Amy Kuceyeski

TL;DR: This work predicts spatially distinct "persistent modes" of dementia that recapitulate known patterns of dementia and match recent reports of selectively vulnerable dissociated brain networks, and closely match T1-weighted MRI volumetrics of 18 Alzheimer's and frontotemporal dementia subjects.

TL;DR: This work uses a network diffusion model to predict future patterns of regional atrophy and metabolism from baseline regional patterns of 418 subjects, and helps validate the model as a prognostic tool for Alzheimer's disease assessment.

TL;DR: An overview of various unsupervised and supervised machine learning applications to resting-state functional Magnetic Resonance Imaging (rs-fMRI) is presented and a methodical taxonomy of machine learning methods in resting- state fMRI is offered.

TL;DR: A new neuroimaging software pipeline called the Network Modification (NeMo) Tool is presented that associates alterations in WM integrity with expected changes in neural connectivity between gray matter regions, enabling an investigation of morphological and functional implications of changes in structural WM integrity.

TL;DR: An ensemble learning strategy to combine the predictions from models trained on connectivity data extracted using different parcellations is proposed, which overcomes the limitations of traditional machine learning models for connectomes that often rely on region-based summary statistics and/or linear models.