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

Work Done on a System by External Force01:11

Work Done on a System by External Force

2.9K
The work done by an external force on a particle changes its kinetic energy. However, internal forces must also be considered for a system of interacting particles. The potential energy formulation helps formulate the effect of internal forces. The net work done by an external force can be written in terms of the total change of mechanical energy, which includes both kinetic and potential energies.
In the presence of a non-conservative opposing force, like friction, some part of the work done...
2.9K
Internal and External Forces01:12

Internal and External Forces

16.1K
Newton's first law states that a net external force causes a change in motion. External forces act on an object or system, originating outside of the object or system. In contrast, internal forces originate inside the system of interest and do not lead to any acceleration. In simpler words, internal forces are forces that act on one part of an object and are exerted by another part of the same object. External forces are forces that act on an object due to some other object. Therefore, when...
16.1K
Convolution Properties II01:17

Convolution Properties II

581
The important convolution properties include width, area, differentiation, and integration properties.
The width property indicates that if the durations of input signals are T1 and T2, then the width of the output response equals the sum of both durations, irrespective of the shapes of the two functions. For instance, convolving two rectangular pulses with durations of 2 seconds and 1 second results in a function with a width of 3 seconds.
The area property asserts that the area under the...
581
Protein Networks02:26

Protein Networks

4.5K
An organism can have thousands of different proteins, and these proteins must cooperate to ensure the health of an organism. Proteins bind to other proteins and form complexes to carry out their functions. Many proteins interact with multiple other proteins creating a complex network of protein interactions.
These interactions can be represented through maps depicting protein-protein interaction networks, represented as nodes and edges. Nodes are circles that are representative of a protein,...
4.5K
Convolution Properties I01:20

Convolution Properties I

559
Convolution computations can be simplified by utilizing their inherent properties.
The commutative property reveals that the input and the impulse response of an LTI (Linear Time-Invariant) system can be interchanged without affecting the output:
559
Network Covalent Solids02:18

Network Covalent Solids

16.1K
Network covalent solids contain a three-dimensional network of covalently bonded atoms as found in the crystal structures of nonmetals like diamond, graphite, silicon, and some covalent compounds, such as silicon dioxide (sand) and silicon carbide (carborundum, the abrasive on sandpaper). Many minerals have networks of covalent bonds.
To break or to melt a covalent network solid, covalent bonds must be broken. Because covalent bonds are relatively strong, covalent network solids are typically...
16.1K

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

WRCANet: wavelet residual cross-attention network for meibomian gland segmentation.

Biomedical optics express·2026
Same author

OphFusionNet: Uncertainty-driven multi-scale multimodal feature fusion network for ophthalmic diseases classification.

IEEE transactions on medical imaging·2026
Same author

Refining feature representation for accurate fundus lesion segmentation.

Medical physics·2026
Same author

Positively Charged Polymer-Brush MOFs for Large-Area, Pressure-Resistant Gas Separation Membranes.

Advanced materials (Deerfield Beach, Fla.)·2026
Same author

Multi-source Unsupervised Domain Adaptation Fundus Lesion Segmentation of Various OCT Devices with Moment Consistency.

IEEE journal of biomedical and health informatics·2026
Same author

Optimizing Strategies of in Situ Loading Photocatalysts in Aramid Nanofiber Aerogels: Harnessing Internal/External Synergistic Photocatalysis for Improving Degradation Efficiency of Pollutants.

ACS applied materials & interfaces·2026

Related Experiment Video

Updated: Jan 20, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K

Deriving external forces via convolutional neural networks for biomedical image segmentation.

Yibiao Rong1,2, Dehui Xiang1,2, Weifang Zhu1

  • 1School of Electrical and Information Engineering, Soochow University, 215006, Suzhou, China.

Biomedical Optics Express
|August 28, 2019
PubMed
Summary
This summary is machine-generated.

This study introduces a novel convolutional neural network approach to enhance active contour segmentation in medical imaging. The method improves accuracy by deriving external forces, outperforming traditional gradient vector flow (GVF) methods.

More Related Videos

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

1.0K
Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

10.3K

Related Experiment Videos

Last Updated: Jan 20, 2026

Deep Neural Networks for Image-Based Dietary Assessment
13:19

Deep Neural Networks for Image-Based Dietary Assessment

Published on: March 13, 2021

9.9K
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

1.0K
Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks
10:53

Image-guided, Laser-based Fabrication of Vascular-derived Microfluidic Networks

Published on: January 3, 2017

10.3K

Area of Science:

  • Medical Image Analysis
  • Computer Vision
  • Biomedical Engineering

Background:

  • Active contours (snakes) are crucial for biomedical image segmentation, evolving curves guided by internal and external forces.
  • Gradient Vector Flow (GVF) is a popular external force but is susceptible to noise and false edges, limiting its application.
  • Effective external force design is critical for accurate active contour segmentation.

Purpose of the Study:

  • To develop a robust external force for active contour models using a convolutional neural network (CNN).
  • To improve the accuracy and reliability of biomedical image segmentation by overcoming limitations of traditional GVF methods.
  • To evaluate the proposed method across diverse clinical applications.

Main Methods:

  • A CNN was trained using GVF as a reference to derive a novel external force for active contours.
  • The derived external force was integrated into active contour models for curve evolution.
  • The method was evaluated on three clinical datasets: optic disc segmentation, retinal fluid segmentation, and fetal head segmentation.

Main Results:

  • The proposed CNN-based external force demonstrated competitive performance across all evaluated segmentation tasks.
  • The method showed robustness in handling noisy image data and complex structures compared to standard GVF.
  • Achieved state-of-the-art or comparable results in segmenting optic discs, retinal fluid, and fetal heads.

Conclusions:

  • The proposed CNN-derived external force offers a promising advancement for active contour-based biomedical image segmentation.
  • This approach effectively addresses the noise sensitivity issues associated with traditional GVF methods.
  • The method shows significant potential for reliable clinical applications in medical imaging.