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.
No takes yet. Share an insight, caveat, or question.
Hosseini-Asl et al. (2016) studied this question.