6533b7d6fe1ef96bd1265d3f
RESEARCH PRODUCT
Training labels for hippocampal segmentation based on the EADC-ADNI harmonized hippocampal protocol
Marina BoccardiMartina BocchettaLuigi AntelmiAndreas FellgiebelHiroshi MatsudaStefan TeipelSimon DuchesneClifford R JackGiovanni B FrisoniEadc-adni Working Group On The Harmonized Protocol For Manual Hippocampal Segmentation AndAlzheimer's Disease Neuroimaging InitiativeFélix C MorencyD Louis CollinsMasami NishikawaRossana GanzolaMichel J. GrotheDominik WolfAlberto RedolfiMichela Pievanisubject
MaleEpidemiologyIntraclass correlationpathology [Cognitive Dysfunction]methods [Pattern Recognition Automated]Hippocampal formationHippocampusFunctional LateralityPattern Recognition Automatedpathology [Alzheimer Disease]ddc:616.89methods [Magnetic Resonance Imaging]methods [Image Processing Computer-Assisted]Image Processing Computer-AssistedSegmentationHARPAged 80 and overmedicine.diagnostic_testHealth PolicyOrgan SizeMiddle AgedMagnetic Resonance Imaginginstrumentation [Magnetic Resonance Imaging]Temporal LobePsychiatry and Mental healthFemalePsychologymethods [Neuroimaging]Algorithmsmethods [Imaging Three-Dimensional]anatomy & histology [Hippocampus]educationNeuroimagingTemporal lobeCellular and Molecular NeuroscienceImaging Three-DimensionalDevelopmental NeuroscienceNeuroimagingAlzheimer DiseasemedicineHumansCognitive Dysfunctionddc:610AgedProtocol (science)business.industryReproducibility of ResultsMagnetic resonance imagingpathology [Temporal Lobe]pathology [Hippocampus]Neurology (clinical)Geriatrics and GerontologyAtrophyNuclear medicinebusinessNeurosciencedescription
Abstract Background The European Alzheimer's Disease Consortium and Alzheimer's Disease Neuroimaging Initiative (ADNI) Harmonized Protocol (HarP) is a Delphi definition of manual hippocampal segmentation from magnetic resonance imaging (MRI) that can be used as the standard of truth to train new tracers, and to validate automated segmentation algorithms. Training requires large and representative data sets of segmented hippocampi. This work aims to produce a set of HarP labels for the proper training and certification of tracers and algorithms. Methods Sixty-eight 1.5 T and 67 3 T volumetric structural ADNI scans from different subjects, balanced by age, medial temporal atrophy, and scanner manufacturer, were segmented by five qualified HarP tracers whose absolute interrater intraclass correlation coefficients were 0.953 and 0.975 (left and right). Labels were validated as HarP compliant through centralized quality check and correction. Results Hippocampal volumes (mm 3 ) were as follows: controls: left = 3060 (standard deviation [SD], 502), right = 3120 (SD, 897); mild cognitive impairment (MCI): left = 2596 (SD, 447), right = 2686 (SD, 473); and Alzheimer's disease (AD): left = 2301 (SD, 492), right = 2445 (SD, 525). Volumes significantly correlated with atrophy severity at Scheltens' scale (Spearman's ρ = P = Cerebrospinal fluid spaces (mm 3 ) were as follows: controls: left = 23 (32), right = 25 (25); MCI: left = 15 (13), right = 22 (16); and AD: left = 11 (13), right = 20 (25). Five subjects (3.7%) presented with unusual anatomy. Conclusions This work provides reference hippocampal labels for the training and certification of automated segmentation algorithms. The publicly released labels will allow the widespread implementation of the standard segmentation protocol.
| year | journal | country | edition | language |
|---|---|---|---|---|
| 2015-01-01 |