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

Artificial intelligence in microscopic hair imaging for scalp disorders: From image acquisition to clinical decisions.

Medical image analysis·2026
Same author

Enhancing the Interpretation of Skin Lesion Diagnosis: Concept Adaptive Fine-Tuning of Vision-Language Models.

IEEE journal of biomedical and health informatics·2025
Same author

Compact CNN module balancing between feature diversity and redundancy.

Neural networks : the official journal of the International Neural Network Society·2025
Same author

HDConv: Heterogeneous kernel-based dilated convolutions.

Neural networks : the official journal of the International Neural Network Society·2024
Same author

Precise Phase Measurement for Fringe Reflection Technique through Optimized Camera Response.

Sensors (Basel, Switzerland)·2023
Same author

A literature survey of MR-based brain tumor segmentation with missing modalities.

Computerized medical imaging and graphics : the official journal of the Computerized Medical Imaging Society·2022

Related Experiment Video

Updated: Jun 27, 2025

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

2.7K

Dilated Heterogeneous Convolution for Cell Detection and Segmentation Based on Mask R-CNN.

Fengdan Hu1, Haigen Hu1, Hui Xu1

  • 1College of Computer Science and Technology, Zhejiang University of Technology, Hangzhou 310014, China.

Sensors (Basel, Switzerland)
|April 27, 2024
PubMed
Summary
This summary is machine-generated.

This study introduces mask R-DHCNN, a novel method for accurate cell detection and segmentation. It utilizes Dilation Heterogeneous Convolution (DHConv) to overcome challenges with cell variability and computational load, improving performance on biological cell datasets.

Keywords:
cell detection and segmentationdilation convolutionheterogeneous convolutionmask R-CNN

More Related Videos

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

542
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

524

Related Experiment Videos

Last Updated: Jun 27, 2025

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

2.7K
Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging
11:38

Author Spotlight: Enhancing PSC-to-Functional Cell Differentiation Using ML Models Based on Live-Cell Bright-Field Imaging

Published on: October 4, 2024

542
Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

524

Area of Science:

  • Biomedical imaging
  • Computer vision
  • Machine learning

Background:

  • Accurate cell detection and segmentation are crucial for biological research but are challenging due to cell variability (shape, size, grayscale) and dense distribution.
  • Standard methods like Mask R-CNN face limitations with resource-constrained microscope imaging devices due to high computational burden and numerous learning parameters.

Purpose of the Study:

  • To develop an efficient and accurate method for cell detection and segmentation that addresses the limitations of existing approaches.
  • To introduce a novel convolutional module, Dilation Heterogeneous Convolution (DHConv), to improve adaptability to diverse cell characteristics.

Main Methods:

  • Propose mask R-DHCNN, integrating a novel Dilation Heterogeneous Convolution (DHConv) module into the Mask R-CNN framework.
  • DHConv combines heterogeneous kernel structures and dilated convolution to better handle variations in cell shape and size.
  • Replace the traditional homogeneous convolution in Mask R-CNN with the DHConv module for enhanced cell analysis.

Main Results:

  • The proposed mask R-DHCNN method demonstrated superior performance across multiple metrics including Average Precision (AP), Precision, Recall, Dice coefficient, and Panoptic Quality (PQ).
  • Experiments conducted on diverse biological cell datasets (U373, GoTW1, SIM+, T24) validated the effectiveness of the DHConv module.
  • The method achieved competitive results while maintaining efficient computational costs (FLOPs) and processing speed (FPS).

Conclusions:

  • The mask R-DHCNN method offers a significant advancement in cell detection and segmentation, particularly for challenging biological imaging scenarios.
  • The novel DHConv module effectively addresses the limitations posed by cell variability and computational constraints.
  • This approach provides a more robust and efficient solution for automated cell analysis in microscopy.