Automated analysis of FDG-PET scans may predict rate of cognitive decline

Article

FDG-PET imaging has become an accepted, reimburseable approach for diagnosing Alzheimer's and other neurodegenerative diseases.

CONTEXT: FDG-PET imaging has become an accepted, reimburseable approach for diagnosing Alzheimer's and other neurodegenerative diseases. No clinically practical method has been proven to predict rate of cognitive degeneration of individuals, however. Dr. Daniel Silverman, an associate professor of molecular medicine and pharmacology at the University of California, Los Angeles, is developing a way to quantify FDG-PET data to predict the rate of cognitive decline.

RESULTS: Silverman and Dr. Gary Small, director of the UCLA Center on Aging, studied 25 subjects using formal neuropsychologic tests and standard clinical brain scans at baseline and two years later. Brain metabolism for each subject was automatically analyzed, using a standardized region of interest (sROI) approach that examines 240 regions and groups them into 42 regional clusters. As the most common types of neurodegenerative processes involving progressively diminished language and memory are associated with posterior-predominant hypometabolism, an index was constructed to capture the posterior/anterior gradient reflected by loss of metabolism in some posterior regional clusters.

FDG-PET predicted the rate of cognitive decline in some subgroups of patients within 20% of the actual rate of change.

IMAGE: Standardized ROI approach automatically quantifies loss of metabolism in some posterior regional clusters (planes 22, 24, and 32) relative to metabolism of some better preserved regional clusters in prefrontal cortex (plane 20) in individual subjects.

IMPLICATIONS: This study demonstrated the feasibility of using an automated analysis of FDG-PET scans in a clinical setting to predict rates of cognitive decline.

"It's a promising start," said Dr. Silverman. "But research needs to be done with much larger groups of subjects."

Recent Videos
What New Research Reveals About the Impact of AI and DBT Screening: An Interview with Manisha Bahl, MD
Can AI Assessment of Longitudinal MRI Scans Improve Prediction for Pediatric Glioma Recurrence?
A Closer Look at MRI-Guided Adaptive Radiotherapy for Monitoring and Treating Glioblastomas
Incorporating CT Colonography into Radiology Practice
What New Research Reveals About Computed Tomography and Radiation-Induced Cancer Risk
What New Interventional Radiology Research Reveals About Treatment for Breast Cancer Liver Metastases
New Mammography Studies Assess Image-Based AI Risk Models and Breast Arterial Calcification Detection
Can Deep Learning Provide a CT-Less Alternative for Attenuation Compensation with SPECT MPI?
Employing AI in Detecting Subdural Hematomas on Head CTs: An Interview with Jeremy Heit, MD, PhD
Pertinent Insights into the Imaging of Patients with Marfan Syndrome
Related Content
© 2025 MJH Life Sciences

All rights reserved.