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

Impact of Several Green Manure Species on the Physicochemical Characteristics, Enzymatic Activities, and Microbial Community Composition of Soils Under Protected Cultivation.

Plants (Basel, Switzerland)·2026
Same author

Itaconate Ameliorates Skin Fibrosis Through Inhibition of HIF-1α/LDHA-Driven Aerobic Glycolysis.

Antioxidants & redox signaling·2026
Same author

Mechanisms and disease associations of oxidative stress-mediated brain-bone axis dysregulation: a knowledge mapping and trend analysis based on Bibliometrics.

Frontiers in aging neuroscience·2026
Same author

Fractional analysis of a coupled dual-capacitance neuronal model with state-wise surrogate neural networks.

Neural networks : the official journal of the International Neural Network Society·2026
Same author

Optimizing Ecological Restoration in Alpine Mining Areas Through Fertilization and Seeding-Rate Management: Insights from Vegetation-Soil Stoichiometry.

Plants (Basel, Switzerland)·2026
Same author

Spent Mushroom Substrate Reused as Organic Fertilizer Enhances Lettuce (<i>Lactuca sativa</i> L.) Quality and Soil Nutrients: Insights from Physicochemical and Microbiome Analyses.

Microorganisms·2026

Related Experiment Video

Updated: Jan 3, 2026

Fully Automated Centrifugal Microfluidic Device for Ultrasensitive Protein Detection from Whole Blood
08:58

Fully Automated Centrifugal Microfluidic Device for Ultrasensitive Protein Detection from Whole Blood

Published on: April 16, 2016

10.9K

A Quantized CNN-Based Microfluidic Lensless-Sensing Mobile Blood-Acquisition and Analysis System.

Yumin Liao1, Ningmei Yu1, Dian Tian1

  • 1School of Automation and Information Engineering, Xi'an University of Technology, Xi'an 710000, China.

Sensors (Basel, Switzerland)
|November 27, 2019
PubMed
Summary

This study introduces a mobile system for blood analysis using microfluidics and lensless sensing. An integer-only quantization algorithm enables accurate, miniaturized, and power-efficient artificial intelligence (AI) blood cell analysis on portable devices.

Keywords:
CNNblood analysislensless sensingmicrofluidic chipquantization scheme

More Related Videos

Wide-field Fluorescent Microscopy and Fluorescent Imaging Flow Cytometry on a Cell-phone
06:42

Wide-field Fluorescent Microscopy and Fluorescent Imaging Flow Cytometry on a Cell-phone

Published on: April 11, 2013

24.0K
Lensless On-chip Imaging of Cells Provides a New Tool for High-throughput Cell-Biology and Medical Diagnostics
08:19

Lensless On-chip Imaging of Cells Provides a New Tool for High-throughput Cell-Biology and Medical Diagnostics

Published on: December 14, 2009

12.3K

Related Experiment Videos

Last Updated: Jan 3, 2026

Fully Automated Centrifugal Microfluidic Device for Ultrasensitive Protein Detection from Whole Blood
08:58

Fully Automated Centrifugal Microfluidic Device for Ultrasensitive Protein Detection from Whole Blood

Published on: April 16, 2016

10.9K
Wide-field Fluorescent Microscopy and Fluorescent Imaging Flow Cytometry on a Cell-phone
06:42

Wide-field Fluorescent Microscopy and Fluorescent Imaging Flow Cytometry on a Cell-phone

Published on: April 11, 2013

24.0K
Lensless On-chip Imaging of Cells Provides a New Tool for High-throughput Cell-Biology and Medical Diagnostics
08:19

Lensless On-chip Imaging of Cells Provides a New Tool for High-throughput Cell-Biology and Medical Diagnostics

Published on: December 14, 2009

12.3K

Area of Science:

  • Biomedical Engineering
  • Computer Engineering
  • Artificial Intelligence

Background:

  • Traditional blood analysis systems are often large, expensive, and require specialized laboratory settings.
  • There is a growing need for portable, cost-effective solutions for rapid blood cell acquisition and analysis, particularly for early disease detection.

Purpose of the Study:

  • To develop a mobile microfluidic lensless-sensing system for blood cell acquisition and analysis.
  • To optimize the system for accuracy, miniaturization, and power efficiency using an integer-only quantization algorithm for convolutional neural networks (CNNs).

Main Methods:

  • Proposed an integer-only quantization algorithm for CNN inference, enabling hardware implementation with reduced area and power consumption.
  • Developed a dual configuration register group structure to enhance CNN processing efficiency.
  • Designed and implemented a CNN accelerator on Field-Programmable Gate Arrays (FPGAs).
  • Integrated the CNN accelerator with a microfluidic chip and a mobile lensless sensing device to create a prototype system.

Main Results:

  • The prototype system achieved a cell classification accuracy of 98.44%, with only a 0.56% drop compared to floating-point methods.
  • The hardware area was reduced by 45% due to the integer-only quantization.
  • The system achieved a classification speed of 17.9 frames per second (fps) at 100 MHz on the FPGA.

Conclusions:

  • The developed quantized CNN microfluidic lensless-sensing system meets the requirements for portable medical devices.
  • This technology facilitates the transition of AI-based blood analysis from large servers to portable devices for rapid early disease detection.