Forskning
Udskriv Udskriv
Switch language
Rigshospitalet - en del af Københavns Universitetshospital
Udgivet

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

Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. Validity and reliability of extrastriatal [11C]raclopride binding quantification in the living human brain

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  2. Optimization of preprocessing strategies in Positron Emission Tomography (PET) neuroimaging: A [11C]DASB PET study

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. Functional neuroimaging of recovery from motor conversion disorder: A case report

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  4. Comparing fully automated state-of-the-art cerebellum parcellation from magnetic resonance images

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  5. Men with high serotonin 1B receptor binding respond to provocations with heightened amygdala reactivity

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  1. Ageing as a risk factor for neurodegenerative disease

    Publikation: Bidrag til tidsskriftReviewForskningpeer review

  2. Automatically computed rating scales from MRI for patients with cognitive disorders

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  3. Exercise as a potential modulator of inflammation in patients with Alzheimer's disease measured in cerebrospinal fluid and plasma

    Publikation: Bidrag til tidsskriftTidsskriftartikelForskningpeer review

  • Rik Vandenberghe
  • Natalie Nelissen
  • Eric Salmon
  • Adrian Ivanoiu
  • Steen Hasselbalch
  • Allan Andersen
  • Ejnar Alex Kørner
  • Lennart Minthon
  • David Brooks
  • Koen Van Laere
  • Patrick Dupont
Vis graf over relationer
(18)F-flutemetamol is a positron emission tomography (PET) tracer for in vivo amyloid imaging. The ability to classify amyloid scans in a binary manner as 'normal' versus 'Alzheimer-like', is of high clinical relevance. We evaluated whether a supervised machine learning technique, support vector machines (SVM), can replicate the assignments made by visual readers blind to the clinical diagnosis, which image components have highest diagnostic value according to SVM and how (18)F-flutemetamol-based classification using SVM relates to structural MRI-based classification using SVM within the same subjects. By means of SVM with a linear kernel, we analyzed (18)F-flutemetamol scans and volumetric MRI scans from 72 cases from the (18)F-flutemetamol phase 2 study (27 clinically probable Alzheimer's disease (AD), 20 amnestic mild cognitive impairment (MCI), 25 controls). In a leave-one-out approach, we trained the (18)F-flutemetamol based classifier by means of the visual reads and tested whether the classifier was able to reproduce the assignment based on visual reads and which voxels had the highest feature weights. The (18)F-flutemetamol based classifier was able to replicate the assignments obtained by visual reads with 100% accuracy. The voxels with highest feature weights were in the striatum, precuneus, cingulate and middle frontal gyrus. Second, to determine concordance between the gray matter volume- and the (18)F-flutemetamol-based classification, we trained the classifier with the clinical diagnosis as gold standard. Overall sensitivity of the (18)F-flutemetamol- and the gray matter volume-based classifiers were identical (85.2%), albeit with discordant classification in three cases. Specificity of the (18)F-flutemetamol based classifier was 92% compared to 68% for MRI. In the MCI group, the (18)F-flutemetamol based classifier distinguished more reliably between converters and non-converters than the gray matter-based classifier. The visual read-based binary classification of (18)F-flutemetamol scans can be replicated using SVM. In this sample the specificity of (18)F-flutemetamol based SVM for distinguishing AD from controls is higher than that of gray matter volume-based SVM.
OriginalsprogEngelsk
TidsskriftNeuroImage
Vol/bind64
Sider (fra-til)517-25
Antal sider9
ISSN1053-8119
DOI
StatusUdgivet - 2013

ID: 36729246