EUVIMEDEUVIMED entdecken
Crossref

CellApop: A knowledge-guided decoupled distillation framework for label-efficient apoptotic cell segmentation and dynamic analysis in brightfield microscopy

Chi Dong, Xuan Xie, Shuai Yue, Wei Ba, Wanming Li, Guangzhu Zhang, Xinmeng Rong, Hua Ai, Jin Fang, Xiran Jiang

Computer Methods and Programs in Biomedicine · 2026

DOI: 10.1016/j.cmpb.2025.109156 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Computer Methods and Programs in Biomedicine, 2026. Verfasst von Chi Dong und 9 weiteren Autor:innen. Beteiligte Einrichtung: School of Intelligent Medicine, China Medical University, Liaoning 110122, PR China. Hauptthemen laut MEDLINE: Apoptosis, Microscopy, Image Processing, Computer-Assisted. Die Arbeit nennt 41 Literaturangaben. Gefördert von: Department of Education of Liaoning Province, National Natural Science Foundation of China.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

BACKGROUND AND OBJECTIVE: Conventional apoptosis detection methods primarily depend on fluorescence staining, which is labor-intensive, potentially cytotoxic, and unsuitable for real-time monitoring. To overcome these limitations, this study presents a segmentation-based deep learning (DL) framework for label-free, dynamic detection of apoptotic cells in bright-field microscopy images. METHODS: A comprehensive training dataset comprising 16,472 bright-field cell images was curated from four sources-three public datasets (BF-C2DL-MuSC, DICC2DHHeLa, and LiveCell) and one proprietary apoptosis dataset. To achieve label-efficient learning, a Knowledge-guided Decoupled Distillation (KDD) framework was developed, wherein multiple expert models collectively guide the training of a lightweight student network, CellApop. The student model incorporates re-parameterization, depthwise separable convolutions, and an edge-aware module to improve segmentation accuracy under challenging conditions such as dense cellular overlap and indistinct boundaries. Performance was evaluated using the Dice similarity coefficient, Hausdorff Distance (HD), Intersection over Union (IoU), sensitivity, and specificity. Furthermore, CellApop was tested in an observer study for automated apoptosis-rate quantification across drug-treatment conditions, with its outputs compared against assessments by biological experts of varying experience levels. RESULTS: CellApop achieved Dice scores of 0.843 for general cells and 0.754 for apoptotic cells, while markedly reducing model complexity and inference latency. The KDD strategy decreased manual labeling requirements by approximately 80 % on the proprietary dataset. In the observer study, model-derived apoptosis rates demonstrated high concordance with ground truth and were comparable to a senior expert's performance, surpassing those of junior and intermediate experts-particularly at early time points when apoptotic morphology was subtle. CONCLUSIONS: The proposed CellApop framework delivers accurate, efficient, and label-free segmentation of apoptotic cells in bright-field microscopy, eliminating the need for fluorescent staining. Its robustness and scalability make it a promising tool for automated apoptosis quantification and drug-response assessment in routine experimental workflows.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

ApoptosisMicroscopyImage Processing, Computer-AssistedHumansDeep LearningAlgorithmsSoftware

Stichwörter der Autor:innen

Cell apoptosisKnowledge distillationMicroscopic imagesSegmentation

Autor:innen und Institutionen

  • School of Intelligent Medicine, China Medical University, Liaoning 110122, PR China.
  • Department of Cell Biology, Key Laboratory of Cell Biology, Key Laboratory of Medical Cell Biology, Ministry of Education, Ministry of Public Health, China Medical University, Shenyang 110122, PR China.
  • Department of Neurosurgery, Senior Department of Neurosurgery, the First Medical Center of PLA General Hospital, Beijing, 100010, PR China.
  • School of Intelligent Medicine, China Medical University, Liaoning 110122, PR China. Electronic address: hai@cmu.edu.cn.
  • Department of Cell Biology, Key Laboratory of Cell Biology, Key Laboratory of Medical Cell Biology, Ministry of Education, Ministry of Public Health, China Medical University, Shenyang 110122, PR China. Electronic addre…
  • School of Intelligent Medicine, China Medical University, Liaoning 110122, PR China. Electronic address: xrjiang@cmu.edu.cn.

Förderung

  • Department of Education of Liaoning Province
  • National Natural Science Foundation of China

Zitieren

APA

Dong, C., Xie, X., Yue, S., Ba, W., Li, W., Zhang, G., Rong, X., Ai, H., Fang, J., & Jiang, X. (2026). CellApop: A knowledge-guided decoupled distillation framework for label-efficient apoptotic cell segmentation and dynamic analysis in brightfield microscopy. Computer Methods and Programs in Biomedicine. https://doi.org/10.1016/j.cmpb.2025.109156

Vancouver

Dong C, Xie X, Yue S, Ba W, Li W, Zhang G, et al. CellApop: A knowledge-guided decoupled distillation framework for label-efficient apoptotic cell segmentation and dynamic analysis in brightfield microscopy. Computer Methods and Programs in Biomedicine. 2026. doi:10.1016/j.cmpb.2025.109156

BibTeX
@article{Dong2026,
  author = {Dong, Chi and Xie, Xuan and Yue, Shuai and Ba, Wei and Li, Wanming and Zhang, Guangzhu and Rong, Xinmeng and Ai, Hua and Fang, Jin and Jiang, Xiran},
  title = {CellApop: A knowledge-guided decoupled distillation framework for label-efficient apoptotic cell segmentation and dynamic analysis in brightfield microscopy},
  journal = {Computer Methods and Programs in Biomedicine},
  year = {2026},
  doi = {10.1016/j.cmpb.2025.109156}
}
Kostenlos starten →