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

Patricio Andres Donnelly-Kehoe, Guido Orlando Pascariello, Adolfo M. García, John R. Hodges, Bruce Miller, Howie Rosen, Facundo Manes, Ramon Landin-Romero, Diana Matallana, Cecilia Serrano, Eduar Herrera, Pablo Reyes, Hernando Santamaria-Garcia, Fiona Kumfor, Olivier Piguet, Agustin Ibanez, Lucas Sedeño

Research output: Contribution to journalArticlepeer-review

38 Scopus citations


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.

Original languageEnglish
Pages (from-to)588-598
Number of pages11
JournalAlzheimer's and Dementia: Diagnosis, Assessment and Disease Monitoring
StatePublished - Dec 2019
Externally publishedYes


  • Classifiers
  • Data-driven computational approaches
  • Dementia
  • Neuroimaging
  • bvFTD


Dive into the research topics of 'Robust automated computational approach for classifying frontotemporal neurodegeneration: Multimodal/multicenter neuroimaging'. Together they form a unique fingerprint.

Cite this