Alzheimer's disease diagnostics by adaptation of 3D convolutional network

Abstract

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

A longitudinal magnetic resonance imaging study of neurodegenerative and small vessel disease, and clinical cognitive trajectories in non demented patients with transient ischemic attack: the PREVENT study

“…The basic idea of this is to predict occurrence of cognitive decline using prediction models developed and trained on the longitudinal data with known clinical outcome (cognitive decline yes / no), which can then be used to predict cognitive impairment in new patients based on the same features used for training of the high-level machine learning model. More precisely, we will develop prediction models based on random forest [29], support vector machines [30], deep neural networks [31], and quadratic inference function classifiers for predicting the occurrence of dementia using available baseline information such as cognitive test results, blood and CSF parameters, as well as quantitative image-based biomarkers such as regional QSM values, volumetric brain and hippocampal values, and white matter lesion (WML) load. The evaluation of the prediction models based on the TIA and control cohorts will be conducted using well-established cross validation techniques.…”

A survey on deep learning in medical image analysis

“…Three papers used an architecture leveraging the unique attributes of medical data: two use 3D convolutions (Hosseini-Asl et al, 2016;Payan and Montana, 2015) instead of 2D to classify patients as having Alzheimer; Kawahara et al (2016b) applied a CNNlike architecture to a brain connectivity graph derived from MRI diffusion-tensor imaging (DTI). In order to do this, they developed several new layers which formed the basis of their network, so-called edge-to-edge, edgeto-node, and node-to-graph layers.…”

Deep Learning for Medical Image Analysis: Applications to Computed Tomography and Magnetic Resonance Imaging

“…The goal in medicine is to utilize the medical images and reports as inputs and outputs of the deep learning model, respectively, to automatically learn important features and biomarkers. For example, a 3D CNN model to determine the degree of Alzheimer's disease progression from structural brain MR images has been proposed [8]. In the study, they used a transfer learning method where features learned through pre-training a CAE with a small number of source domain images were used to fine tune the target domain data, which was then used to train the actual classification model.…”