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: Dec 3, 2025

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy
09:11

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Published on: April 9, 2019

22.0K

Biomechanically constrained non-rigid MR-TRUS prostate registration using deep learning based 3D point cloud

Yabo Fu1, Yang Lei1, Tonghe Wang2

  • 1Department of Radiation Oncology, Emory University, 1365 Clifton Road NE, Atlanta, GA 30322, United States.

Medical Image Analysis
|October 31, 2020
PubMed
Summary

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

<sup>18</sup>F-Fluciclovine or <sup>68</sup>Ga-PSMA-11 PET/CT-guided Salvage Radiotherapy Changes in Postprostatectomy Biochemical Recurrence: Secondary Analysis of the EMPIRE-2 Trial.

Radiology·2026
Same author

A digital twin framework for adaptive treatment planning in radiotherapy.

Physics in medicine and biology·2026
Same author

Efficient vision mamba for MRI super-resolution via hybrid selective scanning.

Medical physics·2026
Same author

Bladder activity of different PSMA PET radioligands and impact of furosemide.

American journal of nuclear medicine and molecular imaging·2026
Same author

Utilization, Cost, and Subsequent Salvage Treatment of Ablative Therapies for Localized Prostate Cancer in the United States.

Clinical genitourinary cancer·2026
Same author

Coronary Plaque Progression After Androgen Deprivation Therapy in Men With Prostate Cancer: A Randomized Clinical Trial.

JAMA cardiology·2026

This study introduces a novel non-rigid image registration framework for prostate interventions, utilizing deep learning and biomechanical constraints for accurate MR-TRUS alignment. The method achieves robust and precise prostate segmentation and matching, enhancing intervention outcomes.

Area of Science:

  • Medical Imaging
  • Computer-Aided Surgery
  • Biomedical Engineering

Background:

  • Accurate image registration is crucial for guiding prostate interventions.
  • Existing methods may struggle with non-rigid deformations common in prostate anatomy.

Purpose of the Study:

  • To develop and evaluate a non-rigid MR-TRUS image registration framework for prostate interventions.
  • To leverage deep learning and biomechanical modeling for enhanced registration accuracy and robustness.

Main Methods:

  • A framework combining Convolutional Neural Networks (CNNs) for prostate segmentation (MR and TRUS) and a point-cloud based network for 3D matching.
  • Training the point-cloud network using deformation fields from finite element analysis to implicitly model biomechanical constraints.
  • Generating volumetric prostate point clouds via tetrahedron meshing from segmented masks.
Keywords:
Deep learningFinite elementImage registrationMR-TRUSPoint cloud matching

More Related Videos

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.3K
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

766

Related Experiment Videos

Last Updated: Dec 3, 2025

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy
09:11

Use of MRI-ultrasound Fusion to Achieve Targeted Prostate Biopsy

Published on: April 9, 2019

22.0K
Four-Dimensional CT Analysis Using Sequential 3D-3D Registration
05:05

Four-Dimensional CT Analysis Using Sequential 3D-3D Registration

Published on: November 23, 2019

8.3K
A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound
06:08

A Cognitive Fusion-guided Prostate Biopsy Using Multiparametric Magnetic Resonance Imaging and Transrectal Ultrasound

Published on: March 21, 2025

766

Main Results:

  • Achieved high registration accuracy with average Dice Similarity Coefficient (DSC) of 0.94±0.02, Mean Surface Distance (MSD) of 0.90±0.23 mm, Hausdorff Distance (HD) of 2.96±1.00 mm, and Target Registration Error (TRE) of 1.57±0.77 mm.
  • Demonstrated robustness to point cloud noise.
  • Analysis of Jacobian determinants and strain tensors confirmed the physical fidelity of the predicted deformation fields.

Conclusions:

  • The proposed framework enables rapid and accurate non-rigid MR-TRUS image registration for prostate interventions.
  • The integration of deep learning and biomechanical constraints leads to robust and precise prostate shape alignment.
  • This approach shows significant potential for improving the efficacy and safety of image-guided prostate therapies.