2 results
Search Results
Now showing 1 - 2 of 2
Item Metadata only An evaluation of physical performance of conventional x-ray machine using computed radiography system(Mahidol University. Mahidol University Library and Knowledge Center, 2008) Tipvimol MeechaiItem Metadata only Computer-aided classification of alzheimer's disease based on support vector machine with combination of cerebral image features in MRI(Mahidol University. Mahidol University Library and Knowledge Center, 2016) Chonnikan Jongkreangkrai; Yudthaphon Vichianin; Chiraporn Tocharoenchai; Kakanand SrungboonmeeSeveral studies have differentiated Alzheimer's disease (AD) using cerebral image features derived from magnetic resonance (MR) brain images, such as the volume and shape of hippocampus and cerebral cortical thicknesses. In this study, we were interested in combining cerebral image features, including hippocampus and amygdala volumes, and entorhinal cortex thickness to improve the performance of the AD differentiation. Thus, the aim of this study was to investigate the useful cerebral image features obtained from MRI for computer-aided classification of AD patients using a support vector machine (SVM). T1-weighted MR brain images of 100 AD patients and those of 100 normal subjects obtained from Alzheimer's Disease Neuroimaging Initiative were studied. FreeSurfer (software for analysis of brain imaging data) was used to measure hippocampus and amygdala volumes, and entorhinal cortex thicknesses in left and right brain hemispheres. Relative volumes of hippocampus and amygdala were then calculated using total intracranial volume (TIV) to correct the variation in individual head size. SVM was employed for classification of AD patients using five different combinations of cerebral image features (H: left and right hippocampus relative volumes, A: left and right amygdala relative volumes, E: left and right entorhinal cortex thicknesses, HA: left and right hippocampus and amygdala relative volumes, and ALL: all features). Receiver operating characteristic (ROC) analysis and area under the curve (AUC) were used to evaluate the method. AUC values of 5 cerebral feature combinations were 0.8575 (H), 0.8374 (A), 0.8422 (E), 0.8631 (HA), and 0.8906 (ALL), respectively. Although using all features (ALL) provided the highest AUC, there were no statistically significant differences among them except for the A feature. Our results showed that all combinations of cerebral image features derived from T1- weighted MR brain images may be feasible for computer-aided classification of AD patients by using SVM.