Marco Pagani1,2, Johanna Öberg3, Fabrizio De Carli4, Andrea Calvo5, Cristina Moglia5, Antonio Canosa5, Flavio Nobili6, Silvia Morbelli7,8, Piercarlo Fania9, Angelina Cistaro9, Adriano Chiò5,10,11. 1. Institute of Cognitive Sciences and Technologies, C.N.R, Rome, Italy. 2. Department of Nuclear Medicine, Karolinska Hospital, Stockholm, Sweden. 3. Department of Hospital Physics, Karolinska Hospital, Stockholm, Sweden. 4. Institute of Molecular Bioimaging and Physiology - C.N.R. - Genoa Unit, Italy. 5. ALS Center, 'Rita Levi Montalcini' Department of Neuroscience University of Turin, Turin, Italy. 6. Clinical Neurology Unit, Department of Neurosciences, Rehabilitation, Ophthalmology, Genetics and Mother-Child Health (DINOGMI) University of Genoa, Genoa, Italy. 7. Department of Health Sciences, Nuclear Medicine Unit, University of Genoa, Genoa, Italy. 8. Department of Internal Medicine, University of Genoa, Genoa, Italy. 9. Positron Emission Tomography Centre IRMET S.P.A, Euromedic Inc, Turin, Italy. 10. CNR, Associate Researcher at Institute of Cognitive Sciences and Technologies, C.N.R, Rome, Italy. 11. Neuroscience Institute of Turin, Turin, Italy.
Abstract
OBJECTIVES: Positron emission tomography (PET) and volume of interest (VOI) analysis have recently shown in amyotrophic lateral sclerosis (ALS) an accuracy of 93% in differentiating patients from controls. The aim of this study was to disclose by spatial independent component analysis (ICA) the brain networks involved in ALS pathological processes and evaluate their discriminative value in separating patients from controls. EXPERIMENTAL DESIGN: Two hundred fifty-nine ALS patients and 40 age- and sex-matched control subjects underwent brain 18F-2-fluoro-2-deoxy-D-glucose PET (FDG-PET). Spatial ICA of the preprocessed FDG-PET images was performed. Intensity values were converted to z-scores and binary masks were used as data-driven VOIs. The accuracy of this classifier was tested versus a validated system processing intensity signals in 27 brain meta-VOIs. A support vector machine was independently applied to both datasets and the 'leave-one-out' technique verified the general validity of results. PRINCIPAL OBSERVATIONS: The 8 components selected as pathophysiologically meaningful discriminated patients from controls with 99.0% accuracy, the discriminating value of bilateral cerebellum/midbrain alone representing 96.3%. Among the meta-VOIs, right temporal lobe alone reached an accuracy of 93.7%. CONCLUSIONS: Spatial ICA identified in a very large cohort of ALS patients distinct spatial networks showing a high discriminatory value, improving substantially on the previously obtained accuracy. The cerebellar/midbrain component accounted for the highest accuracy in separating ALS patients from controls. Spatial ICA and multivariate analysis perform better than univariate semi-quantification methods in identifying the neurodegenerative features of ALS and pave the way for inclusion of PET in clinical trials and early diagnosis.
OBJECTIVES: Positron emission tomography (PET) and volume of interest (VOI) analysis have recently shown in amyotrophic lateral sclerosis (ALS) an accuracy of 93% in differentiating patients from controls. The aim of this study was to disclose by spatial independent component analysis (ICA) the brain networks involved in ALS pathological processes and evaluate their discriminative value in separating patients from controls. EXPERIMENTAL DESIGN: Two hundred fifty-nine ALSpatients and 40 age- and sex-matched control subjects underwent brain 18F-2-fluoro-2-deoxy-D-glucose PET (FDG-PET). Spatial ICA of the preprocessed FDG-PET images was performed. Intensity values were converted to z-scores and binary masks were used as data-driven VOIs. The accuracy of this classifier was tested versus a validated system processing intensity signals in 27 brain meta-VOIs. A support vector machine was independently applied to both datasets and the 'leave-one-out' technique verified the general validity of results. PRINCIPAL OBSERVATIONS: The 8 components selected as pathophysiologically meaningful discriminated patients from controls with 99.0% accuracy, the discriminating value of bilateral cerebellum/midbrain alone representing 96.3%. Among the meta-VOIs, right temporal lobe alone reached an accuracy of 93.7%. CONCLUSIONS: Spatial ICA identified in a very large cohort of ALSpatients distinct spatial networks showing a high discriminatory value, improving substantially on the previously obtained accuracy. The cerebellar/midbrain component accounted for the highest accuracy in separating ALSpatients from controls. Spatial ICA and multivariate analysis perform better than univariate semi-quantification methods in identifying the neurodegenerative features of ALS and pave the way for inclusion of PET in clinical trials and early diagnosis.
Authors: Jennifer L Shaffer; Jeffrey R Petrella; Forrest C Sheldon; Kingshuk Roy Choudhury; Vince D Calhoun; R Edward Coleman; P Murali Doraiswamy Journal: Radiology Date: 2012-12-11 Impact factor: 11.105
Authors: Jan Kassubek; Alexander Unrath; Hans-Jürgen Huppertz; Dorothée Lulé; Thomas Ethofer; Anne-Dorte Sperfeld; Albert C Ludolph Journal: Amyotroph Lateral Scler Other Motor Neuron Disord Date: 2005-12
Authors: Esther Verstraete; Martijn P van den Heuvel; Jan H Veldink; Niels Blanken; René C Mandl; Hilleke E Hulshoff Pol; Leonard H van den Berg Journal: PLoS One Date: 2010-10-27 Impact factor: 3.240
Authors: Silvia Francesca Storti; Emanuela Formaggio; Roberta Nordio; Paolo Manganotti; Antonio Fiaschi; Alessandra Bertoldo; Gianna Maria Toffolo Journal: Front Neurosci Date: 2013-05-20 Impact factor: 4.677
Authors: Stefanie M A Willekens; Donatienne Van Weehaeghe; Philip Van Damme; Koen Van Laere Journal: Eur J Nucl Med Mol Imaging Date: 2016-12-08 Impact factor: 9.236
Authors: Donatienne Van Weehaeghe; Martijn Devrome; Michel Koole; Koen Van Laere; Georg Schramm; Joke De Vocht; Wies Deckers; Kristof Baete; Philip Van Damme Journal: Eur J Nucl Med Mol Imaging Date: 2020-04-20 Impact factor: 9.236
Authors: Kelly Smart; Jean-Dominique Gallezot; Nabeel Nabulsi; David Labaree; Ming-Qiang Zheng; Yiyun Huang; Richard E Carson; Ansel T Hillmer; Patrick D Worhunsky Journal: Neuroimage Date: 2020-03-19 Impact factor: 6.556
Authors: Alexandre Savio; Sarah Fünger; Masoud Tahmasian; Srinivas Rachakonda; Andrei Manoliu; Christian Sorg; Timo Grimmer; Vince Calhoun; Alexander Drzezga; Valentin Riedl; Igor Yakushev Journal: J Nucl Med Date: 2017-03-02 Impact factor: 10.057