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

Parametric shape modeling using deformable superellipses for prostate segmentation.

Lixin Gong1, Sayan D Pathak, David R Haynor

  • 1Department of Electrical Engineering, University of Washington, Seattle, WA 98195, USA. lgong@insightful.com

IEEE Transactions on Medical Imaging
|March 19, 2004
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

Active nitrogen mediated selective ruthenium migration on ceria for high pressure ammonia decomposition.

Nature communications·2026
Same author

Spatial assessment of heat risk from deregulation of greenbelt in Seoul, South Korea.

Scientific reports·2026
Same author

Dependence of catalytic properties of strongly supported platinum clusters with atom counts.

Science (New York, N.Y.)·2026
Same author

Morphological Control of TiO<sub>2</sub> Supports for Enhanced Pt-Catalyzed Methylcyclohexane Dehydrogenation.

Small science·2026
Same author

Summer carbon-flow characteristics of a marine ranching ecosystem revealed by Ecopath and stable isotopes: A case study from the Bohai Sea, China.

Marine pollution bulletin·2026
Same author

Developing Topics.

Alzheimer's & dementia : the journal of the Alzheimer's Association·2025
Same journal

MUST: Multi-style virtual staining with incomplete pairs.

IEEE transactions on medical imaging·2026
Same journal

BrainCL: Transformer-Based Brain Network Contrastive Learning with Multi-Order Topology and Salience Masking.

IEEE transactions on medical imaging·2026
Same journal

LLM-enhanced Neuron Segmentation and Reconstruction in Complex Mouse Brain Images.

IEEE transactions on medical imaging·2026
Same journal

Matrixed-Spectrum Decomposition Accelerated Linear Boltzmann Transport Equation Solver for Fast Scatter Correction in Multi-Spectral CT.

IEEE transactions on medical imaging·2026
Same journal

The Ritz Adjoint Method for MRI Pulse Design.

IEEE transactions on medical imaging·2026
Same journal

Physiology-guided Self-supervised Learning for Simultaneous Dual-Tracer PET Separation.

IEEE transactions on medical imaging·2026
See all related articles

This study introduces a novel deformable superellipse model for accurate prostate segmentation in ultrasound images. The developed Bayesian algorithm significantly improves boundary detection, outperforming human expert variability.

Area of Science:

  • Medical Imaging
  • Computer-Aided Diagnosis
  • Biomedical Engineering

Background:

  • Prostate segmentation in ultrasound images is complex due to noise and anatomical variations.
  • Deformable models require accurate prior shape knowledge for initialization and evolution.

Purpose of the Study:

  • To develop a robust deformable superellipse model for prostate shape representation.
  • To create an efficient Bayesian segmentation algorithm utilizing this model for improved prostate ultrasound image analysis.

Main Methods:

  • Modeled prostate shape using deformable superellipses fitted to 594 expert-outlined contours.
  • Developed a Bayesian segmentation algorithm based on the superellipse model.
  • Applied the algorithm to 125 prostate ultrasound images from 16 patients.

Related Experiment Videos

Main Results:

  • The superellipse model achieved a Hausdorff distance error of 1.32 ± 0.62 mm and mean absolute distance error of 0.54 ± 0.20 mm.
  • The model-based variability was significantly lower than inter-expert variability (p < 0.0001).
  • The Bayesian algorithm yielded a mean segmentation error of 1.36 ± 0.58 mm, outperforming interobserver distances and showing insensitivity to initial curve choice.

Conclusions:

  • Deformable superellipses provide an efficient and accurate model for prostate shape.
  • The developed Bayesian segmentation algorithm offers robust and precise prostate segmentation in ultrasound images.
  • This approach surpasses the accuracy of manual segmentation by human experts.