Robust automated computational approach for classifying frontotemporal neurodegeneration: Multimodal/multicenter neuroimaging

Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring

Olivier Piguet¹  John R. Hodges¹  Ramon Landin‐Romero¹  Fiona Kumfor¹  Eduar Herrera²  Howie Rosen³  Lucas Sedeño⁴  Facundo Manes⁴  Adolfo M. García⁴  Agustin Ibanez⁴  Diana Matallana⁵  Bruce Miller⁶  Cecilia Serrano⁷  Guido Orlando Pascariello⁸  Patricio Andres Donnelly‐Kehoe⁸  Hernando Santamaria‐Garcia⁹  Pablo Reyes⁹ 

[1] Centre of Excellence in Cognition and its DisordersAustralian Research Council (ARC)SydneyAustralia;Departamento de Estudios PsicológicosUniversidad IcesiCaliColombia(eduar);Department of NeurologyMemory Aging Center, University of CaliforniaSan FranciscoCAUSA;Laboratory of Experimental Psychology and Neuroscience (LPEN), Institute of Cognitive and Translational Neuroscience (INCyT)INECO FoundationFavaloro UniversityBuenos AiresArgentina;Medical School, Aging InstitutePsychiatry and Mental Health, Pontificia Universidad Javeriana (PUJ)BogotáColombia;Memory and Aging Center, University of California, San FranciscoSan FranciscoCAUSA;Memory and Balance ClinicBuenos AiresArgentina;Multimedia Signal Processing Group ‐ Neuroimage DivisionFrench‐Argentine International Center for Information and Systems Sciences (CIFASIS) ‐ National Scientific and Technical Research Council (CONICET)RosarioArgentina;RadiologyHospital Universitario San Ignacio (HUSI)BogotáColombia;

关键词: Dementia;    bvFTD;    Data‐driven computational approaches;    Classifiers;    Neuroimaging;   

DOI  :  10.1016/j.dadm.2019.06.002

来源: DOAJ

【 摘 要 】

Abstract Introduction Timely diagnosis of behavioral variant frontotemporal dementia (bvFTD) remains challenging because it depends on clinical expertise and potentially ambiguous diagnostic guidelines. Recent recommendations highlight the role of multimodal neuroimaging and machine learning methods as complementary tools to address this problem. Methods We developed an automatic, cross‐center, multimodal computational approach for robust classification of patients with bvFTD and healthy controls. We analyzed structural magnetic resonance imaging and resting‐state functional connectivity from 44 patients with bvFTD and 60 healthy controls (across three imaging centers with different acquisition protocols) using a fully automated processing pipeline, including site normalization, native space feature extraction, and a random forest classifier. Results Our method successfully combined multimodal imaging information with high accuracy (91%), sensitivity (83.7%), and specificity (96.6%). Discussion This multimodal approach enhanced the system's performance and provided a clinically informative method for neuroimaging analysis. This underscores the relevance of combining multimodal imaging and machine learning as a gold standard for dementia diagnosis.

【 授权许可】

Unknown