Aller au contenu principal
Accès ouvert déclaré 2025 article

Estimation of reference curves for brain atrophy and analysis of robustness to machine effects

1Citations signalées — pas une note de qualité
86Institutions déclarées
6Pays d’affiliation déclarés

Résumé fourni par la source

Neurodegenerative diseases like Alzheimer's are difficult to diagnose due to brain complexity and imaging variability. However, volumetric analysis tools, using reference curves, help detect abnormal brain atrophy and support diagnosis and monitoring. This study evaluates the robustness of three segmentation algorithms, AssemblyNet, FastSurfer and FreeSurfer, in constructing brain volume reference curves and detecting hippocampal atrophy. Using data from 3,730 cognitively normal subjects, we built reference curves and assessed robustness to magnetic field strength (1.5T vs. 3T) using four error metrics (sMAPE, sMSPE, wMAPE, sMdAPE) with bootstrap validation. We evaluated classification performance using hippocampal atrophy rates and HAVAs scores (Hippocampal-Amygdalo-Ventricular Atrophy scores). AssemblyNet shows the lowest errors across all robustness metrics. In contrast, FastSurfer and FreeSurfer exhibit greater deviations, indicating higher sensitivity to field strength variability. AssemblyNet provides consistent hippocampal atrophy rates across all reference models, despite slightly lower sensitivity, while FastSurfer and FreeSurfer display greater variability. Specificity ranges from 0.87 to 0.91 for AssemblyNet, compared to 0.76-0.93 for FastSurfer and 0.86-0.93 for FreeSurfer. Using the HAVAs score, all methods detect high atrophy rates in Alzheimer's patients. FastSurfer achieves the highest sensitivity (0.98), while AssemblyNet reaches the best specificity (0.95) and the highest balanced accuracy (0.91). This study underscores the importance of algorithm choice for reliable brain volumetric analysis in heterogeneous imaging environments. Among the methods tested, AssemblyNet stands out as both sensitive to Alzheimer's-related atrophy and robust to acquisition variability, making it a strong candidate when analyzing hippocampal volumes in large, multi-site datasets.

Ce résumé expose les affirmations des auteurs. BNTIC ne l’interprète pas comme une validation indépendante des résultats.

Contrôle bibliographique ouvert

DOI retrouvé dans Crossref DOI retrouvé ; titre concordant.

Titre Crossref
Estimation of reference curves for brain atrophy and analysis of robustness to machine effects
Date Crossref
03/10/2025
Éditeur
Springer Science and Business Media LLC
Type
journal-article

Ce recoupement confirme des métadonnées liées au DOI. Il ne confirme ni la méthode ni les conclusions de l’étude et ne compte pas comme une seconde source scientifique indépendante.

Institutions déclarées

Grenoble Institute of NeurosciencesUniversité Grenoble AlpesCentre National de la Recherche ScientifiqueInsermCentre Hospitalier Universitaire de GrenobleLaboratoire d'Écologie AlpineUniversity of California, San FranciscoUniversity of California San DiegoMayo Clinic in ArizonaBerkeley CollegeUniversity of California, BerkeleyUniversity of PennsylvaniaLAC+USC Medical CenterUniversity of California, DavisBrigham and Women's HospitalHarvard UniversityIndiana University BloomingtonWashington University in St. LouisPrevent Alzheimer’s Disease 2020Siemens (Germany)Alzheimer's AssociationUniversity of PittsburghCornell UniversityAlbert Einstein College of MedicineYeshiva UniversityAlzheimer's Drug Discovery FoundationAcumen Pharmaceuticals (United States)Northwestern UniversityNational Institute of Mental HealthBrown UniversityUniversity of WashingtonUniversity of LondonUCLA Medical CenterLos Angeles Biomedical Research InstituteUniversity of MichiganUniversity of UtahBanner Alzheimer’s InstituteUniversity of California, IrvineFIT Consulting (Italy)National Institute on AgingOregon Health & Science UniversityUniversity of Alabama at BirminghamJohns Hopkins UniversityIcahn School of Medicine at Mount SinaiRush University Medical CenterBaylor College of MedicineColumbia University Irving Medical CenterNew York UniversityDuke Medical CenterEmory UniversityUniversity of Kansas Medical CenterUniversity of KentuckyJacksonville CollegeWinnMedMayo Clinic in FloridaUniversity of Rochester MedicineYale UniversityJewish General HospitalMcGill UniversitySunnybrook Health Science CentreSt Joseph's Health CentreCleveland ClinicLou Ruvo Brain InstitutePalm Beach NeurologyPremiere Research InstituteGeorgetown UniversityGeorgetown University Medical CenterStanford UniversityBoston UniversityHoward UniversityCase Western Reserve UniversityNeurological SurgerySt Joseph's Health CareDent Neurologic InstituteThe Ohio State UniversityAlbany Medical Center HospitalHartford HospitalDartmouth–Hitchcock Medical CenterWake Forest UniversityMedical University of South CarolinaNathan Kline Institute for Psychiatric ResearchUniversity of IowaUniversity of South FloridaUSF Health Byrd Alzheimer's InstituteMassachusetts General HospitalSeattle University

Une affiliation ne permet pas de déduire la nationalité d’un auteur.

Sujets associés

Dementia and Cognitive Impairment ResearchFunctional Brain Connectivity StudiesAdvanced Neuroimaging Techniques and Applications

BNTIC News n’est pas le producteur de ces données. Recherche à la demande dans Crossref et Europe PMC, sans clé ; OpenAlex reste optionnel. Aucun service payant requis, aucune réponse conservée. Sources et limites.