Lisa Nickerson, PhD

David Harper, PhD

You (Lily) Cheng, PhD

Alzheimer’s disease (AD) symptoms and progression vary widely across people. Although AD is defined by the presence of amyloid-beta plaques and tau tangles, these “hallmarks” may accumulate at different rates and in different regions across the brain. While individual brain scans using technologies like magnetic resonance imaging (MRI) or positron emission tomography (PET) can capture snapshots of disease signals, they only offer clinicians a partial picture when considered individually.

In a new study led by You (Lily) Cheng, PhD, David Harper, PhD, and Lisa Nickerson, PhD, of McLean Hospital, researchers tested whether combining multiple types of brain scans from the same person could better capture the complexity of Alzheimer’s disease.

Using a new machine learning model for fusing different kinds of images, they analyzed amyloid and tau PET scans together with multiple MRI measures of brain structure from 274 participants in the Alzheimer’s Disease Neuroimaging Initiative.

Through this data-fusion approach, the team was able to identify integrated, spatially detailed brain patterns linked to cognitive decline, clinical diagnosis and genetic risk. One pattern connecting tau buildup with structural brain changes was especially accurate at distinguishing mild cognitive impairment from mild dementia, a distinction that can be difficult to make in clinical practice. Another pattern, driven primarily by amyloid burden, differentiated carriers of APOE ε4 (a major genetic risk factor for AD) from non‑carriers.

According to the authors, this tactic of combining multiple brain measures into a unified framework could help improve disease staging and guide more targeted approaches in research and care.

Published in Alzheimer’s & Dementia: Diagnosis, Assessment & Disease Monitoring on May 21, 2026 | Read the paper: “Investigating the Amyloid-Tau-Neurodegeneration Framework in Alzheimer’s Disease Using Semi-Supervised Multimodal Imaging Data Fusion”

Summary reviewed by: You (Lily) Cheng, PhD, lead author; David Harper, PhD, and Lisa Nickerson, PhD, senior authors