A multitask multimodal ML algorithm for PET feature forecasting and AD classification

Edward Martin


Supervised by Xianfang Sun; Moderated by Paul L Rosin

One in five people age 65 or older experience “mild cognitive impairment”, a condition marked by a slight decline in memory, language, or thought. Affected individuals may be prone to forgetting appointments or losing the thread of conversations. They also have a higher-than-average risk of developing the more pronounced cognitive decline of Alzheimer’s disease. Yet for the majority of people, symptoms do not progress. In fact, in some instances, the symptoms can be temporary or reversible. This presents a challenge for diagnosing Alzheimer’s disease early, when those affected have the best chance of benefiting from the limited number of interventions and drug treatments. This project aims to develop a new machine learning algorithm to predict the early stages of Alzheimer’s using PET imaging and molecular data from the Alzheimer’s Disease Neuroimaging Initiative (http://adni.loni.usc.edu/) including 2109 imaging studies from 1002 patients.

The student should have a good programming skill and a relatively strong mathematical background.

Final Report (05/11/2021) [Zip Archive]

Publication Form