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

Robust Non-Invasive Cardiac Index Prediction via Feature Integration and Data-Augmented Neural Networks.

Bioengineering (Basel, Switzerland)·2026
Same author

Hardware Implementation of Improved Oriented FAST and Rotated BRIEF-Simultaneous Localization and Mapping Version 2.

Sensors (Basel, Switzerland)·2025
Same author

Select gene mutations associated with survival outcomes in ER-positive ERBB2-negative early-stage invasive breast cancer: A single-institutional tissue bank study.

Cancer medicine·2024
Same author

Implementation of Sound Direction Detection and Mixed Source Separation in Embedded Systems.

Sensors (Basel, Switzerland)·2024
Same author

Population-based analysis of the human development index and risk factors for head and neck cancer.

Head & neck·2024
Same author

Anti-Aliasing Attention U-net Model for Skin Lesion Segmentation.

Diagnostics (Basel, Switzerland)·2023

Related Experiment Video

Updated: Oct 2, 2025

Using Computer Vision Libraries to Streamline Nuclei Quantification
06:25

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

439

Convolutional Blur Attention Network for Cell Nuclei Segmentation.

Phuong Thi Le1, Tuan Pham2, Yi-Chiung Hsu1

  • 1Department of Biomedical Sciences and Engineering, National Central University, Taoyuan 320317, Taiwan.

Sensors (Basel, Switzerland)
|February 26, 2022
PubMed
Summary
This summary is machine-generated.

This study introduces a novel deep learning method for accurate cell nucleus segmentation, outperforming existing models. The new approach enhances feature salience and multi-scale information capture for improved biomedical applications.

Keywords:
cell nucleiconvolutional neural networkdeep learningnucleus segmentation

More Related Videos

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion
09:03

Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion

Published on: April 13, 2019

8.3K

Related Experiment Videos

Last Updated: Oct 2, 2025

Using Computer Vision Libraries to Streamline Nuclei Quantification
06:25

Using Computer Vision Libraries to Streamline Nuclei Quantification

Published on: June 6, 2025

439
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

3.0K
Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion
09:03

Exploiting Live Imaging to Track Nuclei During Myoblast Differentiation and Fusion

Published on: April 13, 2019

8.3K

Area of Science:

  • Biomedical Imaging
  • Computer Vision
  • Deep Learning

Background:

  • Accurate nucleus segmentation is crucial for cancer classification and treatment prediction.
  • Challenges in nucleus segmentation include diverse cell types, external factors, and illumination variations.

Purpose of the Study:

  • To develop a novel deep learning-based method for cell nucleus segmentation.
  • To improve the accuracy and robustness of nucleus segmentation in biomedical images.

Main Methods:

  • Proposed a convolutional blur attention (CBA) network with downsampling and upsampling procedures.
  • Introduced a blur attention module and blur pooling for feature salience and noise reduction.
  • Developed a pyramid blur pooling (PBP) module to capture multi-scale information.

Main Results:

  • The CBA network demonstrated superior performance compared to U-Net, ENet, SegNet, LinkNet, and Mask RCNN.
  • Achieved an average Jaccard index (AJI) of 0.8429 on the DSB dataset and 0.7985 on the MoNuSeg dataset.
  • Evaluated using Dice similarity coefficient, F1 score, recall, precision, and AJI.

Conclusions:

  • The proposed CBA network offers a significant advancement in cell nucleus segmentation accuracy.
  • The method effectively addresses challenges posed by cell diversity and imaging conditions.
  • This technique holds promise for enhancing various biomedical applications reliant on precise nucleus segmentation.