2024 Alzheimer's Association Research Fellowship to Promote Diversity (AARF-D)

Harmonization of Tau PET Tracers to a Common Scale Using Head-to-Head Data

How can brain scans obtained with different methods be combined or compared? 

Guilherme Povala, Ph.D.
University of Pittsburgh
Pittsburgh, PA - United States

Background

Alzheimer’s is characterized in part by the accumulation of an abnormal form of the tau protein into clumps called tangles. Tau tangles appear to form distinctive patterns in the brains of individuals with Alzheimer’s — patterns that differ from those seen in other forms of dementia. One technique for identifying such patterns in living individuals is via a brain scan called positron emission tomography (PET). This imaging technique uses special “tracers” that highlight the amount and location of tau tangles in the living brain. Tau PET is used in the clinical evaluation of patients and as an outcome measure in Alzheimer’s clinical trials. Several tau PET tracers have been developed in recent years and have distinct properties. This means that tau PET data obtained using different tracers cannot be meaningfully compared or combined.

Research Plan

Dr. Guilherme Povala and colleagues will use an advanced computer science technique called deep learning to overcome the challenge of comparing scans from different PET tracers. The researchers will use tau PET data from the HEAD study to train their deep-learning computer models. The data will include brain scans obtained with two different tracers and from both young and aged individuals with and without cognitive impairment. The team’s goal is to develop a freely available tool that allows tau PET images obtained with different tracers to be directly compared.

Impact

This study may result in a tool that will allow researchers to merge tau PET datasets and compare results from clinical trials using different tracers.