김성훈 (Tsinghua University) | 한빛사논문 > 한빛사

한빛사논문

조회422

Tsinghua University

Nat. Methods, 20 October 2025;Vol22, Issue 11 | https://doi.org/10.1038/s41592-025-02886-x CELLECT: contrastive embedding learning for large-scale efficient cell tracking

Hongyu Zhou^1,2,3,4,12, Seonghoon Kim^1,2,5,12, Zhifeng Zhao^1,2, Jiaqi Fan^1,2, Wen Huang^1,2, Xinghua Sui⁶, Lizhi Shao⁷, Haoran An^8,9, Jing-Ren Zhang¹⁰, Jiamin Wu^1,2,3,4,11 & Qionghai Dai^1,2,3,4,11

¹Department of Automation, Tsinghua University, Beijing, China.
²Institute for Brain and Cognitive Sciences, Tsinghua University, Beijing, China.
³Beijing Key Laboratory of Cognitive Intelligence, Tsinghua University, Beijing, China.
⁴IDG/McGovern Institute for Brain Research, Tsinghua University, Beijing, China.
⁵Hangzhou Zhuoxi Institute of Brain and Intelligence, Hangzhou, China.
⁶School of Pharmaceutical Sciences (Shenzhen), Shenzhen Campus of Sun Yat-sen University, Shenzhen, China.
⁷School of Internet, Anhui University, Hefei, China.
⁸Institute of Medical Technology, Peking University Health Science Center, Beijing, China.
⁹Department of Microbiology and Infectious Disease Center, Peking University Health Science Center, Beijing, China.
¹⁰Center for Infectious Biology, School of Basic Medical Sciences, Tsinghua University, Beijing, China.
¹¹Beijing National Research Center for Information Science and Technology, Tsinghua University, Beijing, China.
¹²These authors contributed equally: Hongyu Zhou, Seonghoon Kim.

Corresponding authors
Correspondence to Jiamin Wu or Qionghai Dai.

Abstract

Quantitative analysis of large-scale cellular behaviors plays an increasingly crucial role in understanding mechanisms of diverse physiopathological processes, but achieving cell tracking with both high performance and efficiency in practical applications remains a challenge. Here we introduce CELLECT, a contrastive embedding learning method for large-scale efficient cell tracking, and demonstrate it on the Caenorhabditis elegans dataset in the Cell Tracking Challenge. By contrastive learning of latent embeddings of diverse cellular structures, a CELLECT model pretrained on a single public dataset can be effectively applied across different imaging modalities and species with broad generalization. Using advanced two-photon imaging, CELLECT enables real-time 3D tracking of large-scale B cells with frequent divisions during germinal center formation in a mouse lymph node, quantitative identification of cell–bacterium interactions in the mouse spleen and high-fidelity extraction of neural signals during strong nonrigid motions. We believe that these results demonstrate broad applications of CELLECT in immunology, pathology and neuroscience.

논문정보

형식Research article
게재일2025년 10월 (BRIC 등록일 2025-10-21)
연구진국외 연구진
분야 생명과학 > 면역학

김성훈 님 전체 논문보기

연구자 키워드

연구자 ID

댓글 작성 로그인

CV 열람하기

연락처 보기