EUVIMEDEUVIMED entdecken
Crossref

DL-CSPF: deep-learning-based cell segmentation with a physical framework for digital holographic microscopy

Zhuoshi Li, Haojie Gu, Linpeng Lu, Qian Shen, Jiasong Sun, Qian Chen, Chao Zuo

Applied Optics · 01.03.2025 · 64 (7) · B20

DOI: 10.1364/ao.546044 ↗

Kurz gefasst

Fachartikel in der Zeitschrift Applied Optics, online erschienen am 06.12.2024. Verfasst von Zhuoshi Li und 6 weiteren Autor:innen. Hauptthemen laut MEDLINE: Holography, Microscopy, Deep Learning, Image Processing, Computer-Assisted. Die Arbeit wurde bisher 11-mal zitiert (Crossref) und nennt 79 Literaturangaben. Gefördert von: National Key Research and Development Program of China, National Natural Science Foundation of China, Leading Technology of Jiangsu Basic Research Plan.

AbstractSchlagwörterBibliografische AngabenZitierenVerwandte Studien

Abstract (Originalsprache)

Digital holographic microscopy (DHM) offers label-free, full-field imaging of live-cell samples by capturing optical path differences to produce quantitative phase images. Accurate cell segmentation from phase images is crucial for long-term quantitative analysis. However, complicated cellular states (e.g., cell adhesion, proliferation, and apoptosis) and imaging conditions (e.g., noise and magnification) pose significant challenge to the accuracy of cell segmentation. Here, we introduce DL-CSPF, a deep-learning-based cell segmentation method with a physical framework designed for high-precision live-cell analysis. DL-CSPF utilizes two neural networks for foreground-background segmentation and cell detection, generating foreground edges and “seed points.” These features serve as input for a marker-controlled watershed algorithm to segment cells. By focusing on foreground edges and “seed points”, which have lower information entropy than complete cell contours, DL-CSPF achieves accurate segmentation with a reduced dataset and without manual parameter tuning. We validated the feasibility and generalization of DL-CSPF using various open-source and DHM-collected datasets, including HeLa, pollen, and COS-7 cells. Long-term live-cell imaging results further demonstrate that DL-CSPF reliably characterized and quantitatively analyzed the morphological metrics across the cellular lifecycle, rendering it a promising tool for biomedical research.

Schlagwörter

MeSH-Schlagwörter (MEDLINE)

HolographyMicroscopyDeep LearningImage Processing, Computer-AssistedHumansAnimalsHeLa CellsAlgorithmsChlorocebus aethiopsCOS CellsPollenNeural Networks, ComputerQuantitative Phase Imaging

Förderung

  • National Key Research and Development Program of China
  • National Natural Science Foundation of China
  • Leading Technology of Jiangsu Basic Research Plan
  • Youth Foundation of Jiangsu Province
  • Biomedical Competition Foundation of Jiangsu Province
  • Key National Industrial Technology Cooperation Foundation of Jiangsu Province
  • Fundamental Research Funds for the Central Universities
  • Open Research Fund of Jiangsu Key Laboratory of Spectral Imaging & Intelligent Sense

Zitieren

APA

Li, Z., Gu, H., Lu, L., Shen, Q., Sun, J., Chen, Q., & Zuo, C. (2025). DL-CSPF: deep-learning-based cell segmentation with a physical framework for digital holographic microscopy. Applied Optics, 64(7), B20. https://doi.org/10.1364/ao.546044

Vancouver

Li Z, Gu H, Lu L, Shen Q, Sun J, Chen Q, et al. DL-CSPF: deep-learning-based cell segmentation with a physical framework for digital holographic microscopy. Applied Optics. 2025;64(7):B20. doi:10.1364/ao.546044

BibTeX
@article{Li2025,
  author = {Li, Zhuoshi and Gu, Haojie and Lu, Linpeng and Shen, Qian and Sun, Jiasong and Chen, Qian and Zuo, Chao},
  title = {DL-CSPF: deep-learning-based cell segmentation with a physical framework for digital holographic microscopy},
  journal = {Applied Optics},
  year = {2025},
  volume = {64},
  number = {7},
  pages = {B20},
  doi = {10.1364/ao.546044}
}
Kostenlos starten →