Deep learning-assisted high-accuracy cell segmentation method for live-cell analysis in digital holographic microscopy

Gu Haojie; Zhuoshi Li; Qian Shen

doi:10.1117/12.3036800

3 January 2025 Deep learning-assisted high-accuracy cell segmentation method for live-cell analysis in digital holographic microscopy

Gu Haojie, Zhuoshi Li, Qian Shen

Author Affiliations +

Proceedings Volume 13240, Holography, Diffractive Optics, and Applications XIV; 1324019 (2025) https://doi.org/10.1117/12.3036800
Event: SPIE/COS Photonics Asia, 2024, Nantong, Jiangsu, China

Abstract

Quantitative phase imaging (QPI) is a valuable tool for investigating weakly absorbing specimens, such as cells and tissues. Digital holographic microscopy (DHM), as a classical QPI technique, enables non-invasive, long-term observation of living cells for cell segmentation and further analysis. In this work, we propose a deep learning-assisted high-accuracy cell segmentation method (DL-HACS) for long-term quantitative live-cell analysis with DHM. In DL-HACS, we employed two distinct deep learning models to independently obtain the foreground segmentation and centroid detection results of cells. Thereafter, the amalgamation of these results via the watershed algorithm culminated in the final cell segmentation outcomes. This methodology excels in navigating complex cellular scenarios, such as cell adhesion, cell division and apoptosis, by providing superior accuracy of segmentation in comparison to traditional approaches. It circumvents the necessity for manuallycrafted feature definitions, thereby diminishing the expertise dependency. Additionally, DL-HACS stands in stark contrast to conventional deep learning techniques by markedly reducing the computational expenditure and the complexity of the learning process. Concurrently, it augments the accuracy of segmenting adherent cells, achieving improvements with even modestly sized datasets.

(2025) Published by SPIE. Downloading of the abstract is permitted for personal use only.

Citation Download Citation

Gu Haojie, Zhuoshi Li, and Qian Shen "Deep learning-assisted high-accuracy cell segmentation method for live-cell analysis in digital holographic microscopy", Proc. SPIE 13240, Holography, Diffractive Optics, and Applications XIV, 1324019 (3 January 2025); https://doi.org/10.1117/12.3036800

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

;

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available

Members: $17.00

Non-members: $21.00 ADD TO CART

PROCEEDINGS
9 PAGES

DOWNLOAD PAPER SAVE TO MY LIBRARY

GET CITATION

RIGHTS & PERMISSIONS

Get copyright permission Get copyright permission on Copyright Marketplace

KEYWORDS

Image segmentation

Digital holography

Deep learning

Education and training

Biological research

Holography

Microscopy

Show All Keywords

Keywords/Phrases

Search In:

Publication Years