Predicting Alzheimer's disease: a neuroimaging study with 3D convolutional neural networks
This work addresses Alzheimer's disease prediction for medical diagnosis, but it is incremental as it applies existing deep learning methods to a known neuroimaging problem.
The authors tackled Alzheimer's disease diagnosis by developing a deep learning algorithm using 3D convolutional neural networks on MRI scans, achieving state-of-the-art results on the ADNI dataset with 2,265 scans.
Pattern recognition methods using neuroimaging data for the diagnosis of Alzheimer's disease have been the subject of extensive research in recent years. In this paper, we use deep learning methods, and in particular sparse autoencoders and 3D convolutional neural networks, to build an algorithm that can predict the disease status of a patient, based on an MRI scan of the brain. We report on experiments using the ADNI data set involving 2,265 historical scans. We demonstrate that 3D convolutional neural networks outperform several other classifiers reported in the literature and produce state-of-art results.