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 Experiment Video

Updated: Mar 21, 2026

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

3.7K

An improved parallel fuzzy connected image segmentation method based on CUDA.

Liansheng Wang1, Dong Li1, Shaohui Huang2

  • 1Department of Computer Science, School of Information Science and Engineering, Xiamen University, Xiamen, China.

Biomedical Engineering Online
|May 14, 2016
PubMed
Summary
This summary is machine-generated.

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

Tenacibaculum xiamenense sp. nov., an algicidal bacterium isolated from coastal seawater.

International journal of systematic and evolutionary microbiology·2013
Same author

The anchoring protein SAP97 influences the trafficking and localisation of multiple membrane channels.

Biochimica et biophysica acta·2013
Same author

Aegilops tauschii draft genome sequence reveals a gene repertoire for wheat adaptation.

Nature·2013
Same author

Draft genome of the wheat A-genome progenitor Triticum urartu.

Nature·2013
Same author

Citreoviridin enhances tumor necrosis factor-α-induced adhesion of human umbilical vein endothelial cells.

Toxicology and industrial health·2013
Same author

Th17/Treg imbalance induced by increased incidence of atherosclerosis in patients with systemic lupus erythematosus (SLE).

Clinical rheumatology·2013
Same journal

Non-invasive classification of stable HFpEF using a deep learning model trained on acoustic features of sustained vowels.

Biomedical engineering online·2026
Same journal

Lung cancer multimodal auxiliary diagnosis based on entropy weight decision fusion.

Biomedical engineering online·2026
Same journal

Potentials of BMSCs for regulating osteogenic-vascular-neural-lymphatic coupling in bone regeneration.

Biomedical engineering online·2026
Same journal

Protein adsorption at material interface: mechanistic design framework for engineering ceramic scaffolds for bone repair applications.

Biomedical engineering online·2026
Same journal

Machine learning models of segmentation in acute ischemic stroke: a systematic review and meta-analysis.

Biomedical engineering online·2026
Same journal

The influence of successful septal myectomy on myocardial stress distributions in the left ventricle: a computational analysis.

Biomedical engineering online·2026
See all related articles

This study introduces an improved fuzzy connectedness (FC) algorithm for medical image segmentation. The enhanced method corrects edge point miscalculations in the parallel CUDA version, achieving higher accuracy and comparable speed to the original CPU-based approach.

Area of Science:

  • Medical Imaging
  • Computer Vision
  • Algorithm Development

Background:

  • Fuzzy connectedness (FC) is effective for medical image segmentation but computationally expensive for large datasets.
  • Existing parallel CUDA versions (CUDA-kFOE) accelerate FC but suffer from edge point miscalculations due to unaddressed GPU block edges.
  • This limits the accuracy of CUDA-kFOE in medical image analysis.

Purpose of the Study:

  • To propose an improved fuzzy connectedness algorithm that enhances calculation accuracy for medical image segmentation.
  • To address the edge point miscalculation errors in the existing CUDA-kFOE algorithm.
  • To achieve accurate and efficient segmentation of fuzzy objects in large medical image datasets.

Main Methods:

  • An iterative approach was developed, modifying the affinity computation strategy in the first iteration with a lookup table for memory reduction.
Keywords:
CUDAFuzzy connectednessVessel segmentation

Related Experiment Videos

Last Updated: Mar 21, 2026

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

3.7K
  • A correction step was added to address edge points, improving accuracy.
  • Error voxels resulting from asynchronism were updated in a second iteration.

    • Main Results:

    • The improved algorithm demonstrated faster segmentation compared to the CPU version.
    • Experimental results showed higher accuracy than the original CUDA-kFOE algorithm.
    • The corrected method achieved calculation consistency with the CPU version, validating the edge point correction.

    Conclusions:

    • The proposed improved fuzzy connectedness algorithm effectively corrects edge point calculation errors inherent in CUDA-kFOE.
    • The method offers comparable time costs and reduced errors, making it a more accurate alternative for medical image segmentation.
    • Future work will focus on developing automatic acquisition and processing methods.