Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

Search research articles

Related Experiment Video

Updated: Jun 25, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Deep-learning-based pelvic automatic segmentation in pelvic fractures.

Jung Min Lee¹, Jun Young Park², Young Jae Kim^1,3,4

¹Department of Computer Engineering, College of IT Convergence, Gachon University, Seongnam, Republic of Korea.

Scientific Reports

|May 28, 2024

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

Does tibial sclerosis severity influence bone resorption risk following total knee arthroplasty? : finite element analysis considering implant design and surgical technique.

Bone & joint research·2026

Same author

Acute Macular Hole Formation after Posterior Vitreous Detachment Induction in Epiretinal Membrane Surgery: A Case Report.

Case reports in ophthalmology·2026

Same author

Rank-adaptive covariance testing with applications to genomics and neuroimaging.

Biometrics·2026

Same author

Radiomics-based differentiation of hepatocellular carcinoma and dysplastic nodules using noncontrast abbreviated MRI.

Digital health·2026

Same author

Cohort Profile: The Youth Vascular Consortium.

Artery research·2026

Same author

Combining UHPLC profiling and random walk network-based in vitro analysis to predict herb-induced liver injury.

Food and chemical toxicology : an international journal published for the British Industrial Biological Research Association·2026

Swin U-Net accurately segments pelvic regions in X-ray images, outperforming other deep learning models. This advancement aids in analyzing pelvic fractures, a growing concern from increased traffic accidents.

Area of Science:

Medical Imaging
Artificial Intelligence
Orthopedics

Background:

Pelvic fractures are a significant cause of mortality and complications, often linked to traffic accidents.
Intra-abdominal bleeding is the primary cause of death in pelvic fracture patients.
While tumor and organ segmentation research is advanced, clinically applicable bone and pelvic segmentation algorithms are limited.

Purpose of the Study:

To evaluate the efficacy of deep learning models for accurate pelvic region segmentation in X-ray images.
To compare the performance of Attention U-Net, Swin U-Net, and U-Net for pelvic segmentation.

Main Methods:

Utilized a dataset of 940 patient X-ray images (ages 18+) from Gachon University Gil Hospital (2015-2022).
Trained Attention U-Net, Swin U-Net, and U-Net models for pelvic segmentation.

Keywords:

Deep learning Pelvic fracture Segmentation

More Related Videos

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Related Experiment Videos

Last Updated: Jun 25, 2025

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Author Spotlight: Bridging Gaps in Anatomy and Establishing a Foundation for Algorithmic Studies

Published on: December 15, 2023

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Deep Learning-Based Segmentation of Cryo-Electron Tomograms

Published on: November 11, 2022

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Automated Segmentation of Cortical Grey Matter from T1-Weighted MRI Images

Published on: January 7, 2019

Employed five-fold cross-validation for rigorous performance analysis.

Main Results:

Swin U-Net demonstrated superior performance compared to Attention U-Net and U-Net.
Swin U-Net achieved high average performance metrics: 96.77% sensitivity, 98.50% specificity, 98.03% accuracy, and 96.32% Dice Similarity Coefficient.

Conclusions:

Deep learning models, particularly Swin U-Net, show significant potential for accurate pelvic segmentation in X-ray imaging.
This technology can aid in the clinical assessment and management of pelvic fractures.