Manual and automated facial de-identification techniques for patient imaging with preservation of sinonasal anatomy.
Authors
Affiliations (3)
Affiliations (3)
- Department of Otolaryngology-Head and Neck Surgery, Johns Hopkins University School of Medicine, 733 N. Broadway, Baltimore, MD, 21205, USA. [email protected].
- Department of Otolaryngology-Head and Neck Surgery, Johns Hopkins University School of Medicine, 733 N. Broadway, Baltimore, MD, 21205, USA.
- Department of Computer Science, Johns Hopkins University, Baltimore, MD, USA.
Abstract
Facial recognition of reconstructed computed tomography (CT) scans poses patient privacy risks, necessitating reliable facial de-identification methods. Current methods obscure sinuses, turbinates, and other anatomy relevant for otolaryngology. We present a facial de-identification method that preserves these structures, along with two automated workflows for large-volume datasets. A total of 20 adult head CTs from the New Mexico Decedent Image Database were included. Using 3D Slicer, a seed-growing technique was performed to label the skin around the face. This label was dilated bidirectionally to form a 6-mm mask that obscures facial features. This technique was then automated using: (1) segmentation propagation that deforms an atlas head CT and corresponding mask to match other scans and (2) a deep learning model (nnU-Net). Accuracy of these methods against manually generated masks was evaluated with Dice scores and modified Hausdorff distances (mHDs). Manual de-identification resulted in facial match rates of 45.0% (zero-fill), 37.5% (deletion), and 32.5% (re-face). Dice scores for automated face masks using segmentation propagation and nnU-Net were 0.667 ± 0.109 and 0.860 ± 0.029, respectively, with mHDs of 4.31 ± 3.04 mm and 1.55 ± 0.71 mm. Match rates after de-identification using segmentation propagation (zero-fill: 42.5%; deletion: 40.0%; re-face: 35.0%) and nnU-Net (zero-fill: 42.5%; deletion: 35.0%; re-face: 30.0%) were comparable to manual masks. We present a simple facial de-identification approach for head CTs, as well as automated methods for large-scale implementation. These techniques show promise for preventing patient identification while preserving underlying sinonasal anatomy, but further studies using live patient photographs are necessary to fully validate its effectiveness.