Comparison of AdaBoost and Support Vector Machines for Detecting Alzheimer's Disease Through Automated Hippocampal Segmentation

Abstract

We compared four automated methods for hippocampal segmentation using different machine learning algorithms (1) hierarchical AdaBoost, (2) Support Vector Machines (SVM) with manual feature selection, (3) hierarchical SVM with automated feature selection (Ada-SVM), and (4) a publicly available brain segmentation package (FreeSurfer). We trained our approaches using T1-weighted brain MRI’s from 30 subjects (10 normal elderly, 10 mild cognitive impairment (MCI), and 10 Alzheimer’s disease (AD)), and tested on an independent set of 40 subjects (20 normal, 20 AD). Manually segmented gold standard hippocampal tracings were available for all subjects (training and testing). We assessed each approach’s accuracy relative to manual segmentations, and its power to map AD effects. We then converted the segmentations into parametric surfaces to map disease effects on anatomy. After surface reconstruction, we computed significance maps, and overall corrected p-values, for the 3D profile of shape differences between AD and normal subjects. Our AdaBoost and Ada-SVM segmentations compared favorably with the manual segmentations and detected disease effects as well as FreeSurfer on the data tested. Cumulative p-value plots, in conjunction with the False Discovery Rate method, were used to examine the power of each method to detect correlations with diagnosis and cognitive scores. We also evaluated how segmentation accuracy depended on the size of the training set, providing practical information for future users of this technique.

Simultaneous segmentation and grading of anatomical structures for patient's classification: Application to Alzheimer's disease

“…Among these methods, several have been used to classify AD patients using HC volume (Chupin et al, 2009a;Colliot et al, 2008;Morra et al, 2010;Mueller et al, 2010). Despite the high segmentation accuracy of the new HC segmentation approaches, using the HC volume enables a separation between AD and cognitively normal (CN) subjects with a success rate only around 72-74% over the entire Alzheimer's Disease Neuroimaging Initiative (ADNI) database (Cuingnet et al, 2010).…”

Classifier Ensemble Recommendation

“…Recommendation boosting+ uses the same underlying mechanism as recommendation boosting, but afterwards combines its selection with the top-k selection to add more variation to the selected set. Note that we use the boosting methods as feature selection mechanisms and discard the final weights of the selected classifiers in favor of simply training an SVM on the selection; this use of AdaBoost is common in vision [12,13] and occasionally sees use in other domains [14,15].…”

A Collaborative Biomedical Image-Mining Framework along with Image Annotation

“…Boosting algorithms [29] are a set of nonparametric metalearning algorithms, provide optimal classification results. The advantages of using adaptive boosting (AdaBoost) algorithm over other machine learning algorithm are its computational efficiency, better robustness and no regressions.…”