OBJECTIVE: To develop and validate a tool for Alzheimer's disease (AD) diagnosis in individual subjects using support vector machine (SVM)-based classification of structural MR (sMR) images. BACKGROUND: Libraries of sMR scans of clinically well characterized subjects can be harnessed for the purpose of diagnosing new incoming subjects. METHODS: One hundred ninety patients with probable AD were age- and gender-matched with 190 cognitively normal (CN) subjects. Three different classification models were implemented: Model I uses tissue densities obtained from sMR scans to give STructural Abnormality iNDex (STAND)-score; and Models II and III use tissue densities as well as covariates (demographics and Apolipoprotein E genotype) to give adjusted-STAND (aSTAND)-score. Data from 140 AD and 140 CN were used for training. The SVM parameter optimization and training were done by four-fold cross validation (CV). The remaining independent sample of 50 AD and 50 CN was used to obtain a minimally biased estimate of the generalization error of the algorithm. RESULTS: The CV accuracy of Model II and Model III aSTAND-scores was 88.5% and 89.3%, respectively, and the developed models generalized well on the independent test data sets. Anatomic patterns best differentiating the groups were consistent with the known distribution of neurofibrillary AD pathology. CONCLUSIONS: This paper presents preliminary evidence that application of SVM-based classification of an individual sMR scan relative to a library of scans can provide useful information in individual subjects for diagnosis of AD. Including demographic and genetic information in the classification algorithm slightly improves diagnostic accuracy.
OBJECTIVE: To develop and validate a tool for Alzheimer's disease (AD) diagnosis in individual subjects using support vector machine (SVM)-based classification of structural MR (sMR) images. BACKGROUND: Libraries of sMR scans of clinically well characterized subjects can be harnessed for the purpose of diagnosing new incoming subjects. METHODS: One hundred ninety patients with probable AD were age- and gender-matched with 190 cognitively normal (CN) subjects. Three different classification models were implemented: Model I uses tissue densities obtained from sMR scans to give STructural Abnormality iNDex (STAND)-score; and Models II and III use tissue densities as well as covariates (demographics and Apolipoprotein E genotype) to give adjusted-STAND (aSTAND)-score. Data from 140 AD and 140 CN were used for training. The SVM parameter optimization and training were done by four-fold cross validation (CV). The remaining independent sample of 50 AD and 50 CN was used to obtain a minimally biased estimate of the generalization error of the algorithm. RESULTS: The CV accuracy of Model II and Model III aSTAND-scores was 88.5% and 89.3%, respectively, and the developed models generalized well on the independent test data sets. Anatomic patterns best differentiating the groups were consistent with the known distribution of neurofibrillary AD pathology. CONCLUSIONS: This paper presents preliminary evidence that application of SVM-based classification of an individual sMR scan relative to a library of scans can provide useful information in individual subjects for diagnosis of AD. Including demographic and genetic information in the classification algorithm slightly improves diagnostic accuracy.
Authors: Charles D Smith; Himachandra Chebrolu; David R Wekstein; Frederick A Schmitt; William R Markesbery Journal: Neurobiol Aging Date: 2006-06-13 Impact factor: 4.673
Authors: D S Knopman; J E Parisi; A Salviati; M Floriach-Robert; B F Boeve; R J Ivnik; G E Smith; D W Dickson; K A Johnson; L E Petersen; W C McDonald; H Braak; R C Petersen Journal: J Neuropathol Exp Neurol Date: 2003-11 Impact factor: 3.685
Authors: Cristina Testa; Mikko P Laakso; Francesca Sabattoli; Roberta Rossi; Alberto Beltramello; Hilkka Soininen; Giovanni B Frisoni Journal: J Magn Reson Imaging Date: 2004-03 Impact factor: 4.813
Authors: Josephine Barnes; Rachael I Scahill; Richard G Boyes; Chris Frost; Emma B Lewis; Charlotte L Rossor; Martin N Rossor; Nick C Fox Journal: Neuroimage Date: 2004-10 Impact factor: 6.556
Authors: Prashanthi Vemuri; Gyorgy Simon; Kejal Kantarci; Jennifer L Whitwell; Matthew L Senjem; Scott A Przybelski; Jeffrey L Gunter; Keith A Josephs; David S Knopman; Bradley F Boeve; Tanis J Ferman; Dennis W Dickson; Joseph E Parisi; Ronald C Petersen; Clifford R Jack Journal: Neuroimage Date: 2010-12-31 Impact factor: 6.556
Authors: Kejal Kantarci; M L Senjem; V J Lowe; H J Wiste; S D Weigand; B J Kemp; A R Frank; M M Shiung; B F Boeve; D S Knopman; R C Petersen; C R Jack Journal: AJNR Am J Neuroradiol Date: 2010-03-18 Impact factor: 3.825
Authors: E Cavedo; S Lista; Z Khachaturian; P Aisen; P Amouyel; K Herholz; C R Jack; R Sperling; J Cummings; K Blennow; S O'Bryant; G B Frisoni; A Khachaturian; M Kivipelto; W Klunk; K Broich; S Andrieu; M Thiebaut de Schotten; J-F Mangin; A A Lammertsma; K Johnson; S Teipel; A Drzezga; A Bokde; O Colliot; H Bakardjian; H Zetterberg; B Dubois; B Vellas; L S Schneider; H Hampel Journal: J Prev Alzheimers Dis Date: 2014-12
Authors: Jonathan Graff-Radford; Timothy G Lesnick; Michelle M Mielke; Eleni Constantopoulos; Alejandro A Rabinstein; Scott A Przybelski; Prashanthi Vemuri; Hugo Botha; David T Jones; Vijay K Ramanan; Ronald C Petersen; David S Knopman; Bradley F Boeve; Melissa E Murray; Dennis W Dickson; Clifford R Jack; Kejal Kantarci; R Ross Reichard Journal: J Alzheimers Dis Date: 2021 Impact factor: 4.472