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

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.
Highlights • A multimodal computational approach was implemented to identify patients with bvFTD. • We combined features from structural MRI data and fMRI-based functional connectivity. • Our approach was validated over 103 subjects from three different centers. • Our multimodal approach yielded high classification accuracy (91%) across centers. • Multimodal computational approaches may be useful complements for dementia diagnosis.