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: Jun 30, 2025

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.3K

Deep learning-based automatic pipeline for 3D needle localization on intra-procedural 3D MRI.

Wenqi Zhou1,2, Xinzhou Li1,2, Fatemeh Zabihollahy1,3

  • 1Department of Radiological Sciences, University of California Los Angeles, 300 UCLA Medical Plaza, Suite B119, Los Angeles, CA, 90095, USA.

International Journal of Computer Assisted Radiology and Surgery
|March 23, 2024
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

Methods for Uncertainty Quantification in Dictionary Matching to Advance Reliability of Quantitative MRI.

Magnetic resonance in medicine·2026
Same author

Active Electromagnetic Interference Suppression for MRI and Proton Resonance Frequency Shift Thermometry During MRI-Guided Microwave Ablation.

Magnetic resonance in medicine·2026
Same author

Revisiting Reconstruction-Based Anomaly Detection for Whole-Slide Image.

IEEE transactions on medical imaging·2026
Same author

Toward the simultaneous detection of multiple diseases with a highly cost-effective cell-free DNA methylome test.

Proceedings of the National Academy of Sciences of the United States of America·2026
Same author

Keypoint detection network for needle localization on intra-procedural MRI in MRI-guided liver interventions.

International journal of computer assisted radiology and surgery·2026
Same author

Enhanced 2D Spiral Cine DENSE MRI Using Low-Rank Denoising for Improved Apparent Signal-to-Noise Ratio, Spatial Resolution, Efficiency, Accuracy, and Accessibility.

Magnetic resonance in medicine·2026

This study introduces an automated deep learning pipeline for fast and accurate 3D needle localization in MRI-guided procedures. The method significantly improves upon manual localization and requires limited training data.

Area of Science:

  • Medical Imaging
  • Artificial Intelligence
  • Surgical Technology

Background:

  • Accurate 3D needle localization is crucial for MRI-guided percutaneous interventions.
  • Current manual methods are time-consuming and cumbersome.
  • Existing automatic methods face challenges with manual plane localization or large 3D training datasets.

Purpose of the Study:

  • To develop an automatic deep learning pipeline for rapid and accurate 3D needle localization on in vivo intra-procedural 3D MRI.
  • To overcome the limitations of existing methods by utilizing a limited training dataset.

Main Methods:

  • A coarse-to-fine segmentation strategy using Shifted Window (Swin) Transformers.
  • Initial 3D needle segmentation with 3D Swin UNETR, followed by 2D reformatting and fine segmentation with 2D Swin Transformer.
Keywords:
Deep learningDevice trackingImage segmentationInterventional MRINeedle featureTransformer networks

More Related Videos

Magnetic Resonance-Guided Stereotaxy for Infusions to the Pig Brain
08:23

Magnetic Resonance-Guided Stereotaxy for Infusions to the Pig Brain

Published on: March 31, 2023

2.4K
Three-Dimensional Ultrasonic Needle Tip Tracking with a Fiber-Optic Ultrasound Receiver
04:33

Three-Dimensional Ultrasonic Needle Tip Tracking with a Fiber-Optic Ultrasound Receiver

Published on: August 21, 2018

10.4K

Related Experiment Videos

Last Updated: Jun 30, 2025

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery
09:41

A Pipeline for 3D Multimodality Image Integration and Computer-assisted Planning in Epilepsy Surgery

Published on: May 20, 2016

12.3K
Magnetic Resonance-Guided Stereotaxy for Infusions to the Pig Brain
08:23

Magnetic Resonance-Guided Stereotaxy for Infusions to the Pig Brain

Published on: March 31, 2023

2.4K
Three-Dimensional Ultrasonic Needle Tip Tracking with a Fiber-Optic Ultrasound Receiver
04:33

Three-Dimensional Ultrasonic Needle Tip Tracking with a Fiber-Optic Ultrasound Receiver

Published on: August 21, 2018

10.4K
  • Pre-training and data augmentation to enhance network training, evaluated on 49 in vivo 3D MR images.

    • Main Results:

    • The pipeline achieved an average end-to-end computation time of 6 seconds per 3D volume.
    • Median Dice scores for 3D Swin UNETR and 2D Swin Transformer were 0.80 and 0.93, respectively.
    • Median needle tip and axis localization errors were 1.48 mm and 0.98°, outperforming human intra-reader variation.

    Conclusions:

    • The proposed automatic pipeline enables rapid pixel-level 3D needle localization on intra-procedural 3D MRI.
    • It does not require extensive 3D training datasets, offering potential to assist MRI-guided percutaneous interventions.