Impact of Defacing Procedures on Brain Age Gap Estimation

Zielsetzung Brain Age Gap Estimation (BrainAGE) is increasingly explored as an imaging biomarker for atypical brain aging. Removal of facial features from MRI scans is mandatory from a data privacy perspective. However, defacing procedures may cause data integrity issues, which could also compromise the quality of BrainAGE. This study aims to systematically assess the impact of defacing on BrainAGE.

Material und Methoden A total of 364 Alzheimer’s disease (AD) patients and 717 cognitively normal (CN) participants were included from the Alzheimer’s Disease Neuroimaging Initiative (ADNI). For those, unaccelerated and accelerated 3D T1 imaging was available. BrainAGE was derived for each AD and CN before and after defacing using afni_refacer, fsl_deface, mri_deface, mri_reface, PyDeface, and spm_deface. Furthermore, for AD n=74 and CN n=84 within-session repeat imaging was available. BrainAGE differences between the two scans were calculated without defacing to serve as a benchmark. The difference in BrainAGE after defacing, as well as the mean absolute error (MAE) and mean squared error (MSE) of BrainAGE with and without defacing were calculated separately for unaccelerated and accelerated imaging.

Ergebnisse MAE and MSE for BrainAGE difference between the initial and repeat scan in the benchmark, both without defacing, were 1.15 and 2.25 for CN (BrainAGE difference -0.15±1.5), and 1.43 and 3.29 for AD (BrainAGE difference of 0.15±1.82). PyDeface performed best with an overall MAE of 0.33 and MSE of 0.27 and the lowest number of outliers according to the benchmark. The overall MAE for fsl_deface and spm_deface was 0.35, for mri_reface 0.41, for mri_deface 0.63, and for afni_refacer 1.04.

Schlussfolgerungen BrainAGE may be affected by defacing, however, in most approaches this influence is less than the methodological variability observed in BrainAGE. Overall, PyDeface had negligible impact on BrainAGE.

Publikationsverlauf

Artikel online veröffentlicht:
25. März 2025