Related Experiment Video
Updated: Jul 6, 2025
Automated Midline Shift and Intracranial Pressure Estimation based on Brain CT Images
Published on: April 13, 2013
Vision Transformer-based Decision Support for Neurosurgical Intervention in Acute Traumatic Brain Injury: Automated
Christopher W Smith1, Armaan K Malhotra1, Christopher Hammill1
1From the Division of Neurosurgery (C.W.S., A.K.M., E.M.H., Y.H., H.S., J.R.W., C.D.W.), Trauma Program and Quality Assurance (A.M., E.C.), Department of Emergency Medicine (A.D.A., G.M.), and Department of Medical Imaging (S.M., R.M., E.C.), St Michael's Hospital, 30 Bond St, Toronto, ON, Canada M5B 1W8; Li Ka Shing Knowledge Institute (C.W.S., A.K.M., E.M.H., Y.H., H.S., H.M.L., M.M., S.M., J.R.W., E.C., C.D.W.) and Data Science and Advanced Analytics (C.H., D.B., B.J., M.M.), Unity Health Toronto, Toronto, Ontario, Canada; Institute for Health Policy, Management and Evaluation (A.K.M., H.S., M.M., J.R.W., C.D.W.), Interdepartmental Division of Critical Care (F.M.), Temerty Faculty of Medicine (A.D.A., G.M., M.M., S.M., J.R.W., R.M., C.D.W.), and Leslie Dan Faculty of Pharmacy (M.M.), University of Toronto, Toronto, Ontario, Canada; and Division of Trauma Surgery, Sunnybrook Health Sciences Centre, Toronto, Ontario, Canada (A.B.N.).
None:
Purpose To develop an automated triage tool to predict neurosurgical intervention for patients with traumatic brain injury (TBI). Materials and Methods A provincial trauma registry was reviewed to retrospectively identify patients with TBI from 2005 to 2022 treated at a specialized Canadian trauma center. Model training, validation, and testing were performed using head CT scans with binary reference standard patient-level labels corresponding to whether the patient received neurosurgical intervention. Performance and accuracy of the model, the Automated Surgical Intervention Support Tool for TBI (ASIST-TBI), were also assessed using a held-out consecutive test set of all patients with TBI presenting to the center between March 2021 and September 2022. Results Head CT scans from 2806 patients with TBI (mean age, 57 years ± 22 [SD]; 1955 [70%] men) were acquired between 2005 and 2021 and used for training, validation, and testing. Consecutive scans from an additional 612 patients (mean age, 61 years ± 22; 443 [72%] men) were used to assess the performance of ASIST-TBI. There was accurate prediction of neurosurgical intervention with an area under the receiver operating characteristic curve (AUC) of 0.92 (95% CI: 0.88, 0.94), accuracy of 87% (491 of 562), sensitivity of 87% (196 of 225), and specificity of 88% (295 of 337) on the test dataset. Performance on the held-out test dataset remained robust with an AUC of 0.89 (95% CI: 0.85, 0.91), accuracy of 84% (517 of 612), sensitivity of 85% (199 of 235), and specificity of 84% (318 of 377). Conclusion A novel deep learning model was developed that could accurately predict the requirement for neurosurgical intervention using acute TBI CT scans. Keywords: CT, Brain/Brain Stem, Surgery, Trauma, Prognosis, Classification, Application Domain, Traumatic Brain Injury, Triage, Machine Learning, Decision Support Supplemental material is available for this article. © RSNA, 2024 See also commentary by Haller in this issue.
