NCT03790930

Brief Summary

It is time-consuming for spine surgeons or radiologists to conduct manual classifications of spinal CT, which may also be correlated with high inter-observer variance. With the development of computer science, deep learning has emerged as a promising technique to classify images from individual level to pixel level. The main of the study is to automatically identify and classify the lesions, or segment targeted structures on spinal CT with deep learning.

Trial Health

43
At Risk

Trial Health Score

Automated assessment based on enrollment pace, timeline, and geographic reach

Trial has exceeded expected completion date
Enrollment
500

participants targeted

Target at P75+ for all trials

Timeline
Completed

Started Feb 2019

Geographic Reach
1 country

1 active site

Status
unknown

Health score is calculated from publicly available data and should be used for screening purposes only.

Trial Relationships

Click on a node to explore related trials.

Study Timeline

Key milestones and dates

First Submitted

Initial submission to the registry

November 16, 2018

Completed
2 months until next milestone

First Posted

Study publicly available on registry

January 2, 2019

Completed
2 months until next milestone

Study Start

First participant enrolled

February 22, 2019

Completed
1.2 years until next milestone

Primary Completion

Last participant's last visit for primary outcome

May 1, 2020

Completed
Same day until next milestone

Study Completion

Last participant's last visit for all outcomes

May 1, 2020

Completed
Last Updated

May 12, 2020

Status Verified

May 1, 2020

Enrollment Period

1.2 years

First QC Date

November 16, 2018

Last Update Submit

May 10, 2020

Conditions

Surgical Procedure, Unspecified

Outcome Measures

Primary Outcomes (2)

  • classification accuracy

    classification accuracy (e.g. area under the curve, etc.)

    1 day

  • segmentation accuracy

    segmentation accuracy of multiple structures (e.g. Dice score, etc.)

    1 day

Study Arms (1)

thin layer CT

Thin-layer CT will be manually labeled and used to train, validate and test deep learning algorithm.

Diagnostic Test: deep learning

Interventions

deep learningDIAGNOSTIC_TEST

manually labeled samples will be used to train, validate and test deep learning algorithm, and then realize automatic classification.

thin layer CT

Eligibility Criteria

Age18 Years - 65 Years
Sexall
Healthy VolunteersNo
Age GroupsAdult (18-64), Older Adult (65+)
Sampling MethodNon-Probability Sample
Study Population

patients with thin layer spinal CT covering targeted level will be included.

You may qualify if:

  • \- spinal thin layer CT
  • medals or other implants induce artifact
  • poor image quality

Contact the study team to confirm eligibility.

Sponsors & Collaborators

Study Sites (1)

Shanghai Tenth People's Hospital

Shanghai, Shanghai Municipality, 200072, China

RECRUITING

MeSH Terms

Interventions

Deep Learning

Intervention Hierarchy (Ancestors)

Machine LearningArtificial IntelligenceAlgorithmsMathematical ConceptsNeural Networks, Computer

Study Officials

  • Shisheng He, M.D.

    Shanghai 10th People's Hospital

    PRINCIPAL INVESTIGATOR

Central Study Contacts

Guoxin Fan

CONTACT

008602166307580gfan@tongji.edu.cn

Study Design

Study Type
observational
Observational Model
CASE ONLY
Time Perspective
RETROSPECTIVE
Sponsor Type
OTHER
Responsible Party
PRINCIPAL INVESTIGATOR
PI Title
Executive Director of Orthopedic Department

Study Record Dates

First Submitted

November 16, 2018

First Posted

January 2, 2019

Study Start

February 22, 2019

Primary Completion

May 1, 2020

Study Completion

May 1, 2020

Last Updated

May 12, 2020

Record last verified: 2020-05

Locations

CN(1)