Newest papers

Cross-disorder Learning of Imaging-derived Joint Mophometric Markers in Alzheimer's and Parkinson's Diseases

Yuji Zhao, Boris A. Gutman · 2026 · arXiv (Cornell University)

DOI: 10.48550/arxiv.2610.27150 · cited by 0 works (OpenAlex) · open-access PDF

Portuguese

Como as duas doenças neurodegenerativas mais prevalentes (NDDs), a doença de Alzheimer (AD) e a doença de Parkinson (PD) compartilham semelhanças tanto na sintomatologia quanto na patofisiologia. No entanto, em que medida e de que forma essas duas doenças distintas se sobrepõem permanecem inexploradas. Neste estudo, propomos um quadro de aprendizagem de transferência explícito, interpretável e adaptável espacialmente para esclarecer os biomarcadores morfométricos ligados ao AD e ao PD. Aplicamos esse modelo de aprendizagem de máquina de alta dimensão a dois conjuntos de dados de neuroimagem de fonte aberta mais populares, ou seja, a Iniciativa de Neuroimagem da Doença de Alzheimer (ADNI) e a Iniciativa de Marcadores de Progressão de Park

Machine translation (Meta M2M100); the English original follows.

Abstract

As two most prevalent neurodegenerative diseases (NDDs), Alzheimer's disease (AD) and Parkinson's disease (PD) shared commonalities both in symptomology and pathophysiology. However, to what extent and in what way these two distinct disorders overlap remain underexplored. In this study, we propose an explicit, interpretable and spatially adaptive transfer learning framework to elucidate the morphometric biomarkers linked to AD and PD. We applied such high-dimensional machine learning model to two most popular open-source neuroimaging datasets, i.e., Alzheimer's Disease Neuroimaging Initiative (ADNI) and Parkinson's Progression Markers Initiative (PPMI). On the one hand, our cross-disorder classifier revealed neuro-anatomical alteration patterns well aligning with previous neuroimaging research findings and underscoring patients' clinical presentations. On the other hand, the spatially adaptive trained classifier using shared prior achieved statistically superior diagnostic performance compared to respective individual models, which further highlights the cross-disorder framework's efficacy on modeling limited-size datasets across disease domains.

Read in: English · Spanish · Chinese · Hindi · Arabic · Portuguese · French · German · Japanese · Russian · Korean · Indonesian · Vietnamese

Topics: Neuroimaging, Disease, Classifier (UML), Artificial intelligence, Medicine, Machine learning

Sources: OpenAlex (CC0), arXiv, Crossref. Agent Exchange