Department of Chemistry, The University of Tokyo, Tokyo 113-0033, Japan (2) Japan Science and Technology Agency, Saitama 332-0012, Japan (3) Department of Micro-Nano Mechanical Science and Engineering, Nagoya University, Nagoya 464-8603, Japan (4) Department of Electrical Engineering and Information Systems, The University of Tokyo, Tokyo 113-8656, Japan (5) Center for Advanced Intelligence Project, RIKEN, Tokyo 103-0027, Japan (6) ExaWizards Inc., Tokyo 105-0013, Japan (7) Graduate School of Biostudies, Kyoto University, Kyoto 606-8502, Japan (8) Department of Precision Mechanics, Chuo University, Tokyo 112-8551, Japan (9) Department of Chemical Engineering, Kyushu University, Fukuoka 819-0395, Japan (10) Department of Creative Informatics, The University of Tokyo, Tokyo 113-0033, Japan (11) Department of Bioengineering, University of California, Los Angeles, Los Angeles, CA 90095, USA (12) Institute of Medical Science, The University of Tokyo, Tokyo 108-8639, Japan (13) Department of Gastroenterology, Cancer Institute Hospital, Japanese Foundation for Cancer Research, Tokyo 135-8550, Japan (14) Department of Neurosurgery, Graduate School of Medicine, Tohoku University, Sendai 980-8577, Japan (15) Department of Biological Sciences, The University of Tokyo, Tokyo 113-0033, Japan (16) Science and Technology Unit, Natural Sciences Cluster, Kochi University, Kochi 780-8520, Japan (17) Division of Protein Engineering, Cancer Institute, Japanese Foundation for Cancer Research, Tokyo 135-8550, Japan (18) Department of Micro Engineering, Kyoto University, Kyoto 606-8501, Japan (19) Center for Biosystems Dynamics Research, RIKEN, Osaka 565-0871, Japan (20) Graduate School of Informatics, Kyoto University, Kyoto 606-8501, Japan (21) Department of Clinical Laboratory Medicine, Graduate School of Medicine, The University of Tokyo, Tokyo 113-0033, Japan (22) Department of Rehabilitation and Regenerative Medicine, Pharmacology, Columbia University, New York, NY 10032, USA (23) Department of Mechanical Engineering, University of California, Los Angeles, Los Angeles, CA 90095, USA (24) California NanoSystems Institute, University of California, Los Angeles, Los Angeles, CA 90095, USA (25) Graduate School of Materials Science, Nara Institute of Science and Technology, Ikoma 630-0192, Japan (26) Department of Electrical Engineering, University of California, Los Angeles, Los Angeles, CA 90095, USA * Corresponding author Article History: Received 10 June 2018; Revised 9 August 2018; Accepted 15 August 2018 (miscellaneous) Published: August 27, 2018 (footnote)27 Lead Contact

Source Citation

Source Citation   

Gale Document Number: GALE|A555208830