Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A survey on the anxiety status of adolescents in minority concentration areas of Western Hunan-three years after the onset of the COVID-19 pandemic.

Frontiers in public health·2025
Same author

Rhizosphere as hotspot for ammonia oxidation in secondary effluent constructed wetlands: Role of comammox Nitrospira.

Bioresource technology·2025
Same author

High-entropy sulfoselenide as negative electrodes with fast kinetics and high stability for sodium-ion batteries.

Nature communications·2025
Same author

Facile generation of drug-like conformational antibodies specific for amyloid fibrils.

Nature chemical biology·2025
Same author

Homocysteine-Responsive Covalent Organic Frameworks as Signaling Scaffolds: Modulating Transsulfuration for Depression Treatment.

Small (Weinheim an der Bergstrasse, Germany)·2025
Same author

Enhanced room-temperature detection of ultra-low level nitrogen dioxide: Improved sensitivity, selectivity and stability through MXene-modified In<sub>2</sub>O<sub>3</sub> microspheres.

Talanta·2025

Related Experiment Video

Updated: Dec 19, 2025

Microfluidic Imaging Flow Cytometry by Asymmetric-detection Time-stretch Optical Microscopy ATOM
07:19

Microfluidic Imaging Flow Cytometry by Asymmetric-detection Time-stretch Optical Microscopy ATOM

Published on: June 28, 2017

10.7K

Fast intelligent cell phenotyping for high-throughput optofluidic time-stretch microscopy based on the XGBoost

Wanyue Zhao1, Yingxue Guo1, Sigang Yang1

  • 1Tsinghua University, Beijing National Research Center for Information Science and Technology, Depart, China.

Journal of Biomedical Optics
|June 5, 2020
PubMed
Summary

This study introduces an intelligent cell phenotyping framework using XGBoost for rapid and accurate cell image classification in high-throughput optofluidic microscopy. The system achieves over 97% accuracy, processing 3000 cells per second.

Keywords:
automatic cell detectionimaging cytometrymachine learningtime-stretch microscopy

More Related Videos

Design and Implementation of an Automated Illuminating, Culturing, and Sampling System for Microbial Optogenetic Applications
11:13

Design and Implementation of an Automated Illuminating, Culturing, and Sampling System for Microbial Optogenetic Applications

Published on: February 19, 2017

10.0K
Rapid Analysis and Exploration of Fluorescence Microscopy Images
11:41

Rapid Analysis and Exploration of Fluorescence Microscopy Images

Published on: March 19, 2014

12.6K

Related Experiment Videos

Last Updated: Dec 19, 2025

Microfluidic Imaging Flow Cytometry by Asymmetric-detection Time-stretch Optical Microscopy ATOM
07:19

Microfluidic Imaging Flow Cytometry by Asymmetric-detection Time-stretch Optical Microscopy ATOM

Published on: June 28, 2017

10.7K
Design and Implementation of an Automated Illuminating, Culturing, and Sampling System for Microbial Optogenetic Applications
11:13

Design and Implementation of an Automated Illuminating, Culturing, and Sampling System for Microbial Optogenetic Applications

Published on: February 19, 2017

10.0K
Rapid Analysis and Exploration of Fluorescence Microscopy Images
11:41

Rapid Analysis and Exploration of Fluorescence Microscopy Images

Published on: March 19, 2014

12.6K

Area of Science:

  • Biomedical Engineering
  • Computational Biology
  • Microscopy

Background:

  • Optofluidic time-stretch flow cytometry offers extreme-throughput cell imaging.
  • Processing the vast amounts of data generated by this technique presents a significant challenge.
  • High-speed identification and classification of cell images are crucial for data analysis.

Purpose of the Study:

  • To develop an intelligent cell phenotyping framework for high-throughput optofluidic time-stretch microscopy.
  • To enable rapid and accurate classification of cell images using advanced machine learning algorithms.
  • To address the data processing bottleneck in high-throughput cell imaging.

Main Methods:

  • An image recognition pipeline was developed, incorporating density-based spatial clustering with noise outlier detection.
  • Histograms of oriented gradients combined with gray histogram fused features were utilized.
  • The XGBoost algorithm was employed for rapid and accurate cell image classification.

Main Results:

  • The XGBoost-based framework achieved over 97% accuracy in classifying cell images.
  • The system demonstrated a classification frequency of 3000 cells per second.
  • Performance was validated against existing algorithms using datasets from over 20,000 drug-treated and untreated cells.

Conclusions:

  • The proposed XGBoost framework offers a promising solution for processing large volumes of flow image data.
  • This work lays the groundwork for advanced cell sorting and clinical applications of high-throughput imaging cytometry.
  • The developed framework enhances the efficiency and accuracy of cell phenotyping in high-throughput imaging systems.