Ensembles of Patch-Based Classifiers for Diagnosis of Alzheimer Diseases

Abstract

There is ongoing research for the automatic diagnosis of Alzheimer's disease (AD) based on traditional machine learning techniques, and deep learning-based approaches are becoming a popular choice for AD diagnosis. The state-of-the-art techniques that consider multimodal diagnosis have been shown to have accuracy better than a manual diagnosis. However, collecting data from different modalities is time-consuming and expensive, and some modalities may have radioactive side effects. Our study is confined to structural magnetic resonance imaging (sMRI). The objectives of our attempt are as follows: 1) to increase the accuracy level that is comparable to the state-of-the-art methods; 2) to overcome the overfitting problem, and; 3) to analyze proven landmarks of the brain that provide discernible features for AD diagnosis. Here, we focused specifically on both the left and right hippocampus areas. To achieve the objectives, at first, we incorporate ensembles of simple convolutional neural networks (CNNs) as feature extractors and softmax cross-entropy as the classifier. Then, considering the scarcity of data, we deployed a patch-based approach. We have performed our experiment on the Gwangju Alzheimer's and Related Dementia (GARD) cohort dataset prepared by the National Research Center for Dementia (GARD), Gwangju, South Korea. We manually localized the left and right hippocampus and fed three view patches (TVPs) to the CNN after the preprocessing steps. We achieve 90.05% accuracy. We have compared our model with the state-of-the-art methods on the same dataset they have used and found our result comparable. INDEX TERMS Alzheimer disease classification, ALZHEIMER disease detection, Alzheimer disease diagnosis, convolutional neural network, deep learning, machine learning, medical imaging.

A Deep Siamese Convolution Neural Network for Multi-Class Classification of Alzheimer Disease

“…In the second step, feature vectors were used for processing the feature and placed into the classifier to check the effectiveness. Ahmed et al [30] designed a simpler CNN model using the patch-based classifier to diagnosis the AD multi-stages. The model reduced the computational cost and produced a great improvement in accuracy.…”

Ensemble of ROI-based convolutional neural network classifiers for staging the Alzheimer disease spectrum from magnetic resonance imaging

“…In addition to clinical evaluation and psychological tests, artificial intelligence (AI)-based computer-aided diagnosis (CAD) methods for staging AD from structured magnetic resonance imaging (sMRI) have been developed [4][5][6][7][8][9][10][11][12][13][14][15][16][17]. Conventional AI techniques require domain expertise and careful engineering for feature extraction [18].…”

Anatomical Landmarks and DAG Network Learning for Alzheimer’s Disease Diagnosis

“…Table Ⅳ shows the performance comparison of the proposed method with the state-of-the-art methods. It can be seen that the proposed method achieves better diagnosis results compared with the three kinds of methods including ROI+CNN model [25], ensemble classifier [38], [39], and end-to-end hierarchical convolution network learning based on whole brain image patches [18]. In addition, larger datasets are applied in the proposed method which improves the generalization and effectiveness of the classification model.…”

“…For example, the discriminating anatomical landmarks are identified as image features by utilizing the morphological characteristics of voxels [33]- [36]. A deep learning framework ensemble based on landmarks is proposed for disease diagnosis [37]- [39]. Besides, a local patch-based weak classifier ensemble method is reported which combines multiple individual classifiers based on different subsets of local patches [40].…”