Alzheimer's Disease Diagnostics by a Deeply Supervised Adaptable 3D Convolutional Network

Early diagnosis, playing an important role in preventing progress and the Alzheimer's disease (AD), is based on classification of features from brain images. The features have to accurately capture main-related variations of anatomical brain structures, such as, e. g. , ventricles, hippocampus shape, cortical thickness, and brain volume. This paper to predict the AD with a deep 3D convolutional neural network (3D-CNN), which can learn generic features capturing AD biomarkers and adapt to domain datasets. The 3D-CNN is built upon a 3D convolutional, which is pre-trained to capture anatomical shape variations in brain MRI scans. Fully connected upper layers of the 3D-CNN are then-tuned for each task-specific AD classification. Experiments on the MRI dataset with no skull-stripping preprocessing have shown our3D-CNN outperforms several conventional classifiers by accuracy and robustness. of the 3D-CNN to generalize the features learnt and adapt to other have been validated on the dataset.