Kenichi Ota1, Naoya Oishi2, Kengo Ito3, Hidenao Fukuyama1. 1. Human Brain Research Center, Kyoto University Graduate School of Medicine, 54 Shogoin Kawahara-cho, Sakyo-ku, Kyoto 606-8507, Japan; Center for the Promotion of Interdisciplinary Education and Research, Kyoto University, 54 Shogoin Kawahara-cho, Sakyo-ku, Kyoto 606-8507, Japan. 2. Human Brain Research Center, Kyoto University Graduate School of Medicine, 54 Shogoin Kawahara-cho, Sakyo-ku, Kyoto 606-8507, Japan; Department of Psychiatry, Kyoto University Graduate School of Medicine, 54 Shogoin Kawahara-cho, Sakyo-ku, Kyoto 606-8507, Japan. Electronic address: noishi@kuhp.kyoto-u.ac.jp. 3. Department of Clinical and Experimental Neuroimaging, National Center for Geriatrics and Gerontology, 7-430 Morioka-cho, Obu-shi, Aichi 474-8511, Japan.
Abstract
BACKGROUND: The choice of biomarkers for early detection of Alzheimer's disease (AD) is important for improving the accuracy of imaging-based prediction of conversion from mild cognitive impairment (MCI) to AD. The primary goal of this study was to assess the effects of imaging modalities and brain atlases on prediction. We also investigated the influence of support vector machine recursive feature elimination (SVM-RFE) on predictive performance. METHODS: Eighty individuals with amnestic MCI [40 developed AD within 3 years] underwent structural magnetic resonance imaging (MRI) and (18)F-fluorodeoxyglucose positron emission tomography (FDG-PET) scans at baseline. Using Automated Anatomical Labeling (AAL) and LONI Probabilistic Brain Atlas (LPBA40), we extracted features representing gray matter density and relative cerebral metabolic rate for glucose in each region of interest from the baseline MRI and FDG-PET data, respectively. We used linear SVM ensemble with bagging and computed the area under the receiver operating characteristic curve (AUC) as a measure of classification performance. We performed multiple SVM-RFE to compute feature ranking. We performed analysis of variance on the mean AUCs for eight feature sets. RESULTS: The interactions between atlas and modality choices were significant. The main effect of SVM-RFE was significant, but the interactions with the other factors were not significant. COMPARISON WITH EXISTING METHOD: Multimodal features were found to be better than unimodal features to predict AD. FDG-PET was found to be better than MRI. CONCLUSIONS: Imaging modalities and brain atlases interact with each other and affect prediction. SVM-RFE can improve the predictive accuracy when using atlas-based features.
BACKGROUND: The choice of biomarkers for early detection of Alzheimer's disease (AD) is important for improving the accuracy of imaging-based prediction of conversion from mild cognitive impairment (MCI) to AD. The primary goal of this study was to assess the effects of imaging modalities and brain atlases on prediction. We also investigated the influence of support vector machine recursive feature elimination (SVM-RFE) on predictive performance. METHODS: Eighty individuals with amnestic MCI [40 developed AD within 3 years] underwent structural magnetic resonance imaging (MRI) and (18)F-fluorodeoxyglucose positron emission tomography (FDG-PET) scans at baseline. Using Automated Anatomical Labeling (AAL) and LONI Probabilistic Brain Atlas (LPBA40), we extracted features representing gray matter density and relative cerebral metabolic rate for glucose in each region of interest from the baseline MRI and FDG-PET data, respectively. We used linear SVM ensemble with bagging and computed the area under the receiver operating characteristic curve (AUC) as a measure of classification performance. We performed multiple SVM-RFE to compute feature ranking. We performed analysis of variance on the mean AUCs for eight feature sets. RESULTS: The interactions between atlas and modality choices were significant. The main effect of SVM-RFE was significant, but the interactions with the other factors were not significant. COMPARISON WITH EXISTING METHOD: Multimodal features were found to be better than unimodal features to predict AD. FDG-PET was found to be better than MRI. CONCLUSIONS: Imaging modalities and brain atlases interact with each other and affect prediction. SVM-RFE can improve the predictive accuracy when using atlas-based features.
Authors: Jacob W Vogel; Niklas Mattsson; Yasser Iturria-Medina; Olof T Strandberg; Michael Schöll; Christian Dansereau; Sylvia Villeneuve; Wiesje M van der Flier; Philip Scheltens; Pierre Bellec; Alan C Evans; Oskar Hansson; Rik Ossenkoppele Journal: Hum Brain Mapp Date: 2018-10-19 Impact factor: 5.038
Authors: Alex F Mendelson; Maria A Zuluaga; Marco Lorenzi; Brian F Hutton; Sébastien Ourselin Journal: Neuroimage Clin Date: 2016-12-24 Impact factor: 4.881