Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloScaled subprofile modeling and convolutional neural networks for the identification of Parkinson's disease in 3D nuclear imaging data
Anno di pubblicazione2019
Autore/iMartinez- Manzanera O, Meles SK, Leenders KL, Renken RJ, Pagani M, Arnaldi D, Nobili F, Obeso J, Rodriguez Oroz M, Morbelli S, Maurits NM
Affiliazioni autoriDepartment of Neurology, University Medical Center Groningen, University of Groningen, the Netherlands Faculty of Medical Sciences, University Medical Center Groningen, University of Groningen,, the Netherlands Institute of Cognitive Sciences and Technologies, CNR, S. Martino dellaBattaglia, 44- 00185, Rome, Italy Department of Nuclear Medicine, Karolinska Hospital. Huddinge S-141 86, Stockholm, Sweden Department of Nuclear Medicine, University of Groningen, University Medical Center Groningen, The Netherlands Department of Neuroscience (DINOGMI), University of Genoa and IRCCS AOU San Martino-IST, Italy CINAC, HM Puerta del Sur and CEU-San Pablo University, Madrid. CIBERNED, Instituto Carlos III, Madrid, Spain Department of Neurosciences of the Biodonostia Health Research Institute, BegiristainDoktoreaPasealekua, 20014, Donostia, Guipúzcoa, Spain Nuclear Medicine, Department of Health Sciences (DISSAL), University of Genoa and IRCCS AOU San Martino-IST, Genoa, Italy Department of Neurology, University Medical Center Groningen, University of Groningen, the Netherlands
Autori CNR e affiliazioni
  • inglese
AbstractOver the last years convolutional neural networks (CNNs) have shown remarkable results in different image classification tasks, including medical imaging. One area that has been less explored with CNNs is Positron Emission Tomography (PET). FDG-PET is a PET technique employed to obtain a representation of brain metabolic function. In this study we employed 3D CNNs in fluorodeoxyglucose (FDG)-positron emission tomography (PET)brain images with the purpose of discriminating patients diagnosed with Parkinson's disease (PD) from controls. We employed Scaled Subprofile Modeling using Principal Component Analysis as a preprocessing step to focus on specific brain regions and limit the number of voxels that are used as input for the CNNs, thereby increasing the signal-to-noise ratio in our data. We performed hyper-parameter optimization on three CNN architectures to estimate the classification accuracy of the networks on new data. The best performance that we obtained was accuracy=0.86, and area under the receiver operating characteristiccurve (AUC)= 0.94 on the test set. We believe that, with larger datasets, PD patients could be reliably distinguished from controls by FDG-PET scans alone and that this technique could be applied to more clinically challenging tasks, like the differential diagnosis of neurological disorders with similar symptoms, such as PD, Progressive Supranuclear Palsy (PSP) and Multiple System Atrophy (MSA).
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da-
Pagine a-
Pagine totali12
RivistaInternational journal of neural systems
Attiva dal 1989
Editore: World Scientific. - Singapore
Paese di pubblicazione: Singapore
Lingua: inglese
ISSN: 0129-0657
Titolo chiave: International journal of neural systems
Titolo abbreviato: Int. j. neural syst.
Numero volume della rivista-
Fascicolo della rivista-
Verificato da refereeSì: Internazionale
Stato della pubblicazionePreprint
Indicizzazione (in banche dati controllate)-
Parole chiavePositron Emission Tomography, Convolutional Neural Networks, Parkinson's disease, Principal Component Analysis
Link (URL, URI)-
Titolo parallelo-
Scadenza embargo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • ISTC — Istituto di scienze e tecnologie della cognizione
Moduli/Attività/Sottoprogetti CNR
  • ME.P02.015.001 : Neuropatologie e bisogni individuali: diagnostica per immagini, assessment linguistico-cognitivo, counseling genetico e trattamento riabilitativo
Progetti Europei-