Effective diagnosis of Alzheimer’s disease by means of large margin-based methodology

Abstract

BackgroundFunctional brain images such as Single-Photon Emission Computed Tomography (SPECT) and Positron Emission Tomography (PET) have been widely used to guide the clinicians in the Alzheimer’s Disease (AD) diagnosis. However, the subjectivity involved in their evaluation has favoured the development of Computer Aided Diagnosis (CAD) Systems.MethodsIt is proposed a novel combination of feature extraction techniques to improve the diagnosis of AD. Firstly, Regions of Interest (ROIs) are selected by means of a t-test carried out on 3D Normalised Mean Square Error (NMSE) features restricted to be located within a predefined brain activation mask. In order to address the small sample-size problem, the dimension of the feature space was further reduced by: Large Margin Nearest Neighbours using a rectangular matrix (LMNN-RECT), Principal Component Analysis (PCA) or Partial Least Squares (PLS) (the two latter also analysed with a LMNN transformation). Regarding the classifiers, kernel Support Vector Machines (SVMs) and LMNN using Euclidean, Mahalanobis and Energy-based metrics were compared.ResultsSeveral experiments were conducted in order to evaluate the proposed LMNN-based feature extraction algorithms and its benefits as: i) linear transformation of the PLS or PCA reduced data, ii) feature reduction technique, and iii) classifier (with Euclidean, Mahalanobis or Energy-based methodology). The system was evaluated by means of k-fold cross-validation yielding accuracy, sensitivity and specificity values of 92.78%, 91.07% and 95.12% (for SPECT) and 90.67%, 88% and 93.33% (for PET), respectively, when a NMSE-PLS-LMNN feature extraction method was used in combination with a SVM classifier, thus outperforming recently reported baseline methods.ConclusionsAll the proposed methods turned out to be a valid solution for the presented problem. One of the advances is the robustness of the LMNN algorithm that not only provides higher separation rate between the classes but it also makes (in combination with NMSE and PLS) this rate variation more stable. In addition, their generalization ability is another advance since several experiments were performed on two image modalities (SPECT and PET).

Alzheimer’s Disease Computer-Aided Diagnosis: Histogram-Based Analysis of Regional MRI Volumes for Feature Selection and Classification

“…In contrast to univariate analysis, these can effectively handle information that simultaneously affects the whole brain as well as characterizing the relationship between different ROIs. Brain networks [36,37], texture features [20,[38][39][40][41] and other voxel and region-wise higher-level features [42][43][44][45][46] could therefore reveal other information than only volumetric, complementing and providing new insights into the disease. In [47] a new framework called spherical brain mapping (SBM) was proposed.…”

“…This goal is achieved by the computation of the feature maps and the direct use of the intensity distribution along the path, as a characterization of the structural differences in normal or AD-affected subjects. Since the gray level co-occurrence matrix (GLCM), firstly developed by Haralick [50], has been used in brain characterization in [41,45], an extension of this strategy is proposed to characterize the brain texture along each path and its neighborhood. Finally, in [52] deep learning is employed in order to extract representative features from each brain area defined by the AAL atlas in an unsupervised manner.…”

Neural networks with dimensionality reduction for predicting temperature change due to plastic deformation in a cold rolling simulation

“…2.Variance versus principal components. Cumulative variance line and contributed variance by each subsequent principal component as bars (Chaves et al , 2012). …”

A Comparative Survey of Feature Extraction and Classification Techniques for Early Diagnosis of Alzhimer’s Disease

“…In 2012 Rosa chaves et al [29] have investigated the performance of kernel distance metric learning approaches for AD diagnosis. In this approach, t-test is applied on the brain image to select the ROI.…”