Facial De-identification of Head CT Scans

HomeRadiologyVol. 296, No. 1 PreviousNext Reviews and CommentaryFree AccessImages in RadiologyFacial De-identification of Head CT ScansScott A. Collins, Jing Wu, Harrison X. Bai Scott A. Collins, Jing Wu, Harrison X. Bai Author AffiliationsFrom the Department of Diagnostic Imaging, Warren Alpert Medical School of Brown University, Providence, RI 02906 (S.A.C., H.X.B.); and Department of Radiology, The Second Xiangya Hospital, Central South University, No. 139 Middle Renmin Road, Changsha, Hunan, 410011, P.R. China (J.W.).Address correspondence to H.X.B. (e-mail: [email protected]).Scott A. CollinsJing WuHarrison X. Bai Published Online:Apr 7 2020https://doi.org/10.1148/radiol.2020192617MoreSectionsPDF ToolsImage ViewerAdd to favoritesCiteTrack CitationsPermissionsReprints ShareShare onFacebookTwitterLinked In AbstractOnline supplemental material is available for this article.Download as PowerPointThe use of de-identification has become of paramount importance due to the increased availability of shared head and neck CT or MRI scans, given the concern that facial features reconstructed from these studies can be used to identify individuals (1). Per the Safe Harbor standard to achieve de-identification in accordance with the Health Insurance Portability and Accountability Act, full-face photographs and any comparable images must be removed. We propose a simple solution to de-identify three-dimensional surface-reconstructed facial images by using 3D Slicer software (version 4.10.2; https://www.slicer.org/) (2). After importing the Digital Imaging and Communications in Medicine (DICOM) volume into the 3D Slicer software, segmentation of the air on the CT scan around the patient’s face was created using a threshold range of −1024 to −150 HU. The segmentation was then dilated by a margin of 5 mm and smoothed using a Gaussian smoothing method with a standard deviation of 5 mm. Then, a surface model was generated from the dilated and smoothed segmentation to replace the original air and skin voxels in the original CT scan. This method created a new DICOM volume with the intracranial anatomy preserved (Figure; Movie [online]).A, Volume rendering from the original nonedited CT scan. B, Volume rendering from the edited CT image does not display any unique distinguishing facial features.Download as PowerPointOpen in Image Viewer Get the Flash Player to see this video.Movie: Video clip of de-identified face.Download Original Video (21.6 MB)Disclosures of Conflicts of Interest: S.A.C. disclosed no relevant relationships. J.W. disclosed no relevant relationships. H.X.B. disclosed no relevant relationships.References1. Schwarz CG, Kremers WK, Therneau TM, et al. Identification of Anonymous MRI Research Participants with Face-Recognition Software. N Engl J Med 2019;381(17):1684–1686. Crossref, Medline, Google Scholar2. Fedorov A, Beichel R, Kalpathy-Cramer J, et al. 3D Slicer as an image computing platform for the Quantitative Imaging Network. Magn Reson Imaging 2012;30(9):1323–1341. Crossref, Medline, Google ScholarArticle HistoryReceived: Nov 26 2019Revision requested: Dec 16 2019Revision received: Jan 28 2020Accepted: Feb 4 2020Published online: Apr 7 2020Published in print: July 2020 FiguresReferencesRelatedDetailsRecommended Articles Creating Three-dimensional Printed Models of Acetabular Fractures for Use as Educational ToolsRadioGraphics2017Volume: 37Issue: 3pp. 871-880Automated Segmentation and Volume Measurement of Intracranial Internal Carotid Artery Calcification at Noncontrast CTRadiology: Artificial Intelligence2021Volume: 3Issue: 5Measuring and Establishing the Accuracy and Reproducibility of 3D Printed Medical ModelsRadioGraphics2017Volume: 37Issue: 5pp. 1424-1450CT of the Neck: Image Analysis and Reporting in the Emergency SettingRadioGraphics2019Volume: 39Issue: 6pp. 1760-1781Establishing and Running a Three-dimensional and Advanced Imaging LaboratoryRadioGraphics2018Volume: 38Issue: 6pp. 1799-1809See More RSNA Education Exhibits Imaging of Head and Neck Vascular Anomalies (Tumors and Malformations)Digital Posters2022The 3D Slicer Open-source Platform for Medical Image Analysis and 3D Visualization of DICOM DataDigital Posters2020Diagnostic Value of the 3D Volume Rendering Imaging in Routine Radiology PracticeDigital Posters2019 RSNA Case Collection Brain abscessRSNA Case Collection2020Intracranial HypotensionRSNA Case Collection2021Pancreatic lacerationRSNA Case Collection2020 Vol. 296, No. 1 Metrics Altmetric Score PDF download