This site requires Cookies enabled in your browser for login.
Updating ...
WaterNet Home
WaterNet
for
pour le
Canada
Menu
WaterNet
Home
GWFO
Home
Catalogue
Master Index
Data
Centre
X
Find Data By Variable Find Data By Site, Facility, or Deployable Show Near-realtime Telemetry (7 day)
Collections
X
Defaults
Select All
Websites
X
Global Water Futures Observatories (GWFO) Global Water Futures (GWF) Global Institute for Water Security (GIWS) International Network of Alpine Research Catchment Hydrology
Legacy Research Programs
X
Changing Cold Regions Network (CCRN) Drought Research Initiative (DRI) International Network of Alpine Research Catchment Hydrology (Legacy Site) Improving Processes & Parameterization for Prediction in Cold Regions Hydrology (IP3) The Mackenzie Global Energy and Water Cycle Experiment (GEWEX) Study (MAGS)
Legacy sites
Map
Utilities
X
Account Settings Create a New Record Record List Alias List Editor
Edit Data Centre
Data Types
. . .
X
Clear
Select All
Advanced Search
Go to Top⇡
Related items loading ...
Fetching Chart ...
Publication Additional Information Download
Publication Type
Journal Article
Authorship
Hong T., Peng M., Kim Y., Schellhorn H. E., Fang Q.
Title
Automated cell profiling in imaging flow cytometry with annotation-efficient learning
Year
2025
Publication Outlet
Optics & Laser Technology, Vol 181, Pg 111992
DOI
https://doi.org/10.1016/j.optlastec.2024.111992
ISSN
0030-3992
Citation
Hong T., Peng M., Kim Y., Schellhorn H. E., Fang Q. (2025) Optics & Laser Technology, Vol 181, Pg 111992, Issn 0030-3992, https://doi.org/10.1016/j.optlastec.2024.111992
Abstract
Image-based cell profiling offers high-quality profiles (i.e., morphological phenotype) after high-throughput microscopic image acquisition. It requires large-scale image analysis and processing ability, and deep learning has recently demonstrated outstanding performance in this field. However, deep learning heavily relies on conventional manual annotation, which becomes a critical bottleneck for the entire profiling workflow. This study develops an annotation-efficient self-supervised active learning pipeline for images acquired by high throughput imaging flow cytometry. First, a fitting pretext task using optical flow and variational autoencoder algorithms is proposed to pre-train the model. The supervisory is derived from the motion cues of cells with zero manual annotation. Then, an active learning cycle selects a small set of samples to annotate, which iteratively achieves an optimal performance with fewer annotated samples. The sample selection criteria consider informativeness and representativeness from static and spatiotemporal features. Once one cell is selected to annotate, it is removed from the unannotated data pool, further reducing human effort. The pipeline is used for a lensless optofluidic imaging flow cytometry and experimentally evaluated by testing three components of biological samples in urinalysis (erythrocytes, leukocytes, and budding yeasts). It shows comparable performance but with only an average of 30–40% annotation workload compared with fully supervised training. The generated image-based profiles can be used for downstream analysis. These results indicate that the proposed training pipeline yields high performance and efficiently decreases the annotation burden for implementing deep learning in image-based cell profiling.
Program Affiliations
GWF: Global Water Futures
GWFO: Global Water Futures Observatories
Publication Stage
Published
Additional Information
Keywords: Annotation-efficient, Self-supervised, Active learning, Optical flow, Spatiotemporal feature
Download Links
https://doi.org/10.1016/j.optlastec.2024.111992
© 2026 - WaterNet Version 2026-09-12
Global Water Futures Observatories
Powered by
G W F Net
T-2025-09-09-R1Cuc8v1f3kCzpXh5glk4Sg Publication 1.0