Deep-learning Based Classification of Spine CT (DETECT)

Tongji University

Status: Unknown

Conditions: Surgical Procedure, Unspecified

Treatments: Diagnostic Test: deep learning

Study type: Observational

Funder types: Other

Identifiers

NCT03790930

SHSY180624

Details and patient eligibility

About

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.

Full description

Computer tomography (CT) is one of the most important imaging tool to assist the diagnostic and treatment of spinal disease. Classification of specific targets (e.g. individuals, lesions, etc.) is one of the most common mission of medical image analysis. However, 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.

Enrollment: 500 estimated patients

Sex: All

Ages: 18 to 65 years old

Volunteers: No Healthy Volunteers

Inclusion and exclusion criteria

Inclusion Criteria:

• spinal thin layer CT

Exclusion Critera:

• medals or other implants induce artifact
• poor image quality

Trial design

500 participants in 1 patient group

thin layer CT

Description:

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

Treatment:

Diagnostic Test: deep learning