Automatic Diagnosis of Spinal Stenosis on CT With Deep Learning
试验速览
- 阶段
- 不适用
- 发起方
- 入组人数
- 500
- 主要终点
- diagnostic accuracy of deep learning
研究概览
简要总结
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.
详细描述
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.
研究设计
- 研究类型
- Observational
- 观察模型
- Case Only
- 时间视角
- Retrospective
入排标准
- 年龄范围
- 18 Years 至 —（Adult, Older Adult）
- 性别
- All
- 接受健康志愿者
- 否
入选标准
- •Age >18 years
- •with radiologists' CT reports on cervical, thoracic and lumbar stenosis
排除标准
- •not applicable (only specific levels with extensive infections, fractures, tumor, high-grade spondylolisthesis would be excluded for analysis).
结局指标
主要结局
diagnostic accuracy of deep learning
时间窗: 1 day
Diagnostic accuracy of deep learning to determine spinal stenosis compared with radiologists' labels based on CT
次要结局
- Diagnostic Performance of deep learning(1 day)
研究者
Shisheng He, MD
Deputy Director of Orthopedic Department
Shanghai 10th People's Hospital