Journal of Digital Imaging

, Volume 30, Issue 2, pp 204–214 | Cite as

Automated Facial Recognition of Computed Tomography-Derived Facial Images: Patient Privacy Implications

Article

Abstract

The recognizability of facial images extracted from publically available medical scans raises patient privacy concerns. This study examined how accurately facial images extracted from computed tomography (CT) scans are objectively matched with corresponding photographs of the scanned individuals. The test subjects were 128 adult Americans ranging in age from 18 to 60 years, representing both sexes and three self-identified population (ancestral descent) groups (African, European, and Hispanic). Using facial recognition software, the 2D images of the extracted facial models were compared for matches against five differently sized photo galleries. Depending on the scanning protocol and gallery size, in 6–61 % of the cases, a correct life photo match for a CT-derived facial image was the top ranked image in the generated candidate lists, even when blind searching in excess of 100,000 images. In 31–91 % of the cases, a correct match was located within the top 50 images. Few significant differences (p > 0.05) in match rates were observed between the sexes or across the three age cohorts. Highly significant differences (p < 0.01) were, however, observed across the three ancestral cohorts and between the two CT scanning protocols. Results suggest that the probability of a match between a facial image extracted from a medical scan and a photograph of the individual is moderately high. The facial image data inherent in commonly employed medical imaging modalities may need to consider a potentially identifiable form of “comparable” facial imagery and protected as such under patient privacy legislation.

Keywords

Facial recognition Patient privacy HIPAA Computed tomography (CT) 

References

  1. 1.
    Smith-Bindman R, Miglioretti DL, Johnson E, Lee C, Feigelson HS, Flynn M, Greenlee RT, Kruger RL, Hornbrook MC, Roblin D, Solberg LI, Vanneman N, Weinmann S, Williams AE: Use of diagnostic imaging studies and associated radiation exposure for patients enrolled in large integrated health care systems, 1996-2010. JAMA 07(22):2400–2409, 2012Google Scholar
  2. 2.
    Rao VM, Levin DC, Parker L, Frangos AJ, Sunshine JH: Trends in utilization rates of the various imaging modalities in emergency departments: Nationwide Medicare data from 2000 to 2008. J Am Coll Radiol 8(10):706–709, 2011CrossRefPubMedGoogle Scholar
  3. 3.
    Agarwal R, Bergey M, Sonnad S, Butowsky H, Bhargavan M, Bleshman MH: Inpatient CT and MRI utilization: trends in the academic hospital setting. J Am Coll Radiol 7(12):949–955. 2010CrossRefPubMedGoogle Scholar
  4. 4.
    Broder J, Warshauer DM: Increasing utilization of computed tomography in the adult emergency department, 2000–2005. Emerg Radio 13(1):25–30. 2006CrossRefGoogle Scholar
  5. 5.
    Brenner DJ, Hall EJ: Computed tomography—an increasing source of radiation exposure. N Engl J Med 357(22):2277–2284. 2007CrossRefPubMedGoogle Scholar
  6. 6.
    The Cancer Imaging Archive. Available at http://www.cancerimagingarchive.net. Accessed January 2016
  7. 7.
    Peddicord D, Waldo AB, Boutin M, Grande T, Gutierrez L Jr: A proposal to protect privacy of health information while accelerating comparative effectiveness research. Health Aff (Milwood) 29(11):2082–2090. 2010CrossRefGoogle Scholar
  8. 8.
    Budin F, Zeng D, Ghosh A, Bullitt E: Preventing facial recognition when rendering MR images of the head in three dimensions. Med Image Anal 12(3):229–239. 2008CrossRefPubMedGoogle Scholar
  9. 9.
    Noumeir R, Lemay A, Lina JM: Pseudonymization of radiology data for research purposes. J Digit Imaging 20(3):284–295. 2007CrossRefPubMedGoogle Scholar
  10. 10.
    P.L. No. 104–191, 110 Stat. 1938 (1996). United States Department of Health and Human Services. The Health Insurance Portability and Accountability Act (HIPAA)Google Scholar
  11. 11.
    11. C.F.R. § 164.514(e) (2). US Department of Health and Human Services. Privacy of Individually Identifiable Health Information. Other requirements relating to uses and disclosures of protected health informationGoogle Scholar
  12. 12.
    Fetzer DT, West OC: The HIPAA privacy rule and protected health information: implications in research involving DICOM image databases. Acad Radiol 15(3):390–395. 2008CrossRefPubMedGoogle Scholar
  13. 13.
    Avrin D: HIPAA privacy and DICOM anonymization for research. Acad Radiol 15(3):273. 2008CrossRefPubMedGoogle Scholar
  14. 14.
    Maal TJJ, Plooij JM, Rangel, FA Mollemans W, Schutyser FAC, Bergé SJ: The accuracy of matching three-dimensional photographs with skin surfaces derived from cone-beam computed tomography. Int J Oral Maxillofac Surg 37(7):641–646. 2008CrossRefPubMedGoogle Scholar
  15. 15.
    Jen-Sho Chen J, Juluru K, Morgan T, Moffitt R, Siddiqui KM, Siegel EL: Implications of surface-rendered facial CT images in patient privacy. Am J Roentgenol 202(6):1267–1271. 2014CrossRefGoogle Scholar
  16. 16.
    OsiriX . DICOM Viewer for Mac. Available at http://www.osirix-viewer.com/Downloads.html. Accessed August 2016
  17. 17.
    MicroDicom. DICOM Viewer for Windows. Available at http://www.microdicom.com. Accessed August 2016
  18. 18.
    Gingo CADx. Cross Platform DICOM Viewer. Available at http://ginkgo-cadx.com/en. Accessed August 2016
  19. 19.
    Prior FW, Brunsden B, Hildebolt C, Nolan TS, Pringle M, Vaishnavi SN, Larson-Prior LJ: Facial recognition from volume-rendered magnetic resonance imaging data. IEEE Trans Inf Technol Biomed 13(1):5–9. 2009CrossRefPubMedGoogle Scholar
  20. 20.
    Mazura JC, Julura K, Chen JJ, Morgan TA, John M, Siegel EL: Facial recognition software success rates for the identification of 3D surface reconstructed facial images: implications for patient privacy and security. J Digit Imaging 25(3):347–351. 2012CrossRefPubMedGoogle Scholar
  21. 21.
    Hwang HG, Han HE, Kuo KM, Liu CF: The differing privacy concerns regarding exchanging electronic medical records of internet users in Taiwan. J Med Syst 36(6):3783–93. 2012CrossRefPubMedGoogle Scholar
  22. 22.
    Senior A, Pankanti S: Privacy protection and face recognition. In: Li, SZ and Jain, AK, eds: Handbook of face recognition, 2nd ed, NY: Springer, pp 671–691. 2011CrossRefGoogle Scholar
  23. 23.
    American Civil Liberties Union. Washington DC. Available at https://www.aclu.org. Accessed August 2016
  24. 24.
    Electronic Privacy Information Center. Washington DC. Available at https://epic.org. Accessed August 2016
  25. 25.
    Electronic Frontier Foundation. San Francisco, California. Available at https://www.eff.org. Accessed August 2016
  26. 26.
    Parks CP, Richard H, Monson KL: Preliminary performance assessment of computer automated facial approximations using computed tomography scans of living individuals. Forensic Sci Int 233(1–3):133–139. 2013CrossRefPubMedGoogle Scholar
  27. 27.
    Picasa: Available at http://picasa.en.softonic.com. Accessed August 2016
  28. 28.
    NeoFace® Reveal: Available at https://www.necam.com/Biometrics/doc.cfm?t = NeoFaceReveal. Accessed August 2016
  29. 29.
    Parks CL, Monson KL: Recognizability of ReFace facial approximations in an automated facial recognition context for potential application in unidentified persons data repositories. Part I: Optimally modeled conditions. Forensic Sci Int (in review)Google Scholar
  30. 30.
    Parks CL, Monson KL: Recognizability of ReFace facial approximations in an automated facial recognition context for potential application in unidentified persons data repositories. Part II: Operationally modeled conditions. Forensic Sci Int (in review)Google Scholar
  31. 31.
    P.J. Phillips, P. Grother, R. Michaels: Evaluation methods in face recognition. In: Li, SZ and Jain, AK, eds: Handbook of face recognition, 2nd ed, NY: Springer, pp 551–574. 2011.CrossRefGoogle Scholar
  32. 32.
    Jain, AK and Ross, AA: Introduction to biometrics. In: Jain, AK, Flynn, P and Ross, AA, eds: Handbook of biometrics, NY: Springer, pp 1–22. 2008CrossRefGoogle Scholar
  33. 33.
    Phillips PJ, Grother P, Micheals RJ, Blackburn DM, Tabassi E, Bone JM: Face Recognition Vendor Test (FRVT). Evaluation Report. National Institute of Standards and Technology Interagency Report 6965. 2002 Available at http://www.nist.gov/customcf/get_pdf.cfm?pub_id = 50767. Accessed August 2016
  34. 34.
    Grother PJ, Quinn GW, Phillips PJ: Report on the evaluation of 2D still-image face recognition algorithms. Technical Report. National Institute of Standards and Technology Interagency Report 7709. Available at http://biometrics.nist.gov/cs_links/face/mbe/MBE_2D_face_report_NISTIR_7709.pdf. Accessed August 2016
  35. 35.
    Grother PJ, Ngan ML: Face Recognition Vendor Test (FRVT). Performance of Face Identification Algorithms. National Institute of Standards and Technology Interagency Report 8009. Available at http://www.nist.gov/customcf/get_pdf.cfm?pub_id = 915761. Accessed August 2016
  36. 36.
    Holm S: A simple sequentially rejective multiple test procedure. Scand J Statistics 6(2):65–70. 1979Google Scholar
  37. 37.
    Ho K: 41 Up-to-date Facebook facts and stats. Available at http://blog.wishpond.com/post/115675435109/40-up-to-date-facebook-facts-and-stats. Accessed August 2016
  38. 38.
    Robertson A: Facebook users have uploaded a quarter-trillion photos since the site’s launch. Available at http://www.theverge.com/2013/9/17/4741332/facebook-users-have-uploaded-a-quarter-trillion-photos-since-launch. Accessed August 2016
  39. 39.

Copyright information

© Society for Imaging Informatics in Medicine 2016

Authors and Affiliations

  1. 1.Counterterrorismand Forensic Science Research Unit, Visiting Scientist Program, FBI Laboratory DivisionQuanticoUSA
  2. 2.Counterterrorism and Forensic Science Research Unit, FBI Laboratory DivisionQuanticoUSA

Personalised recommendations