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

The effectiveness of Chuna manual therapy based on radiographic malposition diagnosis in patients with non-acute low back pain: A study protocol for a randomized, assessor-blind, parallel-group, controlled trial.

PloS one·2026
Same author

Real-World Evidence on the Use of Traditional Korean Medicine in Managing Intervertebral Disc Disease.

Healthcare (Basel, Switzerland)·2025
Same author

A Study on the Diagnosis of Lumbar Spinal Malposition in Chuna Manual Therapy Using X-Ray Images Based on Digital Markers.

Diagnostics (Basel, Switzerland)·2025
Same author

Reliability Analysis of Vertebral Landmark Labelling on Lumbar Spine X-ray Images.

Diagnostics (Basel, Switzerland)·2023
Same author

Part Affinity Fields and CoordConv for Detecting Landmarks of Lumbar Vertebrae and Sacrum in X-ray Images.

Sensors (Basel, Switzerland)·2022
Same author

Comparison of Concordance between Chuna Manual Therapy Diagnostic Methods (Palpation, X-ray, Artificial Intelligence Program) in Lumbar Spine: An Exploratory, Cross-Sectional Clinical Study.

Diagnostics (Basel, Switzerland)·2022

Related Experiment Video

Updated: Mar 29, 2026

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

3.9K

A Fully Automated Deep Learning Pipeline for Anatomical Landmark Localization on Three-Dimensional Pelvic Surface

Woosu Choi1, Jun-Su Jang1

  • 1Korea Institute of Oriental Medicine, 1672 Yuseong-daero, Yuseong-gu, Daejeon 34054, Republic of Korea.

Sensors (Basel, Switzerland)
|March 28, 2026
PubMed
Summary

This study introduces an automated deep learning pipeline for precise anatomical landmark identification on 3D pelvic scans. The AI system offers improved accuracy and repeatability for musculoskeletal assessments compared to manual methods.

Keywords:
3D alignmentdeep learninglandmark localizationpelvic ROI extractionpoint cloud

More Related Videos

Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

270
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

12.8K

Related Experiment Videos

Last Updated: Mar 29, 2026

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans
10:23

Author Spotlight: Three-Dimensional Cephalometric Landmark Annotation Demonstration on Human Cone Beam Computed Tomography Scans

Published on: September 8, 2023

3.9K
Automated Joint Space Detection Improves Bone Segmentation Accuracy
06:45

Automated Joint Space Detection Improves Bone Segmentation Accuracy

Published on: November 28, 2025

270
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

12.8K

Area of Science:

  • Biomedical Engineering
  • Medical Imaging
  • Artificial Intelligence

Background:

  • Accurate anatomical landmark identification on 3D pelvic scans is crucial for musculoskeletal assessment.
  • Manual landmarking methods are operator-dependent and affected by soft tissue variations.
  • A need exists for robust, automated solutions for pelvic surface analysis.

Purpose of the Study:

  • To develop and validate a fully automated deep learning pipeline for localizing anatomical landmarks on the posterior pelvic region using 3D point cloud data.
  • To assess the performance, repeatability, and clinical applicability of the automated system compared to manual methods.

Main Methods:

  • A three-module deep learning pipeline (PelvicROINet, PelvicAlignNet, PelvicLandmarkNet) was developed for region extraction, posture standardization, and landmark localization.
  • The pipeline was trained on 3D point cloud data and evaluated using a subject-level split.
  • Six key anatomical landmarks were targeted: bilateral posterior superior iliac spines, bilateral iliac crests, L1, and L4.

Main Results:

  • The integrated system achieved a median localization error of 11.25 mm on unseen subjects.
  • Automated measurements demonstrated superior within-visit repeatability and reduced variability compared to manual marking.
  • The entire inference process took approximately three seconds per scan, indicating near real-time capability.

Conclusions:

  • The proposed modular deep learning framework provides a robust and numerically consistent approach to surface-based pelvic landmark assessment.
  • This automated pipeline offers a scalable foundation for AI-assisted musculoskeletal evaluation and longitudinal monitoring.
  • The system enhances efficiency and reliability in clinical settings for pelvic surface analysis.