EUVIMEDEUVIMED entdecken
Open Access · CC BY 4.0

ReLink: Reliable Deep Learning for Microscopic Motion Tracking

Yuan Jiang iD, Xiaochen Feng iD, Hongda Wei, Hao Sha iD, Hongpeng Wang iD, Min Zhang, Sanyang Han iD, Yongbing Zhang iD

Advanced Science · 28.10.2026

DOI: 10.1002/advs.78541 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Advanced Science, online erschienen am 28.10.2026. Verfasst von Yuan Jiang und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China. Die Arbeit nennt 70 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Guangdong Innovative and Entrepreneurial Research Team Program.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Single‐particle tracking (SPT) serves as a fundamental technique for deciphering complex microscopic dynamics in biological and physical systems by resolving trajectories of individual particles. However, linking localizations into trajectories remains challenging in realistic experiments, where crowding, blinking, and localization errors lead to linking ambiguity. Both statistical and deep‐learning approaches have been explored in these conditions, yet reliable link selection that generalizes across varying data distributions remains elusive. Here, we propose ReLink, a general deep‐learning framework for reliable trajectory linking in SPT. By integrating physical priors into geometric representations and leveraging confidence‐based adaptive filtering at inference, ReLink enables automated selection of trustworthy linkages, thereby preserving the fidelity of downstream trajectory‐based analyses. Across challenging simulated scenarios spanning broad experimental conditions and motion regimes, ReLink consistently outperforms representative statistical and deep learning‐based trajectory linking methods in both edge‐level and trajectory‐level evaluation metrics, leading to markedly improved downstream inference on public benchmarks. We further validate ReLink on diverse real‐world experiments, from free diffusion systems to crowded intracellular environments, demonstrating its practical significance for quantitative interpretation of microscopic dynamics and its promise for next‐generation trustworthy and automated SPT.

Schlagwörter

Stichwörter der Autor:innen

reliable deep learningsingle particle trackingstochastic processestrajectory linking

Autor:innen und Institutionen

  • School of Computer Science and Technology, Harbin Institute of Technology (Shenzhen), Shenzhen, Guangdong, China.
  • Institute of Biopharmaceutical and Health Engineering, Tsinghua Shenzhen International Graduate School (SIGS), Tsinghua University, Shenzhen, Guangdong, China.

ORCID-Profile: Yuan Jiang, Xiaochen Feng, Hao Sha, Hongpeng Wang, Sanyang Han, Yongbing Zhang

Förderung

  • National Natural Science Foundation of China
  • Guangdong Innovative and Entrepreneurial Research Team Program

Zitieren

APA

Jiang, Y., Feng, X., Wei, H., Sha, H., Wang, H., Zhang, M., Han, S., & Zhang, Y. (2026). ReLink: Reliable Deep Learning for Microscopic Motion Tracking. Advanced Science. https://doi.org/10.1002/advs.78541

Vancouver

Jiang Y, Feng X, Wei H, Sha H, Wang H, Zhang M, et al. ReLink: Reliable Deep Learning for Microscopic Motion Tracking. Advanced Science. 2026. doi:10.1002/advs.78541

BibTeX
@article{Jiang2026,
  author = {Jiang, Yuan and Feng, Xiaochen and Wei, Hongda and Sha, Hao and Wang, Hongpeng and Zhang, Min and Han, Sanyang and Zhang, Yongbing},
  title = {ReLink: Reliable Deep Learning for Microscopic Motion Tracking},
  journal = {Advanced Science},
  year = {2026},
  doi = {10.1002/advs.78541}
}
Kostenlos starten →