MétaCan
Menu
Back to cohort
Record W3133026616 · doi:10.3389/fpsyt.2021.617997

Multisite Comparison of MRI Defacing Software Across Multiple Cohorts

2021· article· en· W3133026616 on OpenAlexafffundabout
Athena Theyers, Mojdeh Zamyadi, Mark F. O’Reilly, Robert Bartha, Sean Symons, Glenda MacQueen, Stefanie Hassel, Jason P. Lerch, Evdokia Anagnostou, Raymond W. Lam, Benício N. Frey, Roumen Milev, Daniel J. Müller, Sidney H. Kennedy, Christopher J.M. Scott, Stephen C. Strother

Bibliographic record

VenueFrontiers in Psychiatry · 2021
Typearticle
Languageen
FieldNeuroscience
TopicFunctional Brain Connectivity Studies
Canadian institutionsHeart and Stroke FoundationCentre for Addiction and Mental HealthQueen's UniversityMcMaster UniversitySt. Joseph’s Healthcare HamiltonUniversity of British ColumbiaOntario Brain InstituteHospital for Sick ChildrenUniversity of CalgarySt. Michael's HospitalSunnybrook Health Science CentreUniversity of TorontoWestern UniversityHolland Bloorview Kids Rehabilitation HospitalBaycrest HospitalUniversity Health NetworkHealth Sciences Centre
FundersFaculty of Health Sciences, Queen's UniversityNatural Sciences and Engineering Research Council of CanadaTemerty Family FoundationServierUniversity of British ColumbiaQueen's UniversityLondon Health Sciences FoundationStrongGovernment of OntarioCentre for Addiction and Mental HealthUniversity of OttawaHospital for Sick ChildrenPfizerOntario Brain InstituteUniversity of CalgaryCanadian Institutes of Health ResearchCentre for Addiction and Mental Health FoundationMcMaster UniversityH. Lundbeck A/SBruyère Research InstituteBristol-Myers Squibb
KeywordsSoftwareNeuroimagingPopulationPreprocessorComputer scienceArtificial intelligenceSkullMedicineMedical physicsPattern recognition (psychology)SurgeryPsychiatry

Abstract

fetched live from OpenAlex

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.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.004
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Observational · Consensus signal: Observational
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.110
Threshold uncertainty score0.832

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.004
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.023
GPT teacher head0.299
Teacher spread0.276 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designObservational
Domainnot available
GenreEmpirical

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations59
Published2021
Admission routes3
Has abstractyes

Explore more

Same venueFrontiers in PsychiatrySame topicFunctional Brain Connectivity StudiesFrench-language works237,207