Related Experiment Video
Updated: Dec 22, 2025
Identification of Disease-related Spatial Covariance Patterns using Neuroimaging Data
Published on: June 26, 2013
The Use of Random Forests to Identify Brain Regions on Amyloid and FDG PET Associated With MoCA Score
Katherine Zukotynski1, Vincent Gaudet2, Phillip H Kuo3
1From the University of Toronto, Toronto and McMaster University, Hamilton.
Purpose:
The aim of this study was to evaluate random forests (RFs) to identify ROIs on F-florbetapir and F-FDG PET associated with Montreal Cognitive Assessment (MoCA) score.
Materials And Methods:
Fifty-seven subjects with significant white matter disease presenting with either transient ischemic attack/lacunar stroke or mild cognitive impairment from early Alzheimer disease, enrolled in a multicenter prospective observational trial, had MoCA and F-florbetapir PET; 55 had F-FDG PET. Scans were processed using the MINC toolkit to generate SUV ratios, normalized to cerebellar gray matter (F-florbetapir PET), or pons (F-FDG PET). SUV ratio data and MoCA score were used for supervised training of RFs programmed in MATLAB.
Results:
F-Florbetapir PETs were randomly divided into 40 training and 17 testing scans; 100 RFs of 1000 trees, constructed from a random subset of 16 training scans and 20 ROIs, identified ROIs associated with MoCA score: right posterior cingulate gyrus, right anterior cingulate gyrus, left precuneus, left posterior cingulate gyrus, and right precuneus. Amyloid increased with decreasing MoCA score. F-FDG PETs were randomly divided into 40 training and 15 testing scans; 100 RFs of 1000 trees, each tree constructed from a random subset of 16 training scans and 20 ROIs, identified ROIs associated with MoCA score: left fusiform gyrus, left precuneus, left posterior cingulate gyrus, right precuneus, and left middle orbitofrontal gyrus. F-FDG decreased with decreasing MoCA score.
Conclusions:
Random forests help pinpoint clinically relevant ROIs associated with MoCA score; amyloid increased and F-FDG decreased with decreasing MoCA score, most significantly in the posterior cingulate gyrus.
Insights
Random forests identified brain regions linked to cognitive scores in patients with white matter disease. Amyloid PET uptake increased and F-FDG PET uptake decreased as cognitive scores declined.
Area of Science:
- Neuroimaging
- Machine Learning
- Cognitive Neurology
Background:
- Mild cognitive impairment and stroke share risk factors.
- Positron Emission Tomography (PET) aids in diagnosing neurodegenerative diseases.
- Montreal Cognitive Assessment (MoCA) is a key cognitive screening tool.
Purpose of the Study:
- To evaluate random forests (RFs) for identifying regions of interest (ROIs) on F-florbetapir and F-FDG PET scans.
- To correlate these ROIs with Montreal Cognitive Assessment (MoCA) scores.
Main Methods:
- Utilized data from 57 subjects with white matter disease undergoing MoCA and PET scans (F-florbetapir and F-FDG).
- Processed PET scans to generate SUV ratios, normalized to specific brain regions.
- Employed supervised training of RFs using SUV ratio data and MoCA scores.
Main Results:
- RFs identified specific ROIs associated with MoCA scores for both F-florbetapir (e.g., posterior cingulate gyrus, precuneus) and F-FDG (e.g., fusiform gyrus, precuneus).
- Amyloid uptake increased with decreasing MoCA scores.
- F-FDG uptake decreased with decreasing MoCA scores.
Conclusions:
- Random forests effectively pinpoint clinically relevant ROIs linked to MoCA scores.
- Amyloid and F-FDG PET findings correlate with cognitive decline, particularly in the posterior cingulate gyrus.
![Studying Metabolic Brain Connectivity Using 2-Deoxy-2-[18F]Fluoro-D-Glucose Dynamic Positron Emission Tomography at the Single-subject Level](/_next/image?url=https%3A%2F%2Fcloudfront.jove.com%2FCDNSource%2Fteasers%2F67458.jpg&w=3840&q=50)