Mario Masellis

The paper identifies the CSF YWHAG:NPTX2 ratio as a biomarker for predicting clinical severity and phenoconversion in FTLD, showing strong correlation with disease progression and improved trial design potential.

This paper uses machine learning to stratify genetic frontotemporal dementia patients into subtypes and provides progression scores that improve trial enrichment efficiency.

The paper develops an MRI-based machine learning classifier to identify presymptomatic C9orf72 carriers at high risk of disease onset within two years.

The paper shows that white matter hyperintensities (WMHs) appear before other biomarkers in GRN-related frontotemporal dementia, suggesting they are early indicators of disease progression.

This study investigates the association between cerebellar and subcortical atrophy and neuropsychiatric symptoms in genetic frontotemporal dementia, finding significant differences across genetic mutations.

The paper introduces a visual quality control protocol for FreeSurfer cortical parcellations using VisualQC, showing it effectively detects errors and has reliable inter-rater agreement.

This study examines the relationship between white matter hyperintensities, cortical thickness, and empathy in neurodegenerative and cerebrovascular diseases, finding associations with specific brain regions and demographic factors.

This paper introduces a Bayesian 3D U-Net for WMH segmentation that provides uncertainty estimates and is robust to imaging variations, achieving high accuracy and efficiency.

This study shows that atrophy patterns in bvFTD are shaped by both global brain network structure and local transcriptomic vulnerability from disease-related genes.

The paper introduces CNN-based models for segmenting intracranial and ventricular volumes in neuroimaging data, showing improved accuracy and efficiency compared to existing methods.

This paper describes the neuroimaging pipeline methods used in the ONDRI study to generate regional brain tissue volumes and neurovascular markers from structural MRI data.

This paper identifies five new genetic risk loci for Lewy body dementia through whole-genome sequencing and shows shared risk profiles with Alzheimer’s and Parkinson’s disease.

ExploreASL provides a standardized image processing pipeline for multi-center ASL MRI studies, improving reproducibility and enabling group-level statistical analysis across diverse clinical populations.

This paper generalizes the MCD algorithm for categorical and mixed data using correspondence analysis, demonstrating its application on neuroimaging and genetics data.

The paper investigates the relationship between gene expression and brain atrophy in genetic frontotemporal dementia, finding correlations between atrophy patterns and specific gene sets related to vascular, glial, and neuronal functions.

The paper develops a random forest classifier to diagnose behavioral variant frontotemporal dementia using MRI and cognitive scores, achieving high accuracy in both training and validation cohorts.

This paper introduces SuStaIn, a machine learning method that identifies disease subtypes and their temporal progression from cross-sectional data, improving prediction of diagnostic conversion in neurodegenerative diseases.

The paper detects pre-symptomatic shape changes in the thalamus using spatiotemporal analysis of MRI scans from the GENFI study, finding differences five years before symptoms appear.