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

You might also read

Related Articles

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

Sort by
Same author

Advancements and Challenges in Computer-Assisted Medical Interventions for Image-Guided Prostate Cancer Treatments.

Annual review of biomedical engineering·2026
Same author

Automating prostate biopsy guidance: A robust CNN approach for non-rigid 3D/3D MR-TRUS image registration.

Computers in biology and medicine·2026
Same author

Defining ground truth for prostate segmentation of transrectal ultrasound images: Inter- and intra-observer variability of manual versus semi-automatic methods.

Medical physics·2025
Same author

Deep sensorless tracking of ultrasound probe orientation during freehand transperineal biopsy with spatial context for symmetry disambiguation.

Computers in biology and medicine·2025
Same author

Learning curve for fusion magnetic resonance imaging targeted prostate biopsy and three-dimensional transrectal ultrasonography segmentation.

BJU international·2024
Same author

Impact of Relative Volume Difference Between Magnetic Resonance Imaging and Three-dimensional Transrectal Ultrasound Segmentation on Clinically Significant Prostate Cancer Detection in Fusion Magnetic Resonance Imaging-targeted Biopsy.

European urology oncology·2023

Related Experiment Video

Updated: Sep 26, 2025

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

3.0K

Multi-eXpert fusion: An ensemble learning framework to segment 3D TRUS prostate images.

Clément Beitone1, Jocelyne Troccaz1

  • 1Univ. Grenoble Alpes, CNRS, CHU Grenoble Alpes, Grenoble INP, TIMC-IMAG, Grenoble, France.

Medical Physics
|April 20, 2022
PubMed
Summary

This study introduces a novel multi-expert fusion (MXF) framework for accurate prostate segmentation in 3D TRUS images, outperforming existing methods and preserving gland structures.

Keywords:
3D TRUSdeep learningensemble learningprostate segmentation

More Related Videos

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

536
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.4K

Related Experiment Videos

Last Updated: Sep 26, 2025

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

3.0K
Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique
04:48

Swin-PSAxialNet: An Efficient Multi-Organ Segmentation Technique

Published on: July 5, 2024

536
Deep Learning-Based Segmentation of Cryo-Electron Tomograms
10:25

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

9.4K

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Biomedical Engineering

Background:

  • Prostate segmentation in 3D TRUS images is crucial for diagnosis and treatment.
  • Current manual segmentation methods suffer from high variability.
  • Automatic segmentation offers significant clinical value.

Purpose of the Study:

  • To develop a novel deep segmentation architecture for 3D TRUS prostate images.
  • To address the limitations of manual segmentation and existing automated methods.
  • To improve the accuracy and reliability of prostate segmentation.

Main Methods:

  • A two-phase deep segmentation architecture: view-specific 2D slice segmentation and fusion.
  • Three parallel segmentation networks trained on axial, coronal, and sagittal views.
  • A fusion network generating confidence maps for pixel-level combination of segmentations.

Main Results:

  • The multi-expert fusion (MXF) framework demonstrated superior performance compared to STAPLE, majority voting, and direct 3D approaches.
  • Evaluated on a 100-patient database, the approach showed flexibility and reliability.
  • Outperformed state-of-the-art methods, often tested on smaller datasets.

Conclusions:

  • The MXF framework provides robust and flexible 3D prostate segmentation from TRUS images.
  • Pixel-level fusion using confidence maps enhances segmentation accuracy.
  • The method effectively captures and preserves prostate gland structures, including base and apex regions.