Emergency room (ER) visits for trauma account for a significant proportion of total emergency room visits and result in significant health care expenditure. For many of these trauma visits, there is sufficient concern of a cervical spine injury to warrant a computed tomography (CT) scan.
Cervical spine CT scans are typically interpreted by a radiologist, which can be a time consuming process. In addition, many hospitals may not have radiology coverage at all hours, which can contribute to prolonged emergency room stays. While many patients undergo a CT scan of the cervical spine, only a minority (10-20%) will have an acute abnormality on their CT scan that would prompt further management.
The aim of this project is to develop a 3D convolutional neural network (CNN) that will classify CT scan images of the cervical spine as containing or not containing a fracture.
This methodology could assist radiologists and emergency room physicians to quickly identify patients with normal, unconcerning CT scans who can be ruled out for a cervical spine injury. Patients with abnormalities could be flagged for further review.
Automated Analysis of Cervical Spine CT Scans
