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 Videos

Parallel fuzzy connected image segmentation on GPU.

Ying Zhuge1, Yong Cao, Jayaram K Udupa

  • 1Radiation Oncology Branch, National Cancer Institute, National Institutes of Health, Bethesda, Maryland 20892, USA. zhugey@mail.nih.gov

Medical Physics
|August 24, 2011
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

Free-breathing Dynamic MRI Analysis of Three-dimensional Diaphragm Curvatures in Pediatric Patients with Thoracic Insufficiency Syndrome.

Radiology. Cardiothoracic imaging·2026
Same author

Open area segmentation in CT images based on pixel displacement and multi-view with application in the axillary and lower cervical regions.

Medical physics·2025
Same author

Auto-segmentation of thoraco-abdominal organs in pediatric dynamic MRI.

Medical physics·2025
Same author

Predicting the Effort Required to Manually Mend Auto-Segmentations.

IEEE journal of biomedical and health informatics·2025
Same author

Corrigendum to "Evaluating indicators of intentionality, flexibility, and goal-association in domestic cat (Felis silvestris catus) facial signals" [Behav. Proc. 231, September 2025, 105244].

Behavioural processes·2025
Same author

Evaluating indicators of intentionality, flexibility, and goal-association in domestic cat (Felis silvestris catus) facial signals.

Behavioural processes·2025
Same journal

Correction to "On the shape of the radiation survival curve in tumor spheroids: The role of oxygen heterogeneity".

Medical physics·2026
Same journal

Multi-view constrained semi-supervised vertebra detection for 3D ultrasound spine volume.

Medical physics·2026
Same journal

Accuracy of quantitative <sup>177</sup>Lu SPECT/CT imaging: A systematic review.

Medical physics·2026
Same journal

Physics-constrained dual-domain network for CBCT reconstruction from orthogonal X-rays in gynecologic radiotherapy.

Medical physics·2026
Same journal

Decomposition-based harmonization for quantitative PET imaging across scanners and radiotracers.

Medical physics·2026
Same journal

Development and evaluation of an in vivo dose-based monitoring system for electron FLASH radiation therapy.

Medical physics·2026
See all related articles

This study accelerates fuzzy connectedness (FC) image segmentation using NVIDIA GPUs. The parallel algorithm significantly speeds up processing for medical image datasets, achieving near-interactive segmentation speeds.

Area of Science:

  • Medical Image Analysis
  • Computational Imaging
  • Parallel Computing

Background:

  • Fuzzy connectedness (FC) principles are effective for image segmentation but computationally intensive.
  • Large-scale image datasets pose significant computational challenges for traditional FC algorithms.
  • Modern graphics hardware offers parallel processing capabilities for computational acceleration.

Purpose of the Study:

  • To implement a parallel fuzzy connected image segmentation algorithm on NVIDIA's Compute Unified Device Architecture (CUDA) platform.
  • To address the computational demands of FC algorithms for segmenting large medical image datasets.
  • To leverage GPU acceleration for faster and more efficient image segmentation.

Main Methods:

  • The fuzzy affinity and fuzzy connectedness relation computations were implemented as CUDA kernels.

Related Experiment Videos

  • These computationally intensive tasks were executed on a GPU.
  • The parallel implementation was tested on small, medium, and large datasets.

    • Main Results:

    • The parallel algorithm achieved significant speed-ups compared to CPU implementation: 24.4x (small), 18.1x (medium), and 10.3x (large datasets).
    • Segmentation times were dramatically reduced, with the large dataset processed in 15.04 seconds.
    • The NVIDIA Tesla C1060 demonstrated substantial performance gains.

    Conclusions:

    • A parallel FC image segmentation algorithm was successfully developed for NVIDIA GPUs.
    • The GPU-based approach is more cost- and speed-effective than CPU-based methods, clusters, or multiprocessing systems.
    • Near-interactive segmentation speeds were achieved, even for large medical image datasets.