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: Nov 17, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.1K

A scalable physician-level deep learning algorithm detects universal trauma on pelvic radiographs.

Chi-Tung Cheng1, Yirui Wang2, Huan-Wu Chen3

  • 1Department of Trauma and Emergency Surgery, Chang Gung Memorial Hospital, Linkou, Chang Gung University, Taoyuan, Taiwan.

Nature Communications
|February 17, 2021
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

Updated Asian consensus guidelines for the diagnosis and management of gastrointestinal stromal tumor (2025).

Gastric cancer : official journal of the International Gastric Cancer Association and the Japanese Gastric Cancer Association·2026
Same author

Outcomes of angioembolization in penetrating hepatic trauma: Equivalent survival, longer hospitalization.

Surgery·2026
Same author

A unified vision-language model for precision oncology and biomarker prediction in neuroblastoma.

Nature communications·2026
Same author

Revised cardiac risk index and adverse outcomes in patients undergoing surgical stabilization of rib fractures.

BMC surgery·2026
Same author

Dose-Expansion Study of OBI-999, a Globo H-Targeting Antibody-Drug Conjugate, in Patients with Advanced Solid Tumors.

The oncologist·2026
Same author

Comparative long-term risks of chronic kidney disease and dialysis following conservative treatment, renal artery embolization, or nephrectomy in patients with blunt kidney injuries: retrospective cohort study.

BJS open·2026

A new deep learning algorithm, PelviXNet, accurately detects most trauma-related findings on pelvic radiographs (PXRs). This AI tool shows performance comparable to human experts in identifying pelvic and hip fractures.

Area of Science:

  • Radiology
  • Artificial Intelligence
  • Medical Imaging

Background:

  • Pelvic radiographs (PXRs) are crucial for diagnosing proximal femur and pelvis injuries in trauma patients.
  • Current algorithms struggle to detect all trauma-related findings on PXRs.
  • A universal algorithm for comprehensive PXR analysis is needed.

Purpose of the Study:

  • To develop and evaluate a novel deep learning algorithm for detecting trauma-related radiographic findings on PXRs.
  • To assess the algorithm's performance against human experts.

Main Methods:

  • Development of a multiscale deep learning algorithm named PelviXNet.
  • Training PelviXNet on 5204 PXRs using weakly supervised point annotation.
  • Validation on a clinical test set of 1888 PXRs.

More Related Videos

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.2K

Related Experiment Videos

Last Updated: Nov 17, 2025

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
14:08

Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images

Published on: April 13, 2013

43.1K
Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model
07:15

Machine Learning Algorithms for Early Detection of Bone Metastases in an Experimental Rat Model

Published on: August 16, 2020

7.2K

Main Results:

  • PelviXNet achieved an AUROC of 0.973 and AUPRC of 0.963.
  • The algorithm demonstrated high accuracy (0.924), sensitivity (0.908), and specificity (0.932).
  • Performance was comparable to radiologists and orthopedics in detecting pelvic and hip fractures.

Conclusions:

  • PelviXNet effectively detects most trauma-related radiographic findings on PXRs.
  • The algorithm shows potential as a valuable tool in trauma assessment.
  • AI-powered analysis can augment the diagnostic capabilities of clinicians in radiology.