Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Forecasting the eddying ocean with a deep neural network.

Nature communications·2025

Same author

An N-Shaped Lightweight Network with a Feature Pyramid and Hybrid Attention for Brain Tumor Segmentation.

Entropy (Basel, Switzerland)·2024

See all related articles

Search research articles

Related Experiment Video

Updated: Jun 14, 2025

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

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

Published on: April 8, 2015

CellRegNet: Point Annotation-Based Cell Detection in Histopathological Images via Density Map Regression.

Xu Jin¹, Hong An¹, Mengxian Chi¹

¹School of Computer Science and Technology, University of Science and Technology of China, Hefei 230000, China.

Bioengineering (Basel, Switzerland)

|August 29, 2024

Summary

CellRegNet enhances cell detection in histopathology images using deep learning. This novel model improves accuracy for multi-scale and multi-class cell identification from point annotations.

Keywords:

attention mechanism cell detection digital pathology

More Related Videos

Non-Destructive Evaluation of Regional Cell Density Within Tumor Aggregates Following Drug Treatment

Non-Destructive Evaluation of Regional Cell Density Within Tumor Aggregates Following Drug Treatment

Published on: June 21, 2022

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

Related Experiment Videos

Last Updated: Jun 14, 2025

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

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

Published on: April 8, 2015

Non-Destructive Evaluation of Regional Cell Density Within Tumor Aggregates Following Drug Treatment

Non-Destructive Evaluation of Regional Cell Density Within Tumor Aggregates Following Drug Treatment

Published on: June 21, 2022

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Area-based Image Analysis Algorithm for Quantification of Macrophage-fibroblast Cocultures

Published on: February 15, 2022

Area of Science:

Digital pathology
Computational biology
Deep learning applications

Background:

Deep learning shows promise for cell detection using density map regression with point annotations.
Existing models face challenges in multi-scale feature extraction and handling spatial priors in multi-class cell detection.

Purpose of the Study:

To introduce CellRegNet, a novel deep learning model for accurate cell detection using point annotations.
To address limitations in multi-scale feature integration and multi-class cell distribution modeling.

Main Methods:

CellRegNet employs a hybrid CNN/Transformer architecture with feature refinement and selection.
A contrastive regularization loss is introduced to model mutual exclusiveness priors in multi-class scenarios.

Main Results:

CellRegNet achieved high F1-scores: 86.38% on breast cancer (BCData), 85.56% on endometrial tissue (EndoNuke), and 93.90% on bone marrow cells (MBM).
The model demonstrated superior performance compared to state-of-the-art methods for cell detection using point annotations.

Conclusions:

CellRegNet effectively addresses challenges in multi-scale feature extraction and multi-class cell detection.
The proposed model significantly enhances the accuracy and reliability of cell detection in digital pathology applications.