Automatic Diagnosis of Spinal Stenosis on CT
- Conditions
- Spinal Stenosis
- Registration Number
- NCT03746561
- Lead Sponsor
- Shanghai 10th People's Hospital
- Brief Summary
MRI is a common tool for radiographic diagnosis of spinal stenosis, but it is expensive and requires long scanning time. CT is also a useful tool to diagnose spinal stenosis, yet interpretation can be time-consuming with high inter-reader variability even among the most specialized radiologists. In this study, the investigators aim to develop a deep-learning algorithm to automatically detect and classify lumbar spinal stenosis.
- Detailed Description
MRI is a common tool for radiographic diagnosis of spinal stenosis, but it is expensive and requires long scanning time. CT is also a useful tool to diagnose spinal stenosis, yet interpretation can be time-consuming with high inter-reader variability even among the most specialized radiologists. In this study, the investigators aim to develop a deep-learning algorithm to automatically detect and classify lumbar spinal stenosis. It would be a time-saving workflow if the software can assist the radiologists to detect and locate the suspected lesion.
Recruitment & Eligibility
- Status
- UNKNOWN
- Sex
- All
- Target Recruitment
- 500
- Age >18 years
- with radiologists' CT reports on cervical, thoracic and lumbar stenosis
- not applicable (only specific levels with extensive infections, fractures, tumor, high-grade spondylolisthesis would be excluded for analysis).
Study & Design
- Study Type
- OBSERVATIONAL
- Study Design
- Not specified
- Primary Outcome Measures
Name Time Method diagnostic accuracy of deep learning 1 day Diagnostic accuracy of deep learning to determine spinal stenosis compared with radiologists' labels based on CT
- Secondary Outcome Measures
Name Time Method Diagnostic Performance of deep learning 1 day Sensitivity, specificity, positive predictive value and negative predictive value of deep learning compared with radiologists' labels based on CT