Research on Acetabular Labrum Injury Based on MR: Multi-angle Deep Learning Model

NCT04950036 | Completed

• 1 other identifier: M2020459
• Study Type: observational
• Target: 1,261
• Locations: 1 country
• Sites: 1

Brief Summary

The purpose of this study is to study the MRI images of acetabular labrum injury by deep learning method, and try to establish a combination model of axial and coronal serial images, and compare with the diagnostic accuracy of radiologists, to establish a deep learning method for accurate identification and classification of acetabular labrum injury.

Conditions

Labrum Injury of the Hip Joint

Keywords

artificial intelligence; Labrum injury; dignosis

Outcome Measures

Primary Outcomes (1)

• Research on acetabular labrum injury based on MR: multi-angle deep learning model

  The model of deep learning was obtained for diagnosis and grading of labrum injury and compared with the doctors of different stages.

  2020.12.01-2021.05.30

Study Arms (3)

Normal control group-Grade 0

Arthroscopic examination of the hip was normal, and the labrum was intact without injury or tear.

Diagnostic Test: Diagnostic Test

Ligament injury -Grade 1

Arthroscopic examination of the hip showed labrum degeneration or injury, but no local or complete tear.

Diagnostic Test: Diagnostic Test

Ligament tear-Grade 2

Arthroscopy of the hip revealed partial or complete loss of labrum.

Diagnostic Test: Diagnostic Test

Interventions

Diagnostic Test DIAGNOSTIC_TEST

The results of hip arthroscopy were taken as the gold standard and MRI examination was taken as the research object.

Ligament injury -Grade 1; Ligament tear-Grade 2; Normal control group-Grade 0

Eligibility Criteria

• Sex: all
• Healthy Volunteers: Yes
• Age Groups: Child (0-17), Adult (18-64), Older Adult (65+)
• Sampling Method: Non-Probability Sample

Study Population

From September 2018 to September 2020, MRI was performed in the Department of Radiology, the Third Hospital of Peking University.

You may qualify if:

• Without any treatment before imaging examination;
• MR of the hip joint was performed within three months before the operation and the image quality was good;
• Arthroscopic operation was performed in our hospital, and the operation records were complete.

You may not qualify if:

• History of hip surgery, tumor, or previous fracture;
• Unclear image, serious artifact, or incomplete clinical data.

Sponsors & Collaborators

• Peking University Third Hospital: lead

Study Sites (1)

Peking University Third Hospital

Beijing, Beijing Municipality, 010, China

Location

MeSH Terms

Interventions

Diagnostic Tests, Routine

Intervention Hierarchy (Ancestors)

Diagnostic Techniques and Procedures; Diagnosis

Study Officials

• huishu Yuan, md

  Peking University Third Hospital

  STUDY CHAIR

Study Design

• Study Type: observational
• Observational Model: CASE CONTROL
• Time Perspective: RETROSPECTIVE
• Sponsor Type: OTHER
• Responsible Party: SPONSOR

Study Record Dates

• First Submitted: June 29, 2021
• First Posted: July 2, 2021
• Study Start: December 1, 2020
• Primary Completion: April 30, 2021
• Study Completion: May 30, 2021
• Last Updated: July 2, 2021

Record last verified: 2021-06

Data Sharing

• IPD Sharing: Will not share

Locations

CN (1)