Radiol Artif Intell 2020 Mar 25;2(2):e190023. Epub 2020 Mar 25.
Departments of Orthopaedic Surgery (J.D.K., K.M.H., P.T., E.G.M., E.J.G., M.Z.), Emergency Medicine (B.F.D., K.A.P.), and Radiology and Biomedical Imaging (K.C.M., R.P., J.H.S., A.W., E.O., S.M., V.P.), University of California, San Francisco, 6945 Geary Blvd, San Francisco, CA 94121; and Department of Electrical Engineering and Computer Sciences, University of California, Berkeley, Berkeley, Calif (K.V.C.).
Purpose: To investigate the feasibility of automatic identification and classification of hip fractures using deep learning, which may improve outcomes by reducing diagnostic errors and decreasing time to operation.
Materials And Methods: Hip and pelvic radiographs from 1118 studies were reviewed, and 3026 hips were labeled via bounding boxes and classified as normal, displaced femoral neck fracture, nondisplaced femoral neck fracture, intertrochanteric fracture, previous open reduction and internal fixation, or previous arthroplasty. A deep learning-based object detection model was trained to automate the placement of the bounding boxes. Read More