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

Longitudinal magnetic resonance spectroscopy study of metabolite changes over 2 years in relapsing and primary progressive multiple sclerosis treated with ocrelizumab.

Multiple sclerosis (Houndmills, Basingstoke, England)·2026
Same author

Myelin damage in radiologically isolated syndrome is associated with decreased processing speed.

Multiple sclerosis journal - experimental, translational and clinical·2026
Same author

Machine learning to predict survival in patients treated for hepatocellular carcinoma: a systematic review.

American journal of surgery·2026
Same author

Generalizable spinal cord multiple sclerosis lesion segmentation across MRI contrasts, protocols, and centers.

Multiple sclerosis (Houndmills, Basingstoke, England)·2026
Same author

Monitoring morphometric drift in lifelong learning segmentation of the spinal cord.

Imaging neuroscience (Cambridge, Mass.)·2026
Same author

Correlations of myelin, axon, and inflammation metrics from multi echo T<sub>2</sub> relaxation and multi-shell diffusion imaging in multiple sclerosis and healthy controls.

Multiple sclerosis and related disorders·2025

Related Experiment Video

Updated: Nov 27, 2025

Author Spotlight: Developing a Tool for Using Inverted Confocal Microscopes for In Vivo Intravital Imaging
04:11

Author Spotlight: Developing a Tool for Using Inverted Confocal Microscopes for In Vivo Intravital Imaging

Published on: June 30, 2023

2.0K

Detecting cells in intravital video microscopy using a deep convolutional neural network.

Bruno C Gregório da Silva1, Roger Tam2, Ricardo J Ferrari1

  • 1Departamento de Computação, Universidade Federal de São Carlos, Washington Luís Rd., Km 235, 13.565-905, São Carlos, SP, Brazil.

Computers in Biology and Medicine
|December 7, 2020
PubMed
Summary

This study introduces an adapted RetinaNet model for precise leukocyte detection in intravital video microscopy (IVM) images. The method achieves high accuracy, even with limited data, improving inflammatory process analysis.

Keywords:
Cell detectionConvolutional neural networkDeep learningLeukocyte recruitment

More Related Videos

Imaging Cell Interaction in Tracheal Mucosa During Influenza Virus Infection Using Two-photon Intravital Microscopy
08:01

Imaging Cell Interaction in Tracheal Mucosa During Influenza Virus Infection Using Two-photon Intravital Microscopy

Published on: August 17, 2018

8.6K
Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.2K

Related Experiment Videos

Last Updated: Nov 27, 2025

Author Spotlight: Developing a Tool for Using Inverted Confocal Microscopes for In Vivo Intravital Imaging
04:11

Author Spotlight: Developing a Tool for Using Inverted Confocal Microscopes for In Vivo Intravital Imaging

Published on: June 30, 2023

2.0K
Imaging Cell Interaction in Tracheal Mucosa During Influenza Virus Infection Using Two-photon Intravital Microscopy
08:01

Imaging Cell Interaction in Tracheal Mucosa During Influenza Virus Infection Using Two-photon Intravital Microscopy

Published on: August 17, 2018

8.6K
Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations
13:13

Time-Lapse Imaging of Neuronal Arborization using Sparse Adeno-Associated Virus Labeling of Genetically Targeted Retinal Cell Populations

Published on: March 19, 2021

3.2K

Area of Science:

  • Biomedical Imaging
  • Computational Biology
  • Immunology

Background:

  • Leukocyte recruitment analysis via intravital video microscopy (IVM) is crucial for understanding inflammation.
  • Conventional methods struggle with the visual complexity of IVM images, hindering precise cell detection and counting.
  • Limited availability of labeled datasets impedes the application of deep learning for IVM cell analysis.

Purpose of the Study:

  • To develop and evaluate an adapted RetinaNet model for accurate leukocyte detection in IVM data.
  • To address the challenge of limited labeled data using augmentation and transfer learning techniques.
  • To compare the performance of the proposed model against traditional image processing methods.

Main Methods:

  • Adaptation of the RetinaNet model incorporating advanced augmentation techniques (Airy pattern, motion artifacts, photometric, geometric, elastic transformations).
  • Utilized transfer learning and analyzed variations in network backbones, feature pyramid levels, and input scales.
  • Evaluated model performance using the average precision (AP) metric and compared cell counting and centroid distance errors with existing tools.

Main Results:

  • The adapted RetinaNet model achieved a high average precision (AP) of 94.84% across different image modalities.
  • The strategy effectively trained the model without overfitting, enhancing generalization performance despite limited data.
  • Demonstrated superior precision and lower error rates in cell counting and centroid distances compared to conventional image processing techniques and open-source tools.

Conclusions:

  • The proposed RetinaNet adaptation offers a robust and accurate solution for leukocyte detection in IVM.
  • The employed augmentation and transfer learning strategies successfully overcome data limitations in microscopy image analysis.
  • This approach significantly advances the quantitative analysis of inflammatory processes through improved cell detection and counting.