Forskning
Udskriv Udskriv
Switch language
Rigshospitalet - en del af Københavns Universitetshospital
E-pub ahead of print

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

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

DOI

  1. Automatically computed rating scales from MRI for patients with cognitive disorders

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Prostate artery embolisation for benign prostatic hyperplasia: a systematic review and meta-analysis

    Publikation: Bidrag til tidsskriftReviewForskningpeer review

  3. Simulator training improves ultrasound scanning performance on patients: a randomized controlled trial

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. A free and simple computerized screening test for visual field defects

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Comparative effectiveness of teriflunomide and dimethyl fumarate: A nationwide cohort study

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. Frequency and immunophenotype of IL10-producing regulatory B cells in optic neuritis

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. The role of gluten in multiple sclerosis: A systematic review

    Publikation: Bidrag til tidsskriftReviewForskningpeer review

  5. Treatment escalation leads to fewer relapses compared with switching to another moderately effective therapy

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  • MAGNIMS Study Group and Alzheimer’s Disease Neuroimaging Initiative
Vis graf over relationer

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 impact of three FFR methods on subsequent automated image analysis to obtain clinically relevant outcome measurements in three clinical groups.

METHODS: FFR was performed using QuickShear, FaceMasking, and Defacing. In 110 subjects of Alzheimer's Disease Neuroimaging Initiative, normalized brain volumes (NBV) were measured by SIENAX. In 70 multiple sclerosis patients of the MAGNIMS Study Group, lesion volumes (WMLV) were measured by lesion prediction algorithm in lesion segmentation toolbox. In 84 glioblastoma patients of the PICTURE Study Group, tumor volumes (GBV) were measured by BraTumIA. Failed analyses on FFR-processed images were recorded. Only cases in which all image analyses completed successfully were analyzed. Differences between outcomes obtained from FFR-processed and full images were assessed, by quantifying the intra-class correlation coefficient (ICC) for absolute agreement and by testing for systematic differences using paired t tests.

RESULTS: Automated analysis methods failed in 0-19% of cases in FFR-processed images versus 0-2% of cases in full images. ICC for absolute agreement ranged from 0.312 (GBV after FaceMasking) to 0.998 (WMLV after Defacing). FaceMasking yielded higher NBV (p = 0.003) and WMLV (p ≤ 0.001). GBV was lower after QuickShear and Defacing (both p < 0.001).

CONCLUSIONS: All three outcome measures were affected differently by FFR, including failure of analysis methods and both "random" variation and systematic differences. Further study is warranted to ensure high-quality neuroimaging research while protecting participants' privacy.

KEY POINTS: • Protecting participants' privacy when sharing MRI data is important. • Impact of three facial features removal methods on subsequent analysis was assessed in three clinical groups. • Removing facial features degrades performance of image analysis methods.

OriginalsprogEngelsk
TidsskriftEuropean Radiology
ISSN0938-7994
DOI
StatusE-pub ahead of print - 2019

ID: 58366820