Accuracy and generalization capability of an automatic method for the detection of typical brain hypometabolism in prodromal Alzheimer disease

  • Fabrizio De CarliEmail author
  • Flavio Nobili
  • Marco Pagani
  • Matteo Bauckneht
  • Federico Massa
  • Matteo Grazzini
  • Cathrine Jonsson
  • Enrico Peira
  • Silvia Morbelli
  • Dario Arnaldi
  • for the Alzheimer’s Disease Neuroimaging Initiative
Original Article



The aim of this study was to verify the reliability and generalizability of an automatic tool for the detection of Alzheimer-related hypometabolic pattern based on a Support-Vector-Machine (SVM) model analyzing 18F-fluorodeoxyglucose (FDG) PET data.


The SVM model processed metabolic data from anatomical volumes of interest also considering interhemispheric asymmetries. It was trained on a homogeneous dataset from a memory clinic center and tested on an independent multicentric dataset drawn from the Alzheimer’s Disease Neuroimaging Initiative. Subjects were included in the study and classified based on a diagnosis confirmed after an adequate follow-up time.


The accuracy of the discrimination between patients with Alzheimer Disease (AD), in either prodromal or dementia stage, and normal aging subjects was 95.8%, after cross-validation, in the training set. The accuracy of the same model in the testing set was 86.5%. The role of the two datasets was then reversed, and the accuracy was 89.8% in the multicentric training set and 88.0% in the monocentric testing set. The classification rate was also evaluated in different subgroups, including non-converter mild cognitive impairment (MCI) patients, subjects with MCI reverted to normal conditions and subjects with non-confirmed memory concern. The percent of pattern detections increased from 77% in early prodromal AD to 91% in AD dementia, while it was about 10% for healthy controls and non-AD patients.


The present findings show a good level of reproducibility and generalizability of a model for detecting the hypometabolic pattern in AD and confirm the accuracy of FDG-PET in Alzheimer disease.


Alzheimer disease MCI due to AD FDG-PET Discriminant analysis Neuroimage classification Classification and prediction Neurodegenerative disorders Support vector machine 



Data collection and sharing for this project was partly funded by the Alzheimer’s Disease Neuroimaging Initiative (ADNI) (National Institutes of Health Grant U01 AG024904) and DOD ADNI (Department of Defense award number W81XWH-12-2-0012). ADNI is funded by the National Institute on Aging, the National Institute of Biomedical Imaging and Bioengineering, and through contributions from the following: AbbVie, Alzheimer’s Association; Alzheimer’s Drug Discovery Foundation; Araclon Biotech; BioClinica, Inc.; Biogen; Bristol-Myers Squibb Company; CereSpir, Inc.; Cogstate; Eisai Inc.; Elan Pharmaceuticals, Inc.; Eli Lilly and Company; EuroImmun; F. Hoffmann-La Roche Ltd. and its affiliated company Genentech, Inc.; Fujirebio; GE Healthcare; IXICO Ltd.; Janssen Alzheimer Immunotherapy Research&Development, LLC.; Johnson & Johnson Pharmaceutical Research&Development LLC.; Lumosity; Lundbeck; Merck&Co., Inc.; Meso Scale Diagnostics, LLC.; NeuroRx Research; Neurotrack Technologies; Novartis Pharmaceuticals Corporation; Pfizer Inc.; Piramal Imaging; Servier; Takeda Pharmaceutical Company; and Transition Therapeutics. The Canadian Institutes of Health Research provides funds to support ADNI clinical sites in Canada. Private sector contributions are facilitated by the Foundation for the National Institutes of Health ( The grantee organization is the Northern California Institute for Research and Education, and the study is coordinated by the Alzheimer’s Therapeutic Research Institute at the University of Southern California. ADNI data are disseminated by the Laboratory for Neuro Imaging at the University of Southern California.

A substantial part of data used in preparation of this article were obtained from the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database ( As such, the investigators within the ADNI contributed to the design and implementation of ADNI and/or provided data but did not participate in analysis or writing of this report. A complete listing of ADNI investigators can be found at:

Compliance with ethical standards

Conflict of interest

F.N.: received personal fees and nonfinancial support from GE Healthcare, non-financial support from Eli-Lilly and grants from Chiesi Farmaceutici; D.A. received speaking honoraria from Fidia s.p.a.; S.M. acted as a consultant for Eli Lilly in 2014 and for Avid Radiopharmaceuticals in 2016. All other authors have no potential conflicts to declare.

Ethical approval

The institutional review board of the University of Genoa approved the recording and data treatment procedures involving human participants in this study and all procedures were in accordance with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.

Informed consent

Informed consent was obtained from all individual participants included in the study.

Supplementary material

259_2018_4197_MOESM1_ESM.pdf (440 kb)
ESM 1 (PDF 440 kb)


  1. 1.
    Frisoni GB, Bocchetta M, Chételat G, Rabinovici GD, De Leon MJ, Kaye J, et al. Imaging markers for Alzheimer disease: which vs how. Neurology. 2013;81:487–500.CrossRefGoogle Scholar
  2. 2.
    Jack CR, Knopman DS, Jagust WJ, Shaw LM, Aisen PS, Weiner MW, et al. Hypothetical model of dynamic biomarkers of the Alzheimer’s pathological cascade. Lancet Neurol. 2010;9:119–28.CrossRefGoogle Scholar
  3. 3.
    Landau SM, Harvey D, Madison CM, Koeppe RA, Reiman EM, Foster NL, et al. Associations between cognitive, functional, and FDG-PET measures of decline in AD and MCI. Neurobiol Aging. 2011;32:1207–18.CrossRefGoogle Scholar
  4. 4.
    Signorini M, Paulesu E, Friston K, Perani D, Colleluori A, Lucignani G, et al. Rapid assessment of regional cerebral metabolic abnormalities in single subjects with quantitative and nonquantitative [18F]FDG PET: a clinical validation of statistical parametric mapping. NeuroImage. 1999;9:63–80.CrossRefGoogle Scholar
  5. 5.
    Caminiti SP, Ballarini T, Sala A, Cerami C, Presotto L, Santangelo R, et al. FDG-PET and CSF biomarker accuracy in prediction of conversion to different dementias in a large multicentre MCI cohort. NeuroImage Clin. Elsevier. 2018;18:167–77.CrossRefGoogle Scholar
  6. 6.
    Perani D, Della Rosa PA, Cerami C, Gallivanone F, Fallanca F, Vanoli EG, et al. Validation of an optimized SPM procedure for FDG-PET in dementia diagnosis in a clinical setting. NeuroImage Clin [Internet]. Elsevier B.V. 2014;6:445–54. Available from:
  7. 7.
    Herholz K, Salmon E, Perani D, Baron JC, Holthoff V, Frölich L, et al. Discrimination between Alzheimer dementia and controls by automated analysis of multicenter FDG PET. NeuroImage. 2002;17:302–16.CrossRefGoogle Scholar
  8. 8.
    Haense C, Herholz K, Jagust WJ, Heiss WD. Performance of FDG PET for detection of Alzheimer’s disease in two independent multicentre samples (NEST-DD and ADNI). Dement Geriatr Cogn Disord. 2009;28:259–66.CrossRefGoogle Scholar
  9. 9.
    Chen K, Ayutyanont N, Langbaum JBS, Fleisher AS, Reschke C, Lee W, et al. Characterizing Alzheimer’s disease using a hypometabolic convergence index. NeuroImage [Internet]. Elsevier Inc. 2011;56:52–60. Available from:
  10. 10.
    Tzourio-Mazoyer N, Landeau B, Papathanassiou D, Crivello F, Etard O, Delcroix N, et al. Automated anatomical labeling of activations in SPM using a macroscopic anatomical parcellation of the MNI MRI single-subject brain. NeuroImage. 2002;15:273–89.CrossRefGoogle Scholar
  11. 11.
    Pagani M, De Carli F, Morbelli S, Öberg J, Chincarini A, Frisoni GB, et al. Volume of interest-based [18F]fluorodeoxyglucose PET discriminates MCI converting to Alzheimer’s disease from healthy controls. A European Alzheimer’s disease consortium (EADC) study. NeuroImage Clin [Internet]. 2015;7:34–42. Available from:
  12. 12.
    Pagani M, Nobili F, Morbelli S, Arnaldi D, Giuliani A, Öberg J, et al. Early identification of MCI converting to AD: a FDG PET study. Eur J Nucl Med Mol Imaging. 2017;44:2042–52.CrossRefGoogle Scholar
  13. 13.
    Smailagic N, Vacante M, Hyde C, Martin S, Ukoumunne O, Sachpekidis C. F-FDG-PET for the early diagnosis of Alzheimer ’ s disease dementia and other dementias in people with mild cognitive impairment ( MCI ) (review). Cochrane Database Syst Rev. 2015:1–104.Google Scholar
  14. 14.
    Rathore S, Habes M, Iftikhar MA, Shacklett A, Davatzikos C. A review on neuroimaging-based classification studies and associated feature extraction methods for Alzheimer’s disease and its prodromal stages. NeuroImage. Elsevier. 2017;155:530–48.CrossRefGoogle Scholar
  15. 15.
    Morbelli S, Drzezga A, Perneczky R, Frisoni GB, Caroli A, Van Berckel BNM, et al. Resting metabolic connectivity in prodromal Alzheimer’s disease. A European Alzheimer disease consortium (EADC) project. Neurobiol Aging [Internet]. Elsevier Inc. 2012;33:2533–50. Available from:
  16. 16.
    Herholz K. PET studies in dementia. Ann Nucl Med. 2003;17:79–89.CrossRefGoogle Scholar
  17. 17.
    Herholz K, Westwood S, Haense C, Dunn G. Evaluation of a calibrated 18F-FDG PET score as a biomarker for progression in Alzheimer disease and mild cognitive impairment. J Nucl Med [Internet]. 2011;52:1218–26. Available from:
  18. 18.
    Caroli A, Prestia A, Chen K, Ayutyanont N, Landau SM, Madison CM, et al. Summary metrics to assess Alzheimer disease-related hypometabolic pattern with 18F-FDG PET: head-to-head comparison. J Nucl Med [Internet]. 2012;53:592–600. Available from:
  19. 19.
    Pagani M, De Carli F, Morbelli S, Öberg J, Chincarini A, Frisoni GB, et al. Volume of interest-based [18F]fluorodeoxyglucose PET discriminates MCI converting to Alzheimer’s disease from healthy controls. A European Alzheimer’s disease consortium (EADC) study. NeuroImage Clin [Internet]. Elsevier B.V. 2015;7:34–42. Available from:
  20. 20.
    Pagani M, Giuliani A, Öberg J, De Carli F, Morbelli S, Girtler N, et al. Progressive disintegration of brain networking from Normal aging to Alzheimer disease: analysis of independent components of 18 F-FDG PET data. J Nucl Med [Internet]. 2017;58:1132–9. Available from:
  21. 21.
    Petersen RC, Negash S. Mild cognitive impairment: an overview. CNS Spectr. 2008;13:45–53.CrossRefGoogle Scholar
  22. 22.
    Albert MS, DeKosky ST, Dickson D, Dubois B, Feldman HH, Fox NC, et al. The diagnosis of mild cognitive impairment due to Alzheimer’s disease: recommendations from the National Institute on Aging-Alzheimer’s association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimer’s Dement [Internet]. Elsevier Ltd. 2011;7:270–9. Available from:
  23. 23.
    McKhann GM, Knopman DS, Chertkow H, Hyman BT, Jack CR, Kawas CH, et al. The diagnosis of dementia due to Alzheimer’s disease: recommendations from the National Institute on Aging-Alzheimer’s association workgroups on diagnostic guidelines for Alzheimer’s disease. Alzheimer’s Dement [Internet]. Elsevier Ltd. 2011;7:263–9. Available from:
  24. 24.
    Varrone A, Asenbaum S, Vander Borght T, Booij J, Nobili F, Någren K, et al. EANM procedure guidelines for PET brain imaging using [18F]FDG, version 2. Eur J Nucl Med Mol Imaging. 2009;36:2103–10.CrossRefGoogle Scholar
  25. 25.
    Della Rosa PA, Cerami C, Gallivanone F, Prestia A, Caroli A, Castiglioni I, et al. A standardized [18F]-FDG-PET template for spatial normalization in statistical parametric mapping of dementia. Neuroinformatics. 2014;12:575–93.CrossRefGoogle Scholar
  26. 26.
    Soonawala D, Amin T, Ebmeier KP, Steele DJ, Dougall NJ, Best J, et al. Statistical parametric mapping of99mTc-HMPAO-SPECT images for the diagnosis of Alzheimer’s disease: normalizing to cerebellar tracer uptake. NeuroImage. 2002;17:1193–202.CrossRefGoogle Scholar
  27. 27.
    Dukart J, Mueller K, Horstmann A, Vogt B, Frisch S, Barthel H, et al. Differential effects of global and cerebellar normalization on detection and differentiation of dementia in FDG-PET studies. Neuroimage. Elsevier Inc. 2010;49:1490–5.CrossRefGoogle Scholar
  28. 28.
    Morbelli S, Brugnolo A, Bossert I, Buschiazzo A, Frisoni GB, Galluzzi S, et al. Visual versus semi-quantitative analysis of18F-FDG-PET in amnestic MCI: an European Alzheimer’s disease consortium (EADC) project. J Alzheimer’s Dis [Internet]. 2015;44:815–26. Available from:
  29. 29.
    Zahn R, Juengling F, Bubrowski P, Jost E, Dykierek P, Talazko J, et al. Hemispheric asymmetries of hypometabolism associated with semantic memory impairment in Alzheimer’s disease: a study using positron emission tomography with fluorodeoxyglucose-F18. Psychiatry Res Neuroimaging. 2004;132:159–72.CrossRefGoogle Scholar
  30. 30.
    Brown LD, Cai TT, Dasgupta A. Interval estimation for a binomial. Stat Sci. 2001;16:101–33.Google Scholar
  31. 31.
    Simel DL, Samsa GP, Matchar DB. Likelihood ratios with confidence: sample size estimation for diagnostic test studies. J Clin Epidemiol [Internet]. 1991;44:763–70. Available from:
  32. 32.
    Chen F, Xue Y, Tan MT, Chen P. Efficient statistical tests to compare Youden index: accounting for contingency correlation. Stat Med. 2015;34:1560–76.CrossRefGoogle Scholar
  33. 33.
    Qin G, Hotilovac L. Comparison of non-parametric confidence intervals for the area under the ROC curve of a continuous-scale diagnostic test. Stat Methods Med Res. 2008;17:207–21.CrossRefGoogle Scholar
  34. 34.
    Hanley JA, McNeil BJ. The meaning and use of the area under a receiver operating characteristic (ROC) curve. Radiology [Internet]. Radiological Society of North America. 1982;143:29–36. Available from:
  35. 35.
    Landau SM, Mintun MA, Joshi AD, Koeppe RA, Petersen RC, Aisen PS, et al. Amyloid deposition, hypometabolism, and longitudinal cognitive decline. Ann Neurol [Internet]. 2012;72:578–86. Available from:
  36. 36.
    Cabral C, Morgado PM, Campos Costa D, Silveira M. Predicting conversion from MCI to AD with FDG-PET brain images at different prodromal stages. Comput Biol Med [Internet]. Elsevier. 2015;58:101–9. Available from:
  37. 37.
    Pagani M, Giuliani A, Öberg J, Chincarini A, Morbelli S, Brugnolo A, et al. Predicting the transition from normal aging to Alzheimer’s disease: a statistical mechanistic evaluation of FDG-PET data. Neuroimage [Internet]. Elsevier Inc. 2016;141:282–90. Available from:
  38. 38.
    Arnaldi D, Morbelli S, Brugnolo A, Girtler N, Picco A, Ferrara M, et al. Functional neuroimaging and clinical features of drug naive patients with de novo Parkinson’s disease and probable RBD. Parkinsonism Relat Disord. 2016;29:47–53.CrossRefGoogle Scholar
  39. 39.
    Kryscio RJ, Abner EL, Cooper GE, Fardo DW, Jicha GA, Nelson PT, et al. Self-reported memory complaints: implications from a longitudinal cohort with autopsies. Neurology. 2014;83(15):1359-65.Google Scholar
  40. 40.
    Rasmussen JM, Lakatos A, van Erp TGM, Kruggel F, Keator DB, Fallon JT, et al. Empirical derivation of the reference region for computing diagnostic sensitive18fluorodeoxyglucose ratios in Alzheimer’s disease based on the ADNI sample. Biochim Biophys Acta - Mol Basis Dis [Internet]. Elsevier B.V. 2012;1822:457–66. Available from:
  41. 41.
    Braak H, Braak E, Bohl J, Lang W. Alzheimer’s disease: amyloid plaques in the cerebellum. J Neurol Sci. 1989;93:277–87.CrossRefGoogle Scholar
  42. 42.
    Catafau AM, Bullich S, Seibyl JP, Barthel H, Ghetti B, Leverenz J, et al. Cerebellar amyloid- plaques: how frequent are they, and do they influence 18F-Florbetaben SUV ratios? J Nucl Med [Internet]. 2016;57:1740–5 Available from: Scholar
  43. 43.
    Ishii K, Sasaki M, Kitagaki H, Yamaji S, Sakamoto S, Matsuda K, et al. Reduction of cerebellar glucose metabolism in advanced Alzheimer’s disease. J Nucl Med [Internet]. 1997;38:925–8 Available from: Scholar
  44. 44.
    Bocchetta M, Cardoso MJ, Cash DM, Ourselin S, Warren JD, Rohrer JD. Patterns of regional cerebellar atrophy in genetic frontotemporal dementia. NeuroImage Clin [Internet]. The Authors. 2016;11:287–90. Available from:
  45. 45.
    Bauckneht M, Chincarini A, Piva R, Arnaldi D, Girtler N, Massa F, et al. Metabolic correlates of reserve and resilience in MCI due to Alzheimer’s disease (AD) Rik Ossenkoppele. Alzheimer’s Res Ther Alzheimer’s Research & Therapy. 2018;10:1–13.Google Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2018

Authors and Affiliations

  • Fabrizio De Carli
    • 1
    Email author
  • Flavio Nobili
    • 2
  • Marco Pagani
    • 3
    • 4
  • Matteo Bauckneht
    • 5
    • 6
  • Federico Massa
    • 2
  • Matteo Grazzini
    • 2
  • Cathrine Jonsson
    • 4
  • Enrico Peira
    • 7
  • Silvia Morbelli
    • 5
    • 6
  • Dario Arnaldi
    • 2
  • for the Alzheimer’s Disease Neuroimaging Initiative
  1. 1.Institute of Molecular Bioimaging and PhysiologyNational Research CouncilGenoaItaly
  2. 2.Department of Neuroscience (DINOGMI), IRCCS Polyclinic San Martino-ISTUniversity of GenoaGenoaItaly
  3. 3.Institute of Cognitive Sciences and TechnologiesCNRRomeItaly
  4. 4.Medical Radiation Physics and Nuclear Medicine, Imaging and PhysiologyKarolinska University HospitalStockholmSweden
  5. 5.Department of Health Sciences (DISSAL)University of GenoaGenoaItaly
  6. 6.Nuclear Medicine UnitPolyclinic San Martino HospitalGenoaItaly
  7. 7.National Institute of Nuclear Physics (INFN)GenoaItaly

Personalised recommendations