GridMRISeg is based on AdaBoost. AdaBoost is a machine learning method that learns features to guide hippocampal segmentation. AdaBoost classifies voxels as belonging to the hippocampus based on thousands of features (e.g: image intensity, position, image curvatures, image gradients, tissue classification maps of gray/white matter and CSF, mean, standard deviation, etc..), which are learned from a training set of manually delineated T13D structural images. AdaBoost selects the classification features automatically. Moreover, AdaBoost sequentially selects the "weak classifiers" from the candidate pool and weights each of them based on their error. Each iteration of AdaBoost assigns an "importance weight" to each example; examples with a higher weight, classified incorrectly on previous iterations, will receive more attention on subsequent iterations, tuning the weak learners to the difficult examples. AdaBoost is available for online usage, through the "LONI pipeline environment", with the training and testing processing steps already set up for the ADNI datasets. The automated hippocampal segmentation portion usually takes less than 200 minutes while the whole workflow, plus the trainging phase, takes about 24 hour depending on the number of samples to be segmented. The user guide for Physician profile is available here. The user guide for Scientist profile is available here.