J E Small1, P Osler2, A B Paul3, M Kunst3. 1. From the Departments of Neuroradiology (J.E.S., A.B.P., M.K.) Juan.E.Small@Lahey.org. 2. Radiology (P.O), Lahey Hospital and Medical Center, Burlington, Massachusetts. 3. From the Departments of Neuroradiology (J.E.S., A.B.P., M.K.).
Abstract
BACKGROUND AND PURPOSE: Multidetector CT has emerged as the standard of care imaging technique to evaluate cervical spine trauma. Our aim was to evaluate the performance of a convolutional neural network in the detection of cervical spine fractures on CT. MATERIALS AND METHODS: We evaluated C-spine, an FDA-approved convolutional neural network developed by Aidoc to detect cervical spine fractures on CT. A total of 665 examinations were included in our analysis. Ground truth was established by retrospective visualization of a fracture on CT by using all available CT, MR imaging, and convolutional neural network output information. The ĸ coefficients, sensitivity, specificity, and positive and negative predictive values were calculated with 95% CIs comparing diagnostic accuracy and agreement of the convolutional neural network and radiologist ratings, respectively, compared with ground truth. RESULTS: Convolutional neural network accuracy in cervical spine fracture detection was 92% (95% CI, 90%-94%), with 76% (95% CI, 68%-83%) sensitivity and 97% (95% CI, 95%-98%) specificity. The radiologist accuracy was 95% (95% CI, 94%-97%), with 93% (95% CI, 88%-97%) sensitivity and 96% (95% CI, 94%-98%) specificity. Fractures missed by the convolutional neural network and by radiologists were similar by level and location and included fractured anterior osteophytes, transverse processes, and spinous processes, as well as lower cervical spine fractures that are often obscured by CT beam attenuation. CONCLUSIONS: The convolutional neural network holds promise at both worklist prioritization and assisting radiologists in cervical spine fracture detection on CT. Understanding the strengths and weaknesses of the convolutional neural network is essential before its successful incorporation into clinical practice. Further refinements in sensitivity will improve convolutional neural network diagnostic utility.
BACKGROUND AND PURPOSE: Multidetector CT has emerged as the standard of care imaging technique to evaluate cervical spine trauma. Our aim was to evaluate the performance of a convolutional neural network in the detection of cervical spine fractures on CT. MATERIALS AND METHODS: We evaluated C-spine, an FDA-approved convolutional neural network developed by Aidoc to detect cervical spine fractures on CT. A total of 665 examinations were included in our analysis. Ground truth was established by retrospective visualization of a fracture on CT by using all available CT, MR imaging, and convolutional neural network output information. The ĸ coefficients, sensitivity, specificity, and positive and negative predictive values were calculated with 95% CIs comparing diagnostic accuracy and agreement of the convolutional neural network and radiologist ratings, respectively, compared with ground truth. RESULTS: Convolutional neural network accuracy in cervical spine fracture detection was 92% (95% CI, 90%-94%), with 76% (95% CI, 68%-83%) sensitivity and 97% (95% CI, 95%-98%) specificity. The radiologist accuracy was 95% (95% CI, 94%-97%), with 93% (95% CI, 88%-97%) sensitivity and 96% (95% CI, 94%-98%) specificity. Fractures missed by the convolutional neural network and by radiologists were similar by level and location and included fractured anterior osteophytes, transverse processes, and spinous processes, as well as lower cervical spine fractures that are often obscured by CT beam attenuation. CONCLUSIONS: The convolutional neural network holds promise at both worklist prioritization and assisting radiologists in cervical spine fracture detection on CT. Understanding the strengths and weaknesses of the convolutional neural network is essential before its successful incorporation into clinical practice. Further refinements in sensitivity will improve convolutional neural network diagnostic utility.
Authors: Kenji Inaba; Saskya Byerly; Lisa D Bush; Matthew J Martin; David T Martin; Kimberly A Peck; Galinos Barmparas; Matthew J Bradley; Joshua P Hazelton; Raul Coimbra; Asad J Choudhry; Carlos V R Brown; Chad G Ball; Jill R Cherry-Bukowiec; Clay Cothren Burlew; Bellal Joseph; Julie Dunn; Christian T Minshall; Matthew M Carrick; Gina M Berg; Demetrios Demetriades Journal: J Trauma Acute Care Surg Date: 2016-12 Impact factor: 3.313
Authors: Matthew Adams; Weijia Chen; David Holcdorf; Mark W McCusker; Piers Dl Howe; Frank Gaillard Journal: J Med Imaging Radiat Oncol Date: 2018-11-08 Impact factor: 1.735
Authors: Francesco Alessandrino; Christopher M Bono; Christopher A Potter; Mitchel B Harris; Aaron D Sodickson; Bharti Khurana Journal: Emerg Radiol Date: 2019-03-31
Authors: Sheldon Derkatch; Christopher Kirby; Douglas Kimelman; Mohammad Jafari Jozani; J Michael Davidson; William D Leslie Journal: Radiology Date: 2019-09-17 Impact factor: 11.105