Support vector machine-based classification of neuroimages in Alzheimer's disease: direct comparison of FDG-PET, rCBF-SPECT and MRI data acquired from the same individuals

• Published in: Revista brasileira de psiquiatria Vol. 40; no. 2; pp. 181 - 191
• Main Authors: Ferreira, Luiz K, Rondina, Jane M, Kubo, Rodrigo, Ono, Carla R, Leite, Claudia C, Smid, Jerusa, Bottino, Cassio, Nitrini, Ricardo, Busatto, Geraldo F, Duran, Fabio L, Buchpiguel, Carlos A
• Format: Journal Article
• Language: English; Portuguese
• Published: Brazil Associação Brasileira de Psiquiatria 01.04.2018; Associação Brasileira de Psiquiatria (ABP)
• Subjects: Aged; Alzheimer Disease - diagnostic imaging; Alzheimer’s disease; Brain Mapping; Case-Control Studies; Educational Status; FDG-PET; Female; Fluorodeoxyglucose F18; Humans; Magnetic Resonance Imaging - methods; Male; MRI; Original; Positron-Emission Tomography - methods; Predictive Value of Tests; PSYCHIATRY; Sensitivity and Specificity; SPECT; Support Vector Machine; Tomography, Emission-Computed, Single-Photon - methods; FDG-PET; support vector machine; Alzheimer’s disease; MRI; SPECT
• ISSN: 1516-4446; 1809-452X; 1809-452X
• DOI: 10.1590/1516-4446-2016-2083

To conduct the first support vector machine (SVM)-based study comparing the diagnostic accuracy of T1-weighted magnetic resonance imaging (T1-MRI), F-fluorodeoxyglucose-positron emission tomography (FDG-PET) and regional cerebral blood flow single-photon emission computed tomography (rCBF-SPECT) in Alzheimer's disease (AD). Brain T1-MRI, FDG-PET and rCBF-SPECT scans were acquired from a sample of mild AD patients (n=20) and healthy elderly controls (n=18). SVM-based diagnostic accuracy indices were calculated using whole-brain information and leave-one-out cross-validation. The accuracy obtained using PET and SPECT data were similar. PET accuracy was 68∼71% and area under curve (AUC) 0.77∼0.81; SPECT accuracy was 68∼74% and AUC 0.75∼0.79, and both had better performance than analysis with T1-MRI data (accuracy of 58%, AUC 0.67). The addition of PET or SPECT to MRI produced higher accuracy indices (68∼74%; AUC: 0.74∼0.82) than T1-MRI alone, but these were not clearly superior to the isolated neurofunctional modalities. In line with previous evidence, FDG-PET and rCBF-SPECT more accurately identified patients with AD than T1-MRI, and the addition of either PET or SPECT to T1-MRI data yielded increased accuracy. The comparable SPECT and PET performances, directly demonstrated for the first time in the present study, support the view that rCBF-SPECT still has a role to play in AD diagnosis.