Facing privacy in neuroimaging: removing facial features degrades performance of image analysis methods

• Published in: European radiology Vol. 30; no. 2; pp. 1062 - 1074
• Main Authors: de Sitter, A., Visser, M., Brouwer, I., Cover, K. S., van Schijndel, R. A., Eijgelaar, R. S., Müller, D. M. J., Ropele, S., Kappos, L., Rovira, Á., Filippi, M., Enzinger, C., Frederiksen, J., Ciccarelli, O., Guttmann, C. R. G., Wattjes, M. P., Witte, M. G., de Witt Hamer, P. C., Barkhof, F., Vrenken, H.
• Format: Journal Article
• Language: English
• Published: Berlin/Heidelberg Springer Berlin Heidelberg 01.02.2020; Springer Nature B.V
• Subjects: Algorithms; Alzheimer's disease; Automation; Correlation coefficient; Correlation coefficients; Data retrieval; Diagnostic Radiology; Failure analysis; Glioblastoma; Image analysis; Image processing; Image segmentation; Imaging; Internal Medicine; Interventional Radiology; Lesions; Magnetic Resonance; Magnetic resonance imaging; Medical ethics; Medical imaging; Medicine; Medicine & Public Health; Multiple sclerosis; Neurodegenerative diseases; Neuroimaging; Neuroradiology; Performance degradation; Privacy; Radiology; Test procedures; Ultrasound; Neuroimaging; Database; Ethics; Privacy; Magnetic resonance imaging

Background Recent studies have created awareness that facial features can be reconstructed from high-resolution MRI. Therefore, data sharing in neuroimaging requires special attention to protect participants’ privacy. Facial features removal (FFR) could alleviate these concerns. We assessed the impa...