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

AI-driven digital holographic microscopy for label-free quantitative cellular analysis: toward low-cost and field-deployable platforms.

Biomedical optics express·2026
Same author

Morphological investigation of astrocyte brain cells using quantitative phase imaging.

Biomedical optics express·2026
Same author

Security authentication and tracking of unmanned moving vehicles with optical ID tags.

Optics express·2026
Same author

3D profilometric object detection in turbid water using integral imaging and deep neural networks.

Optics express·2026
Same author

Underwater multidimensional metrology in degraded environments with augmented reality devices.

Optics express·2026
Same author

Dynamic vision-based underwater optical signal detection system in a degraded environment using multi-dimensional integral imaging and deep learning.

Optics express·2026

Related Experiment Video

Updated: Sep 11, 2025

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

12.1K

Automated lensless blood sample identification through scattering media using deep learning architectures.

Gaurav Gupta, Rakesh Joshi, Saurabh Goswami

    Optics Express
    |August 13, 2025
    PubMed
    Summary
    This summary is machine-generated.

    A new lensless imaging system uses deep learning to non-invasively identify red blood cells in smeared blood samples, even through scattering materials. This portable device shows high accuracy and potential for low-cost, field-based diagnostics.

    More Related Videos

    A Rapid and Chemical-free Hemoglobin Assay with Photothermal Angular Light Scattering
    05:18

    A Rapid and Chemical-free Hemoglobin Assay with Photothermal Angular Light Scattering

    Published on: December 7, 2016

    9.8K
    Measuring Spatially- and Directionally-varying Light Scattering from Biological Material
    11:57

    Measuring Spatially- and Directionally-varying Light Scattering from Biological Material

    Published on: May 20, 2013

    13.6K

    Related Experiment Videos

    Last Updated: Sep 11, 2025

    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

    12.1K
    A Rapid and Chemical-free Hemoglobin Assay with Photothermal Angular Light Scattering
    05:18

    A Rapid and Chemical-free Hemoglobin Assay with Photothermal Angular Light Scattering

    Published on: December 7, 2016

    9.8K
    Measuring Spatially- and Directionally-varying Light Scattering from Biological Material
    11:57

    Measuring Spatially- and Directionally-varying Light Scattering from Biological Material

    Published on: May 20, 2013

    13.6K

    Area of Science:

    • Biomedical optics
    • Machine learning in healthcare
    • Cellular imaging and analysis

    Background:

    • Traditional biological screening methods can be invasive and require complex laboratory setups.
    • Lensless imaging combined with deep learning offers a promising avenue for simplified, non-invasive biological analysis.
    • Automated cell identification is crucial for efficient and accurate disease diagnosis.

    Purpose of the Study:

    • To develop and validate a field-portable, compact lensless system for non-invasive detection and classification of whole blood samples.
    • To assess the system's performance in identifying red blood cell types through scattering media.
    • To evaluate the robustness of the system against variations in scattering layer thickness.

    Main Methods:

    • A lensless optical system utilizing a laser diode and image sensor to capture opto-biological signatures of blood samples.
    • Samples were placed between two layers of scattering media to simulate challenging imaging conditions.
    • Local Binary Pattern (LBP) transformation and Convolutional Neural Networks (CNNs) including AlexNet, VGG-16, and SqueezeNet were employed for image analysis and classification, compared against PCA+SVM.

    Main Results:

    • The lensless system successfully detected and classified red blood cells through scattering media.
    • SqueezeNet and VGG-16 CNN architectures achieved the highest classification accuracy (up to 97.2%) and Matthew's Correlation Coefficient (MCC) scores (up to 0.96).
    • VGG-16 demonstrated superior robustness, maintaining high accuracy as scattering layer thickness increased up to three times the training value.

    Conclusions:

    • This work presents a proof-of-concept for non-invasive blood sample identification using lensless devices and deep learning through scattering media.
    • The developed system is low-cost, field-portable, and offers high identification accuracy, indicating potential as a viable diagnostic device.
    • The study highlights the effectiveness of deep learning models like SqueezeNet and VGG-16 in analyzing complex opto-biological signatures from lensless imaging.