MétaCan
Menu
Back to cohort
Record W2113802523 · doi:10.1016/j.jalz.2015.01.002

Manual segmentation qualification platform for the EADC‐ADNI harmonized protocol for hippocampal segmentation project

2015· article· en· W2113802523 on OpenAlexafffund
Simon Duchesne, Fernando Valdivia, Nicolas Robitaille, Abderazzak Mouiha, Martina Bocchetta, Liana G. Apostolova, Rossana Ganzola, Greg M. Preboske, Dominik Wolf‎, Marina Boccardi, Clifford R. Jack, Giovanni B. Frisoni

Bibliographic record

VenueAlzheimer s & Dementia · 2015
Typearticle
Languageen
FieldMedicine
TopicDementia and Cognitive Impairment Research
Canadian institutionsUniversité LavalInstitut Universitaire en Santé Mentale de Québec
FundersJanssen Research and DevelopmentNational Institute of Biomedical Imaging and BioengineeringCanadian Institutes of Health ResearchServierBiogen IdecGenentechElanInnogeneticsEisaiAlzheimer's Disease Neuroimaging InitiativeGE HealthcarePfizerBioClinicaTakeda Pharmaceutical CompanyMedpaceEli Lilly and CompanyBristol-Myers SquibbNovartis Pharmaceuticals CorporationSynarcRocheMerckAlzheimer's Drug Discovery FoundationMeso Scale DiagnosticsNational Institute on AgingAlzheimer's Association
KeywordsJaccard indexSegmentationHARPComputer scienceArtificial intelligenceNeuroimagingBiomarkerMagnetic resonance imagingPattern recognition (psychology)MedicineRadiologyBiology

Abstract

fetched live from OpenAlex

BACKGROUND: The use of hippocampal volumetry as a biomarker for Alzheimer's disease (AD) requires that tracers from different laboratories comply with the same segmentation method. Here we present a platform for training and qualifying new tracers to perform the manual segmentation of the hippocampus on magnetic resonance images (MRI) following the European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (EADC-ADNI) Harmonized Protocol (HarP). Our objective was to demonstrate that the training process embedded in the platform leads to increased compliance and qualification with the HarP. METHOD: Thirteen new tracers' segmentations were compared with benchmark images with respect to: (a) absolute segmentation volume; (b) spatial overlap of contour with the reference using the Jaccard similarity index; and (c) spatial distance of contour with the reference. Point by point visual feedback was provided through three training phases on 10 MRI. Tracers were then tested on 10 different MRIs in the qualification phase. RESULTS: Statistical testing of training over three phases showed a significant increase of Jaccard (i.e. mean Jaccard overlap P < .001) between phases on average for all raters, demonstrating that training positively increased compliance with the HarP. Based on these results we defined qualification thresholds which all tracers were able to meet. CONCLUSIONS: This platform is an adequate infrastructure allowing standardized training and evaluation of tracers' compliance with the HarP. This is a necessary step allowing the use of hippocampal volumetry as a biomarker for AD in clinical and research centers.

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 machine prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.

metaresearch head score (Codex)0.102
metaresearch head score (Gemma)0.125
Version: metacan-v3-hybrid-931329e0061cValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.102
Threshold uncertainty score0.541

Distilled classifier scores by category (both heads)

CategoryCodexGemma
Metaresearch0.1020.125
Meta-epidemiology (narrow)0.0020.002
Meta-epidemiology (broad)0.0020.002
Bibliometrics0.0040.002
Science and technology studies0.0030.002
Scholarly communication0.0030.003
Open science0.0060.006
Research integrity0.0030.004
Insufficient payload (model declined to judge)0.0300.024

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 head0.176
GPT teacher head0.444
Teacher spread0.268 · 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 source (direct Gemma or distilled Codex), not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designBench or experimental
Domainnot available
GenreMethods

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

Citations22
Published2015
Admission routes2
Has abstractyes

Explore more

Same venueAlzheimer s & DementiaSame topicDementia and Cognitive Impairment ResearchFrench-language works237,207