23 Dec Determining Brain Age Using AI and PET Imaging
MedicalResearch.com Interview with:
Dr. Weidong Luo
MedicalResearch.com: What is the background for this study?
Response: We were interested in whether or not we can predict the age of the brain accurately from T1 weighted MRI and/or fluorodeoxyglucose (FDG) PET scans using the brain volumetric and the relative metabolic activity. The uptake of FDG is a clinical marker used to measure the uptake of glucose and therefore metabolism.
Also, we were interested in the patterns of the predicted ages for Alzheimer’s disease (AD) and minor cognitive impairment (MCI) subjects when using their brain measurements for age prediction in the normal brain age model.
MedicalResearch.com: What are the main findings?
Response: We have found that the normal brain age model based on MRI imaging alone can predict normal subject’s age accurately. However, the brain age model using PET metabolic and MRI volumetric measurements has a better performance for older normal subjects. We have also found that brain age models created from normal subjects cannot predict the ages for Alzheimer’s disease and MCI subjects correctly and showed clear biases in their predicted ages.
MedicalResearch.com: What should readers take away from your report?
Response: Structural volumetry alone or combined with metabolic measurements can predict the brain age. The predicted ages for AD had a large discrepancy between normal and younger AD subjects from 55 to 70 years. This suggests that Alzheimer’s disease and MCI is likely caused by pathological changes, rather than an accelerated aging process. The discrepancy between predicted age and the actual calendar age might be a potential biomarker to distinguish patients with Alzheimer’s disease from normal within the age range from 55 to 70 years old.
MedicalResearch.com: What recommendations do you have for future research as a result of this work?
Response: We would like to see what the brain age model can reveal when using PET scans with different radiotracers, such as F-18 Florbetapir that is a marker for beta amyloid deposits, rather than metabolic activity. Also, it would be interesting to compare the outcomes from different machine learning models using a similar data set.
RSNA 2019 presentation:
Determining Brain Age Using Machine Learning Combined with Automated Brain Segmentation and PET Imaging in Normal, Alzheimer’s Disease and Mild Cognitive Impairment Subjects
W Luo, PhD, San Diego, CA; A M Ulug, PhD; W Thompson, PhD; R Haxton; S Magda, PhD; L J Kjonigsen, MSc; et al. (email@example.com)
The information on MedicalResearch.com is provided for educational purposes only, and is in no way intended to diagnose, cure, or treat any medical or other condition. Always seek the advice of your physician or other qualified health and ask your doctor any questions you may have regarding a medical condition. In addition to all other limitations and disclaimers in this agreement, service provider and its third party providers disclaim any liability or loss in connection with the content provided on this website.