Systematic Redaction for Neuroimage Data

Matlock, Matthew K.; Schimke, Nakeisha; Kong, Liang; Macke, Stephen; Hale, John

doi:10.4018/jcmam.2012040104

Cited by 6 publications

(1 citation statement)

References 18 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The final method, defacing, is similar to facial blurring, except that voxels containing facial features are removed, rather than blurred, eliminating the possibility of reversing the deidentification ( 20 ). There have been numerous, publicly available software algorithms that have been developed using this method ( 13 , 21 – 23 ) (descriptions in Table 2 ), and while there have been a few reports on the success of individual defacers ( 13 , 24 ), there has not been a systematic review of the available choices and how they perform across scans in different populations. In this study, we sought to fill that gap, by examining the performance of different defacing algorithms across a wide range of structural scans.…”

Section: Introductionmentioning

confidence: 99%

Multisite Comparison of MRI Defacing Software Across Multiple Cohorts

et al. 2021

View full text Add to dashboard Cite

With improvements to both scan quality and facial recognition software, there is an increased risk of participants being identified by a 3D render of their structural neuroimaging scans, even when all other personal information has been removed. To prevent this, facial features should be removed before data are shared or openly released, but while there are several publicly available software algorithms to do this, there has been no comprehensive review of their accuracy within the general population. To address this, we tested multiple algorithms on 300 scans from three neuroscience research projects, funded in part by the Ontario Brain Institute, to cover a wide range of ages (3–85 years) and multiple patient cohorts. While skull stripping is more thorough at removing identifiable features, we focused mainly on defacing software, as skull stripping also removes potentially useful information, which may be required for future analyses. We tested six publicly available algorithms (afni_refacer, deepdefacer, mri_deface, mridefacer, pydeface, quickshear), with one skull stripper (FreeSurfer) included for comparison. Accuracy was measured through a pass/fail system with two criteria; one, that all facial features had been removed and two, that no brain tissue was removed in the process. A subset of defaced scans were also run through several preprocessing pipelines to ensure that none of the algorithms would alter the resulting outputs. We found that the success rates varied strongly between defacers, with afni_refacer (89%) and pydeface (83%) having the highest rates, overall. In both cases, the primary source of failure came from a single dataset that the defacer appeared to struggle with - the youngest cohort (3–20 years) for afni_refacer and the oldest (44–85 years) for pydeface, demonstrating that defacer performance not only depends on the data provided, but that this effect varies between algorithms. While there were some very minor differences between the preprocessing results for defaced and original scans, none of these were significant and were within the range of variation between using different NIfTI converters, or using raw DICOM files.

show abstract

Section: Introductionmentioning

confidence: 99%

Multisite Comparison of MRI Defacing Software Across Multiple Cohorts

et al. 2021

View full text Add to dashboard Cite

show abstract

Clinical trials in radiology and data sharing: results from a survey of the European Society of Radiology (ESR) research committee

2019

View full text Add to dashboard Cite

De-Identification Technique with Facial Deformation in Head CT Images

et al. 2023

View full text Add to dashboard Cite

Head CT, which includes the facial region, can visualize faces using 3D reconstruction, raising concern that individuals may be identified. We developed a new de-identification technique that distorts the faces of head CT images. Head CT images that were distorted were labeled as "original images" and the others as "reference images." Reconstructed face models of both were created, with 400 control points on the facial surfaces. All voxel positions in the original image were moved and deformed according to the deformation vectors required to move to corresponding control points on the reference image. Three face detection and identification programs were used to determine face detection rates and match confidence scores. Intracranial volume equivalence tests were performed before and after deformation, and correlation coefficients between intracranial pixel value histograms were calculated. Output accuracy of the deep learning model for intracranial segmentation was determined using Dice Similarity Coefficient before and after deformation. The face detection rate was 100%, and match confidence scores were < 90. Equivalence testing of the intracranial volume revealed statistical equivalence before and after deformation. The median correlation coefficient between intracranial pixel value histograms before and after deformation was 0.9965, indicating high similarity. Dice Similarity Coefficient values of original and deformed images were statistically equivalent. We developed a technique to de-identify head CT images while maintaining the accuracy of deep-learning models. The technique involves deforming images to prevent face identification, with minimal changes to the original information.

show abstract

Systematic Redaction for Neuroimage Data

Cited by 6 publications

References 18 publications

Multisite Comparison of MRI Defacing Software Across Multiple Cohorts

Multisite Comparison of MRI Defacing Software Across Multiple Cohorts

Clinical trials in radiology and data sharing: results from a survey of the European Society of Radiology (ESR) research committee

De-Identification Technique with Facial Deformation in Head CT Images

Contact Info

Product

Resources

About