Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Experiment Video

Updated: May 18, 2026

MRI and PET in Mouse Models of Myocardial Infarction
10:46

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

Binary classification of ¹⁸F-flutemetamol PET using machine learning: comparison with visual reads and structural

Rik Vandenberghe1, Natalie Nelissen, Eric Salmon

  • 1Laboratory for Cognitive Neurology, Experimental Neurology Section, Katholieke Universiteit Leuven, Belgium. rik.vandenberghe@uz.kuleuven.ac.be

Neuroimage
|September 18, 2012
PubMed
Summary

Related Concept Videos

Positron Emission Tomography01:29

Positron Emission Tomography

Positron emission tomography (PET) is a medical imaging technique involving radiopharmaceuticals — substances that emit short-lived radiation. Although the first PET scanner was introduced in 1961, it took 15 more years before radiopharmaceuticals were combined with the technique and revolutionized its potential.
One of the main requirements of a PET scan is a positron-emitting radioisotope, which is produced in a cyclotron and then attached to a substance used by the part of the body being...

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

A Message From the Editors to Our Reviewers: 2025.

Neurology. Clinical practice·2026
Same author

Modulating the default mode network with deep TMS: a proof-of-concept framework with potential relevance to circuits implicated in lack of awareness of cognitive decline.

Frontiers in aging neuroscience·2026
Same author

Tau pathological activity in plasma before the onset of symptomatic Alzheimer's disease.

medRxiv : the preprint server for health sciences·2026
Same author

Differential Progression of Neuroinflammation in Patients with Isolated Rapid-Eye-Movement Sleep Behavior Disorder.

Movement disorders : official journal of the Movement Disorder Society·2026
Same author

Positron emission tomography imaging of the cholinergic system in parkinsonian tremor.

Parkinsonism & related disorders·2026
Same author

Diffusion kurtosis imaging detects cortical microstructural alterations in amyloid-positive MCI patients.

Frontiers in dementia·2026

Support vector machines (SVM) accurately replicate visual amyloid scan classifications using (18)F-flutemetamol PET imaging. This machine learning approach demonstrates higher specificity for Alzheimer's disease detection compared to MRI-based methods.

Area of Science:

  • Neuroimaging
  • Machine Learning
  • Biomarkers

Background:

  • Amyloid imaging using (18)F-flutemetamol PET is crucial for diagnosing Alzheimer's disease (AD).
  • Binary classification of amyloid scans as normal or 'Alzheimer-like' is clinically significant.
  • Supervised machine learning, specifically support vector machines (SVM), can potentially automate and standardize image interpretation.

Purpose of the Study:

  • To evaluate if SVM can replicate visual classification of (18)F-flutemetamol PET scans.
  • To identify image components with the highest diagnostic value according to SVM.
  • To compare SVM-based classification of amyloid scans with SVM-based classification of structural MRI data.

Main Methods:

  • Support vector machines (SVM) with a linear kernel were applied to (18)F-flutemetamol PET and volumetric MRI scans from 72 subjects (27 AD, 20 MCI, 25 controls).

Related Experiment Videos

Last Updated: May 18, 2026

MRI and PET in Mouse Models of Myocardial Infarction
10:46

MRI and PET in Mouse Models of Myocardial Infarction

Published on: December 19, 2013

  • A leave-one-out cross-validation approach was used to train and test the SVM classifiers.
  • Classification performance was assessed by comparing SVM results to visual reads and clinical diagnoses.

    • Main Results:

    • The SVM classifier accurately replicated visual read assignments for (18)F-flutemetamol scans with 100% accuracy.
    • Key brain regions contributing to classification included the striatum, precuneus, cingulate, and middle frontal gyrus.
    • The (18)F-flutemetamol-based SVM classifier showed higher specificity (92%) than the MRI-based classifier (68%) for distinguishing AD from controls, and better identified MCI converters.

    Conclusions:

    • SVM can reliably replicate visual classification of (18)F-flutemetamol amyloid PET scans.
    • (18)F-flutemetamol PET combined with SVM offers high specificity for Alzheimer's disease detection.
    • This approach shows promise for improved diagnostic accuracy, particularly in differentiating between MCI converters and non-converters.