ApuShape: Human-in-the-Loop Annotation Software for Fluorescent Nuclei Segmentation
Analytical Chemistry · 04.08.2026 · 98 (30) · 22043-22052
DOI: 10.1021/acs.analchem.5c08200 ↗Kurz gefasst
Fachartikel in der Zeitschrift Analytical Chemistry, online erschienen am 21.07.2026. Verfasst von Ziwei Chen und 7 weiteren Autor:innen. Beteiligte Einrichtung: School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing100044, China. Hauptthemen laut MEDLINE: Software, Cell Nucleus, Image Processing, Computer-Assisted. Die Arbeit nennt 33 Literaturangaben. Gefördert von: Fundamental Research Funds for the Central Universities, National Basic Research Program of China (973 Program), National Natural Science Foundation of China (NSFC).
Abstract (Originalsprache)
Large-scale cellular imaging studies increasingly require highly accurate and efficient nucleus annotation in fluorescence microscopy images. However, dedicated annotation software designed for high-throughput nucleus instance segmentation remains scarce. Here, we introduce ApuShape, an interactive annotation software that integrates a contour-level nucleus instance segmentation algorithm, a human-in-the-loop active learning strategy, and a boundary refinement algorithm for the rapid creation of data sets. ApuShape demonstrates strong performance in identifying and refining nucleus shapes across three large-scale data sets. It achieves expert-level annotation accuracy while significantly reducing manual annotation effort. As a result, ApuShape efficiently produces refined nucleus annotations featuring highly accurate contours at scale. Our results suggest that ApuShape provides a standard operating procedure for annotating fluorescence microscopy images at single-cell resolution. The ApuShape software is freely available at https://github.com/BUAA-LiuLab/ApuShape.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Autor:innen und Institutionen
- School of Electronic and Information Engineering, Beijing Jiaotong University, Beijing100044, China.
- School of Biological Science and Medical Engineering & School of Engineering Medicine, Beihang University, Beijing100191, China.
- School of Medical Technology, Beijing Institute of Technology, Beijing100081, China.
Förderung
- Fundamental Research Funds for the Central Universities
- National Basic Research Program of China (973 Program)
- National Natural Science Foundation of China (NSFC)
- Beijing Municipal Natural Science Foundation
Zitieren
APA
Chen, Z., Li, J., Wei, Q., Zhang, L., Luo, S., Jin, J., Zhang, Z., & Liu, C. (2026). ApuShape: Human-in-the-Loop Annotation Software for Fluorescent Nuclei Segmentation. Analytical Chemistry, 98(30), 22043-22052. https://doi.org/10.1021/acs.analchem.5c08200
Vancouver
Chen Z, Li J, Wei Q, Zhang L, Luo S, Jin J, et al. ApuShape: Human-in-the-Loop Annotation Software for Fluorescent Nuclei Segmentation. Analytical Chemistry. 2026;98(30):22043-22052. doi:10.1021/acs.analchem.5c08200
BibTeX
@article{Chen2026,
author = {Chen, Ziwei and Li, Jingyi and Wei, Qiushi and Zhang, Liangzhe and Luo, Siyu and Jin, Jiayue and Zhang, Zhe and Liu, Chao},
title = {ApuShape: Human-in-the-Loop Annotation Software for Fluorescent Nuclei Segmentation},
journal = {Analytical Chemistry},
year = {2026},
volume = {98},
number = {30},
pages = {22043--22052},
doi = {10.1021/acs.analchem.5c08200}
}
EUVIMED