Classification of Alzheimer's Disease using fMRI Data and Deep Learning Convolutional Neural Networks

Abstract

Recently, machine learning techniques especially predictive modeling and pattern recognition in biomedical sciences from drug delivery system to medical imaging has become one of the important methods which are assisting researchers to have deeper understanding of entire issue and to solve complex medical problems. Deep learning is a powerful machine learning algorithm in classification while extracting low to high-level features. In this paper, we used convolutional neural network to classify Alzheimer's brain from normal healthy brain. The importance of classifying this kind of medical data is to potentially develop a predict model or system in order to recognize the type disease from normal subjects or to estimate the stage of the disease. Classification of clinical data such as Alzheimer's disease has been always challenging and most problematic part has been always selecting the most discriminative features. Using Convolutional Neural Network (CNN) and the famous architecture LeNet-5, we successfully classified structural MRI data of Alzheimer's subjects from normal controls where the accuracy of test data on trained data reached 98.84%. This experiment suggests us the shift and scale invariant features extracted by CNN followed by deep learning classification is most powerful method to distinguish clinical data from healthy data in fMRI. This approach also enables us to expand our methodology to predict more complicated systems.

Neuroimaging modality fusion in Alzheimer’s classification using convolutional neural networks

“…These models are well suited to tasks with 2D or 3D data due to the shared filter weights within each convolutional layer. A CNN was proposed in [14] that takes fMRI slices as input to a modified LeNet-5 CNN architecture [15]. The DeepAD paper [16] further developed this notion by utilizing the more complex GoogleNet CNN [17].…”

Diagnosis of Alzheimer’s Disease via Multi-Modality 3D Convolutional Neural Network

“…Take CNN-based AD diagnosis as an instance, different people used different architectures. Hosseini-Asl et al built a 3D-CNN based on a 3D convolutional auto-encoder, which takes fMRI images as input and gives prediction of AD/MCI/NL [22], while Sarraf et al used a LeNet-5-like CNN to classify AD from NL based on fMRI [23]. Multi-modality classification was also implemented in CNN.…”

Analyzing Neuroimaging Data Through Recurrent Deep Learning Models

“…While researchers have started exploring the application of DL models to neuroimaging data (e.g., [Plis et al, 2014, Mensch et al, 2018, Sarraf and Tofighi, 2016, Nie et al, 2016, Suk et al, 2014, Petrov et al, 2018, Yousefnezhad and Zhang, 2018), two major challenges have so far prevented broad DL usage: (1) Neuroimaging data are high dimensional, while containing comparably few samples. For example, a typical fMRI dataset comprises up to a few hundred samples per subject and recently up to several hundred subjects [Van Essen et al, 2013], while each sample contains several hundred thousand dimensions (i.e., voxels).…”