Diagnostic Accuracy and Failure Mode Analysis of a Deep Learning Algorithm for the Detection of Cervical Spine Fractures

References

1. 1.↵
   2. Copley D,
   3. Tilliridou D,
   4. Jamjoom M

   . Traumatic cervical spine fractures in the adult. Br J Hosp Med (Lond) 2016;77:530–35 doi:10.12968/hmed.2016.77.9.530 pmid:27640656

   CrossRefPubMed
2. 2.↵
   2. Denis F

   . The three-column spine and its significance in the classification of acute thoracolumbar spinal injuries. Spine (Phila Pa 1976) 1983;8:817–31 doi:10.1097/00007632-198311000-00003 pmid:6670016

   CrossRefPubMedWeb of Science
3. 3.↵
   2. Fischer PE,
   3. Perina DG,
   4. Delbridge TR, et al

   . Spinal motion restriction in the trauma patient: a joint position statement. Prehosp Emerg Care 2018;22:659–61 doi:10.1080/10903127.2018.1481476 pmid:30091939

   CrossRefPubMed
4. 4.↵
   2. Beckmann NM,
   3. West OC,
   4. Nunez D Jr., et al

   . Expert Panel on Neurological Imaging and Musculoskeletal Imaging. ACR Appropriateness Criteria® Suspected Spine Trauma. J Am Coll Radiol 2019;16:S264–85 doi:10.1016/j.jacr.2019.02.002 pmid:31054754

   CrossRefPubMed
5. 5.↵
   2. Hess EP,
   3. Haas LR,
   4. Shah ND, et al

   . Trends in computed tomography utilization rates: a longitudinal practice-based study. J Patient Saf 2014;10:52–58 doi:10.1097/PTS.0b013e3182948b1a pmid:24080717

   CrossRefPubMed
6. 6.↵
   2. Kocher KE,
   3. Meurer WJ,
   4. Fazel R, et al

   . National trends in use of computed tomography in the emergency department. Ann Emerg Med 2011;58:452–62 doi:10.1016/j.annemergmed.2011.05.020 pmid:21835499

   CrossRefPubMed
7. 7.↵
   2. McDonald RJ,
   3. Schwartz KM,
   4. Eckel LJ, et al

   . The effects of changes in utilization and technological advancements of cross-sectional imaging on radiologist workload. Acad Radiol 2015;22:1191–98 doi:10.1016/j.acra.2015.05.007 pmid:26210525

   CrossRefPubMed
8. 8.↵
   2. Hoffman JR,
   3. Mower WR,
   4. Wolfson AB, et al

   . Validity of a set of clinical criteria to rule out injury to the cervical spine in patients with blunt trauma: National Emergency X-Radiography Utilization Study Group. N Engl J Med 2000;343:94–99 doi:10.1056/NEJM200007133430203 pmid:10891516

   CrossRefPubMedWeb of Science
9. 9.↵
   2. Mower WR,
   3. Wolfson AB,
   4. Hoffman JR, et al

   . The Canadian C-spine rule. N Engl J Med 2004;350:1467–69 doi:10.1056/NEJM200404013501420 pmid:15074005, 15070802

   CrossRefPubMedWeb of Science
10. 10.↵
    2. Sharp AL,
    3. Huang BZ,
    4. Tang T, et al

    . Implementation of the Canadian CT head rule and its association with use of computed tomography among patients with head injury. Ann Emerg Med 2018;71:54–63 doi:10.1016/j.annemergmed.2017.06.022 pmid:28739290

    CrossRefPubMed
11. 11.↵
    2. Mower WR,
    3. Gupta M,
    4. Rodriguez R, et al

    . Validation of the sensitivity of the National Emergency X-Radiography Utilization Study (NEXUS) head computed tomographic (CT) decision instrument for selective imaging of blunt head injury patients: an observational study. PLoS Med 2017;14:e1002313 doi:10.1371/journal.pmed.1002313 pmid:28700585

    CrossRefPubMed
12. 12.↵
    DSI Home. FDA Cleared AI Algorithms. American College of Radiology. 2020. https://models.acrdsi.org/. Accessed September 11, 2020
13. 13.↵
    2. Benjamens S,
    3. Dhunnoo P,
    4. Mesko B

    . The state of artificial intelligence-based FDA-approved medical devices and algorithms: an online database. NPJ Digit Med 2020;3:118 doi:10.1038/s41746-020-00324-0 pmid:32984550

    CrossRefPubMed
14. 14.↵
    2. Alwosheel A,
    3. van Cranenburgh S,
    4. Chorus CG

    . Is your dataset big enough? Sample size requirements when using artificial neural networks for discrete choice analysis. J Choice Model 2018;28:167–82 doi:10.1016/j.jocm.2018.07.002

    CrossRef
15. 15.↵
    2. Park SH,
    3. Han K

    . Methodologic guide for evaluating clinical performance and effect of artificial intelligence technology for medical diagnosis and prediction. Radiology 2018;286:800–09 doi:10.1148/radiol.2017171920 pmid:29309734

    CrossRefPubMed
16. 16.↵
    2. Kim DW,
    3. Jang HY,
    4. Kim KW, et al

    . Design characteristics of studies reporting the performance of artificial intelligence algorithms for diagnostic analysis of medical images: results from recently published papers. Korean J Radiol 2019;20:405–10 doi:10.3348/kjr.2019.0025 pmid:30799571

    CrossRefPubMed
17. 17.↵
    2. Liu X,
    3. Faes L,
    4. Kale AU, et al

    . A comparison of deep learning performance against health-care professionals in detecting diseases from medical imaging: a systematic review and meta-analysis. Lancet Digit Health 2019;1:e271–97 doi:10.1016/S2589-7500(19)30123-2 pmid:33323251

    CrossRefPubMed
18. 18.↵
    2. Zech JR,
    3. Badgeley MA,
    4. Liu M, et al

    . Variable generalization performance of a deep learning model to detect pneumonia in chest radiographs: a cross-sectional study. PLoS Med 2018;15:e1002683 doi:10.1371/journal.pmed.1002683 pmid:30399157

    CrossRefPubMed
19. 19.↵
    U.S. Food and Drug Administration. K190896. 2019 https://www.accessdata.fda.gov/cdrh_docs/pdf19/K190896.pdf. Accessed February 19, 2021
20. 20.↵
    2. Burns JE,
    3. Yao J,
    4. Munoz H, et al

    . Automated detection, localization, and classification of traumatic vertebral body fractures in the thoracic and lumbar spine at CT. Radiology 2016;278:64–73 doi:10.1148/radiol.2015142346 pmid:26172532

    CrossRefPubMed
21. 21.↵
    2. Burns JE,
    3. Yao J,
    4. Summers RM

    . Vertebral body compression fractures and bone density: automated detection and classification on CT images. Radiology 2017;284:788–97 doi:10.1148/radiol.2017162100 pmid:28301777

    CrossRefPubMed
22. 22.↵
    2. Tomita N,
    3. Cheung YY,
    4. Hassanpour S

    . Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Comput Biol Med and Med 2018;98:8–15 doi:10.1016/j.compbiomed.2018.05.011 pmid:29758455

    CrossRefPubMed
23. 23.↵
    2. Roth HR,
    3. Wang Y,
    4. Yao J, et al

    . Deep convolutional networks for automated detection of posterior-element fractures on spine CT. Computer Science > Computer Vision and Pattern Recognition January 29, 2016. https://arxiv.org/abs/1602.00020. Accessed September 2, 2020
24. 24.↵
    2. Ginat DT

    . Analysis of head CT scans flagged by deep learning software for acute intracranial hemorrhage. Neuroradiology 2020;62:335–40 doi:10.1007/s00234-019-02330-w pmid:31828361

    CrossRefPubMed
25. 25.↵
    2. Ojeda PZ,
    3. Zawaideh M,
    4. Mossa-Basha M, et al

    . The utility of deep learning: evaluation of a convolutional neural network for detection of intracranial bleeds on non-contrast head computed tomography studies. In: Proeedings of SPIE Medical Imaging, San Diego California. February 16–21, 2019