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 Comparative Study of Machine Learning Models for Identification of Antiviral Peptides Using Various Encoded Features.

IEEE transactions on computational biology and bioinformatics·2026
Same author

K-SNOpred: Identification of protein S-nitrosylation sites through word embedding features and machine learning.

Analytical biochemistry·2025
Same author

BitterEN: A novel ensemble model for the identification of bitter peptide.

Computers in biology and medicine·2025
Same author

DHUpredET: A comparative computational approach for identification of dihydrouridine modification sites in RNA sequence.

Analytical biochemistry·2025
Same author

A robust deep learning approach for identification of RNA 5-methyluridine sites.

Scientific reports·2024
Same author

MLAFP-XN: Leveraging neural network model for development of antifungal peptide identification tool.

Heliyon·2024

Related Experiment Video

Updated: Jan 14, 2026

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

12.0K

ReVGG-R2Net: Optimized recurrent framework for microscopic blood cell segmentation.

Mst Shapna Akter1, Md Fahim Sultan1, Tasmin Karim1

  • 1Department of Computer Science and Engineering, Oakland University, Rochester, MI 48309, USA.

Tissue & Cell
|October 19, 2025
PubMed
Summary
This summary is machine-generated.

A new model, ReVGG-R2Net, precisely segments diverse microscopic blood cells, even when crowded. This blood cell segmentation advance uses a novel architecture and a new dataset, RaabinWBCSeg, for improved biomedical analysis.

Keywords:
Biomedical analysisDeep learningLeukocytesMicroscopic blood cellSegmentationVGG16

More Related Videos

Controlled Microfluidic Environment for Dynamic Investigation of Red Blood Cell Aggregation
10:27

Controlled Microfluidic Environment for Dynamic Investigation of Red Blood Cell Aggregation

Published on: June 4, 2015

12.3K
Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments
07:46

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Published on: April 30, 2021

5.4K

Related Experiment Videos

Last Updated: Jan 14, 2026

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone
09:31

Automated Quantification of Hematopoietic Cell – Stromal Cell Interactions in Histological Images of Undecalcified Bone

Published on: April 8, 2015

12.0K
Controlled Microfluidic Environment for Dynamic Investigation of Red Blood Cell Aggregation
10:27

Controlled Microfluidic Environment for Dynamic Investigation of Red Blood Cell Aggregation

Published on: June 4, 2015

12.3K
Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments
07:46

Microfluidic Co-Culture Models for Dissecting the Immune Response in in vitro Tumor Microenvironments

Published on: April 30, 2021

5.4K

Area of Science:

  • Medical Imaging
  • Computational Biology
  • Biomedical Engineering

Background:

  • Accurate microscopic blood cell segmentation is vital for biomedical analysis and diagnostics.
  • Existing models struggle with diverse cell types and densely packed cells, limiting fine detail capture.

Purpose of the Study:

  • To introduce ReVGG-R2Net, a novel model for precise blood cell segmentation.
  • To address limitations in dataset diversity and cellular detail capture in current segmentation models.
  • To present RaabinWBCSeg, a comprehensive dataset for blood cell segmentation tasks.

Main Methods:

  • Developed ReVGG-R2Net, integrating recurrent blocks in encoder/decoder for enhanced feature refinement.
  • Utilized a modified VGG16 backbone with recurrent features in the encoder.
  • Employed an R2U-Net-based decoder with recurrent feature fusion for improved accuracy in dense regions.
  • Introduced the RaabinWBCSeg dataset with diverse uninfected and infected cell types.

Main Results:

  • ReVGG-R2Net demonstrated state-of-the-art (SOTA) performance across five benchmark datasets, including RaabinWBCSeg and BBBC041Seg.
  • The model effectively captures intricate cellular structures and improves segmentation accuracy in densely packed cell regions.
  • The RaabinWBCSeg dataset enhances model generalization for blood cell segmentation tasks.

Conclusions:

  • ReVGG-R2Net offers a significant advancement in blood cell image segmentation.
  • The proposed model and dataset contribute to more accurate and generalized biomedical analysis.
  • This work paves the way for improved diagnostics through enhanced microscopic image analysis.