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

Cerebrovascular segmentation from TOF using stochastic models.

M Sabry Hassouna1, A A Farag, Stephen Hushek

  • 1Computer Vision and Image Processing Laboratory, University of Louisville, Louisville, KY 40292, USA. msabry@cvip.uofl.edu

Medical Image Analysis
|May 17, 2005
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

Promising Nitrogen-Doped Graphene Derivatives; A Case Study for Preparations, Fabrication Mechanisms, and Applications in Perovskite Solar Cells.

Topics in current chemistry (Cham)·2022
Same author

A Rare Case of Spontaneous Arachnoid Cyst Rupture Presenting as Right Hemiplegia and Expressive Aphasia in a Pediatric Patient.

Children (Basel, Switzerland)·2021
Same author

Three-Dimensional Volumetric Changes in Posterior Vault Distraction With Distraction Osteogenesis.

The Journal of craniofacial surgery·2020
Same author

Protocol-driven prevention of perioperative hypothermia in the pediatric neurosurgical population.

Journal of neurosurgery. Pediatrics·2020
Same author

Pathophysiological and behavioral deficits in developing mice following rotational acceleration-deceleration traumatic brain injury.

Disease models & mechanisms·2017
Same author

Neoadjuvant chemotherapy for atypical teratoid rhabdoid tumors: case report.

Journal of neurosurgery. Pediatrics·2017
Same journal

Co-assistant networks by pathology foundation model and convolutional neural network for gigapixel whole slide image analysis.

Medical image analysis·2026
Same journal

MBAS2024: A large-scale benchmark for multi-class bi-atrial segmentation in multi-center contrast-enhanced MRIs.

Medical image analysis·2026
Same journal

Respiratory motion augmentation for personalized super-resolution (RMApSR) of 3D cine MR images in MRI-guided radiotherapy.

Medical image analysis·2026
Same journal

Biom3d, a modular framework to host and develop 3D segmentation methods.

Medical image analysis·2026
Same journal

Embracing intra-class heterogeneity for semi-supervised medical image segmentation: From diversity to precision.

Medical image analysis·2026
Same journal

Real-time patient-specific microwave ablation zone prediction via a unified bioheat solver and MRI-informed perturbation learning.

Medical image analysis·2026
See all related articles

This study introduces an automatic statistical method for 3D blood vessel extraction from time-of-flight MRA data. The approach accurately segments vessels, even small ones, using advanced modeling and 3D Markov random fields.

Area of Science:

  • Medical Imaging
  • Image Processing
  • Computational Anatomy

Background:

  • Accurate 3D blood vessel segmentation is crucial for diagnosing vascular diseases.
  • Time-of-flight magnetic resonance angiography (TOF-MRA) is a key imaging modality for visualizing vasculature.
  • Existing segmentation methods often struggle with signal loss and small vessel delineation.

Purpose of the Study:

  • To develop an automatic statistical approach for robust 3D blood vessel extraction from TOF-MRA data.
  • To improve segmentation accuracy, especially in regions with signal attenuation.
  • To enable precise delineation of small and medium-sized vessels.

Main Methods:

  • A two-level stochastic modeling approach: low-level for intensity distribution and high-level for spatial dependence.

Related Experiment Videos

  • Low-level modeling uses a finite mixture of distributions for background and blood vessels.
  • High-level modeling employs a 3D Markov random field (MRF) to capture spatial context and improve segmentation quality.
  • Expectation maximization (EM) algorithm for parameter estimation, with automatic initialization via histogram analysis.
  • Maximum pseudo-likelihood estimator (MPLE) for 3D MRF parameter estimation.

    • Main Results:

    • The proposed model accurately classifies voxels into blood vessels or background noise.
    • Effective segmentation of vessels with diameters as small as 3 voxels.
    • Demonstrated good fit to clinical data and robust performance on synthetic phantoms and diverse TOF datasets.
    • The 3D MRF approach mitigates limitations of 2D MRF in preserving small and medium vessels.

    Conclusions:

    • The presented automatic statistical method offers high-quality 3D blood vessel segmentation from TOF-MRA.
    • The approach is robust and capable of delineating fine vascular structures.
    • This technique holds promise for improved diagnosis and analysis of cerebrovascular diseases.