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

Ultrarapid Kinetic Antimicrobial Susceptibility Testing from Blood Using Single-Cell Scattering Phenotypic Imaging.

ACS sensors·2026
Same author

CRISPR/Cas12a2-Mediated Ultrasensitive Assay for Rapid Detection of H1N1 Influenza Virus RNA.

ACS omega·2026
Same author

Virion display reveals MD-1 as an endogenous agonist for the orphan receptor GPRC5B.

Science signaling·2026
Same author

CRISPR-Cas12a2-Based Multiplexed Diagnostic for Rapid and Highly Sensitive Detection of Respiratory Viruses.

Analytical chemistry·2026
Same author

Evaluating Antibody Quality via Simultaneous Size and Charge Measurement with Single Protein Oscillators.

Analytical chemistry·2026
Same author

Leveraging Naturalistic Driving Digital Biomarkers for Early Mild Cognitive Impairment Detection: Deep Learning Strategies.

JMIR medical informatics·2026

Related Experiment Video

Updated: May 28, 2026

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

Machine Learning-Assisted Rapid Optical Imaging for Label-Free CAR T-Cell Detection in Whole Blood.

Nanxi Yu1,2, Ryan M Porter1,3, Xinyu Zhou1,4

  • 1Center for Biosensors and Bioelectronics, The Biodesign Institute, Arizona State University, Tempe, AZ 85287, USA.

Biosensors
|May 26, 2026
PubMed
Summary

A new biosensor quantifies CAR T-cells in whole blood using optical imaging and machine learning. This technology offers real-time monitoring for improved chimeric antigen receptor T-cell therapy outcomes.

Keywords:
CAR Tagglutinationchimeric antigen receptor T-cellsdigital countingmachine learningmicrofluidic chipobject classificationoptical imagingwhole blood

More Related Videos

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology
08:27

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Published on: March 24, 2015

Field-Deployable Lens-Free Imaging Platform for Rapid Label-Free Analysis of Natural Killer Cell Activation
08:34

Field-Deployable Lens-Free Imaging Platform for Rapid Label-Free Analysis of Natural Killer Cell Activation

Published on: August 8, 2025

Related Experiment Videos

Last Updated: May 28, 2026

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning
08:58

Label-Free Identification of Lymphocyte Subtypes Using Three-Dimensional Quantitative Phase Imaging and Machine Learning

Published on: November 19, 2018

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology
08:27

Detection of Human Leukocyte Antigen Biomarkers in Breast Cancer Utilizing Label-free Biosensor Technology

Published on: March 24, 2015

Field-Deployable Lens-Free Imaging Platform for Rapid Label-Free Analysis of Natural Killer Cell Activation
08:34

Field-Deployable Lens-Free Imaging Platform for Rapid Label-Free Analysis of Natural Killer Cell Activation

Published on: August 8, 2025

Area of Science:

  • Biomedical Engineering
  • Immunology
  • Medical Diagnostics

Background:

  • Chimeric antigen receptor (CAR) T-cell therapy shows promise for hematologic malignancies but faces challenges including high costs, severe toxicities, and variable patient responses.
  • Current monitoring relies on subjective assessments and basic tests, lacking real-time, quantitative evaluation of CAR T-cell activity, which hinders personalized care and increases costs.

Purpose of the Study:

  • To develop and validate a label-free, rapid optical imaging (ROI) biosensor integrated with machine learning for direct quantification of CAR T-cells in whole blood.
  • To provide a timely, quantitative immune monitoring tool to overcome limitations in current CAR T-cell therapy management.

Main Methods:

  • A microfluidic platform was designed for red blood cell (RBC) removal, CAR T-cell capture, and imaging-based quantification on a single chip.
  • Whole blood samples spiked with CAR T-cells underwent RBC depletion, followed by incubation on a sensor chip functionalized with target antigen.
  • Captured CAR T-cells were imaged using brightfield microscopy and enumerated by a machine learning algorithm trained on fluorescence-validated cells.

Main Results:

  • The machine learning model achieved 88% sensitivity and 96% specificity for CAR T-cell detection.
  • High correlations (R² = 0.975 and 0.990) were observed between spiked concentrations and detected CAR T-cells in buffer and whole blood.
  • The limit of quantification (LOQ) for whole blood was determined to be 67 cells/µL with 95% certainty.

Conclusions:

  • The label-free ROI biosensor with automated machine learning analysis offers a proof-of-concept for direct, quantitative monitoring of CAR T-cells in whole blood.
  • This technology has the potential to enable real-time immune monitoring, facilitating individualized patient care and potentially reducing treatment costs associated with CAR T-cell therapy.