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

Deformations in a Transverse Cross Section01:21

Deformations in a Transverse Cross Section

When a material is subjected to uniaxial stress, it elongates or contracts in the direction of the applied force, and also undergoes changes in the perpendicular directions. This behavior is crucial for understanding how materials behave under stress and is governed by mechanical properties such as Poisson's ratio v, which measures the ratio of transverse strain to axial strain.
As the material stretches, it expands or contracts in orthogonal directions to the load. This phenomenon varies...
Computed Tomography01:10

Computed Tomography

Tomography refers to imaging by sections. Computed tomography (CT) is a non-invasive imaging technique that uses computers to analyze several cross-sectional X-rays to reveal minute details about structures in the body.
The technique was invented in the 1970s and is based on the principle that as X-rays pass through the body, they are absorbed or reflected at different levels. In the technique, a patient lies on a motorized platform while a computerized axial tomography (CAT) scanner rotates...

You might also read

Related Articles

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

Sort by
Same author

Integrating microbial biomass, composition and function to discern the level of anthropogenic activity in a river ecosystem.

Environment international·2018
Same author

c-Jun-mediated microRNA-302d-3p induces RPE dedifferentiation by targeting p21<sup>Waf1/Cip1</sup>.

Cell death & disease·2018
Same author

High expression of synthesis of cytochrome c oxidase 2 and TP53-induced glycolysis and apoptosis regulator can predict poor prognosis in human lung adenocarcinoma.

Human pathology·2018
Same author

Comparison of the efficacy of dispensing granules with traditional decoction: a systematic review and meta-analysis.

Annals of translational medicine·2018
Same author

Serum Wisteria floribunda agglutinin-positive Mac-2-binding protein evaluates liver function and predicts prognosis in liver cirrhosis.

Journal of digestive diseases·2018
Same author

Acupuncture for constipation in patients with stroke: protocol of a systematic review and meta-analysis.

BMJ open·2018

Related Experiment Video

Updated: May 16, 2026

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

PF-DAformer: Proximal Femur Segmentation via Domain Adaptive Transformer for Dual-Center QCT.

Rochak Dhakal1, Chen Zhao2, Zixin Shi1

  • 1Department of Applied Computing, Michigan Technological University, Houghton, MI, 49931, USA.

Biomedical Signal Processing and Control
|May 15, 2026
PubMed
Summary
This summary is machine-generated.

This study introduces a domain-adaptive transformer segmentation framework to improve multi-institutional quantitative computed tomography (QCT) analysis for bone density assessment. The new method ensures accurate proximal femur segmentation across different sites, enhancing osteoporosis research reproducibility.

Keywords:
domain adaptationhip fractureimage segmentationquantitative computed tomographytransformers

More Related Videos

Proximal Cadaveric Femur Preparation for Fracture Strength Testing and Quantitative CT-based Finite Element Analysis
08:04

Proximal Cadaveric Femur Preparation for Fracture Strength Testing and Quantitative CT-based Finite Element Analysis

Published on: March 11, 2017

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

Related Experiment Videos

Last Updated: May 16, 2026

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

Proximal Cadaveric Femur Preparation for Fracture Strength Testing and Quantitative CT-based Finite Element Analysis
08:04

Proximal Cadaveric Femur Preparation for Fracture Strength Testing and Quantitative CT-based Finite Element Analysis

Published on: March 11, 2017

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy
07:43

In Vivo Quantification of Hip Arthrokinematics during Dynamic Weight-bearing Activities using Dual Fluoroscopy

Published on: July 2, 2021

Area of Science:

  • Medical Imaging and Artificial Intelligence
  • Bone Densitometry and Fracture Risk Assessment

Background:

  • Quantitative computed tomography (QCT) is vital for bone strength and fracture risk assessment via proximal femur density analysis.
  • Automated segmentation models struggle with domain shift across institutions, leading to unreliable quantitative metrics and hindering multi-center research.

Purpose of the Study:

  • To develop a domain-adaptive transformer segmentation framework for robust multi-institutional QCT analysis of the proximal femur.
  • To overcome domain shift challenges and ensure reproducible radiomics and finite element analysis results across different clinical sites.

Main Methods:

  • Developed a 3D TransUNet backbone incorporating adversarial alignment (Gradient Reversal Layer - GRL) and statistical alignment (Maximum Mean Discrepancy - MMD).
  • Trained and validated on a large cohort (1,024 scans from Tulane, 398 unlabeled scans from Mayo Clinic) for domain-invariant feature learning.
  • Employed unlabeled data from a second institution to facilitate domain adaptation without relying on its labels during training.

Main Results:

  • The combined domain adaptation strategy (GRL + MMD) achieved superior performance: Dice score 99.53%, Precision 99.64%, HD95 0.77 mm, significantly outperforming the baseline (p < 0.01).
  • Radiomic features extracted from the adapted segmentation showed high fidelity to ground truth (Pearson r > 0.99), confirming preserved anatomical detail.
  • The framework demonstrated scanner-agnostic feature learning, maintaining accuracy and reliability across different QCT data sources.

Conclusions:

  • The proposed domain-adaptive transformer segmentation framework effectively addresses domain shift in multi-institutional QCT.
  • This approach ensures accurate and reproducible proximal femur segmentation, crucial for advancing multi-center osteoporosis research and quantitative bone analysis.
  • The method preserves the fidelity of radiomic features, enabling reliable downstream analyses like finite element modeling.