Spinal Stenosis
Conditions
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.
Interventions
DIAGNOSTIC_TESTdeep learning
detect and classify spinal stenosis by deep learning
Sponsors
Brigham and Women's Hospital
Shanghai East Hospital
Shanghai Tongji Hospital, Tongji University School of Medicine
Shanghai 10th People's Hospital
Study design
Observational model
CASE_ONLY
Time perspective
RETROSPECTIVE
Eligibility
Sex/Gender
ALL
Age
18 Years to No maximum
Healthy volunteers
No
Inclusion criteria
* Age \>18 years * with radiologists' CT reports on cervical, thoracic and lumbar stenosis
Exclusion criteria
* not applicable (only specific levels with extensive infections, fractures, tumor, high-grade spondylolisthesis would be excluded for analysis).
Design outcomes
Primary
| Measure | Time frame | Description |
|---|---|---|
| diagnostic accuracy of deep learning | 1 day | Diagnostic accuracy of deep learning to determine spinal stenosis compared with radiologists' labels based on CT |
Secondary
| Measure | Time frame | Description |
|---|---|---|
| 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 |
Contacts
Primary ContactShisheng He, MD
Backup ContactGUOXIN FAN, MD
Outcome results
None listed