Alexandre Savio

Computer Aided Diagnosis system for Alzheimer Disease using brain Diffusion Tensor Imaging features selected by Pearson's correlation

The aim of this paper is to obtain discriminant features from two scalar measures of Diffusion Tensor Imaging (DTI) data, Fractional Anisotropy (FA) and Mean Diffusivity (MD), and to train and test classifiers able to discriminate Alzheimers Disease (AD) patients from controls on the basis of features extracted from the FA or MD volumes. In this study, support vector machine (SVM) classifier was trained and tested on FA and MD data. Feature selection is done computing the Pearsons correlation between FA or MD values at voxel site across subjects and the indicative variable specifying the subject class. Voxel sites with high absolute correlation are selected for feature extraction. Results are obtained over an on-going study in Hospital de Santiago Apostol collecting anatomical T1-weighted MRI volumes and DTI data from healthy control subjects and AD patients. FA features and a linear SVM classifier achieve perfect accuracy, sensitivity and specificity in several cross-validation studies, supporting the usefulness of DTI-derived features as an image-marker for AD and to the feasibility of building Computer Aided Diagnosis systems for AD based on them.

Hybrid dendritic computing with kernel-LICA applied to Alzheimer's disease detection in MRI

Dendritic computing has been proved to produce perfect approximation of any data distribution. This result guarantees perfect accuracy training. However, we have found great performance degradation when tested on conventional k-fold cross-validation schemes. In this paper we propose to use Lattice Independent Component Analysis (LICA) and the Kernel transformation of the data as an appropriate feature extraction that improves the generalization of dendritic computing classifiers. We obtain a big increase in classification performance applying with this schema over a database of features extracted from Magnetic Resonance Imaging (MRI) including Alzheimers disease (AD) patients and control subjects.

Neurocognitive disorder detection based on feature vectors extracted from VBM analysis of structural MRI

Dementia is a growing concern due to the aging process of the western societies. Non-invasive detection is therefore a high priority research endeavor. In this paper we report results of classification systems applied to the feature vectors obtained by a feature extraction method computed on structural magnetic resonance imaging (sMRI) volumes for the detection of two neurological disorders with cognitive impairment: myotonic dystrophy of type 1 (MD1) and Alzheimer disease (AD). The feature extraction process is based on the voxel clusters detected by voxel-based morphometry (VBM) analysis of sMRI upon a set of patient and control subjects. This feature extraction process is specific for each kind of disease and is grounded on the findings obtained by medical experts. The 10-fold cross-validation results of several statistical and neural network based classification algorithms trained and tested on these features show high specificity and moderate sensitivity of the classifiers, suggesting that the approach is better suited for rejecting than for detecting early stages of the diseases.

Classification results of artificial neural networks for Alzheimer's disease detection

Detection of Alzheimers disease on brain Magnetic Resonance Imaging (MRI) is a highly sought goal in the Neurosciences. We used four different models of Artificial Neural Networks (ANN): Back-propagation (BP), Radial Basis Networks (RBF), Learning Vector Quantization Networks (LVQ) and Probabilistic Neural Networks (PNN) to perform classification of patients of mild Alzheimers disease vs. control subjects. Features are extracted from the brain volume data using Voxel-based Morphometry (VBM) detection clusters. The voxel location detection clusters given by the VBM were applied to select the voxel values upon which the classification features were computed. We have evaluated feature vectors computed from the GM segmentation volumes using the VBM clusters as voxel selection masks. The study has been performed on MRI volumes of 98 females, after careful demographic selection from the Open Access Series of Imaging Studies (OASIS) database, which is a large number of subjects compared to current reported studies.

Evolutionary ELM wrapper feature selection for Alzheimer's disease CAD on anatomical brain MRI

This paper proposes an evolutionary wrapper feature selection using Extreme Learning Machines (ELM) as the base classifier training algorithm, comprising a Genetic Algorithm (GA) exploring the space of feature combinations. GA fitness function is the mean accuracy of a cross-validation evaluation of each individual feature selection. The marginal distribution of the classification accuracy corresponding to a feature is used to measure feature saliency. The raw features are extracted as a voxel selection from anatomical brain magnetic resonance imaging (MRI). Voxel selection is provided by Voxel Based Morphometry (VBM) which finds statistically significant clusters of voxels that have differences across MRI volumes on a paired dataset of Alzheimers Disease (AD) and healthy controls.

Prognostic value of changes in resting-state functional connectivity patterns in cognitive recovery after stroke: A 3T fMRI pilot study

Resting‐state studies conducted with stroke patients are scarce. First objective was to explore whether patients with good cognitive recovery showed differences in resting‐state functional patterns of brain activity when compared to patients with poor cognitive recovery. Second objective was to determine whether such patterns were correlated with cognitive performance. Third objective was to assess the existence of prognostic factors for cognitive recovery. Eighteen right‐handed stroke patients and eighteen healthy controls were included in the study. Stroke patients were divided into two groups according to their cognitive improvement observed at three months after stroke. Probabilistic independent component analysis was used to identify resting‐state brain activity patterns. The analysis identified six networks: frontal, fronto‐temporal, default mode network, secondary visual, parietal, and basal ganglia. Stroke patients showed significant decrease in brain activity in parietal and basal ganglia networks and a widespread increase in brain activity in the remaining ones when compared with healthy controls. When analyzed separately, patients with poor cognitive recovery (n = 10) showed the same pattern as the whole stroke patient group, while patients with good cognitive recovery (n = 8) showed increased activity only in the default mode network and fronto‐temporal network, and decreased activity in the basal ganglia. We observe negative correlations between basal ganglia network activity and performance in Semantic Fluency test and Part A of the Trail Making Test for patients with poor cognitive recovery. A reverse pattern was observed between frontal network activity and the abovementioned tests for the same group. Hum Brain Mapp 35:3819–3831, 2014.

A lattice computing approach for on-line fMRI analysis

We introduce an approach to fMRI analysis based on the Endmember Induction Heuristic Algorithm (EIHA). This algorithm uses the Lattice Associative Memory (LAM) to detect Lattice Independent vectors, which can be assumed to be Affine Independent, and therefore candidates to be the endmembers of the data. Induced endmembers are used to compute the activation levels of voxels as result of an unmixing process. The endmembers correspond to diverse activation patterns, one of these activation patterns corresponds to the resting state of the neuronal tissue. The on-line working of the algorithm does not need neither a previous training process nor a priori models of the data. Results on a case study compare with the results given by the state of art SPM software.

Results of an Adaboost Approach on Alzheimer's Disease Detection on MRI

In this paper we explore the use of the Voxel-based Morphometry (VBM) detection clusters to guide the feature extraction processes for the detection of Alzheimers disease on brain Magnetic Resonance Imaging (MRI). The voxel location detection clusters given by the VBM were applied to select the voxel values upon which the classification features were computed. We have evaluated feature vectors computed over the data from the original MRI volumes and from the GM segmentation volumes, using the VBM clusters as voxel selection masks. We use the Support Vector Machine (SVM) algorithm to perform classification of patients with mild Alzheimers disease vs. control subjects. We have also considered combinations of isolated cluster based classifiers and an Adaboost strategy applied to the SVM built on the feature vectors. The study has been performed on MRI volumes of 98 females, after careful demographic selection from the Open Access Series of Imaging Studies (OASIS) database, which is a large number of subjects compared to current reported studies. Results are moderately encouraging, as we can obtain up to 85% accuracy with the Adaboost strategy in a 10-fold cross-validation.

Deformation based feature selection for Computer Aided Diagnosis of Alzheimer's Disease

Deformation-based Morphometry (DBM) allows detection of significant morphological differences of brain anatomy, such as those related to brain atrophy in Alzheimers Disease (AD). DBM process is as follows: First, performs the non-linear registration of a subjects structural MRI volume to a reference template. Second, computes scalar measures of the registrations deformation field. Third, performs across volume statistical group analysis of these scalar measures to detect effects. In this paper we use the scalar deformation measures for Computer Aided Diagnosis (CAD) systems for AD. Specifically this paper deals with feature extraction methods over five such scalar measures. We evaluate three supervised feature selection methods based on voxel site significance measures given by Pearson correlation, Bhattacharyya distance and Welchs t-test, respectively. The CAD system discriminating between healthy control subjects (HC) and AD patients consists of a Support Vector Machine (SVM) classifier trained on the DBM selected features. The paper reports experimental results on structural MRI data from the cross-sectional OASIS database. Average 10-fold cross-validation classification results are comparable or improve the state-of-the-art results of other approaches performing CAD from structural MRI data. Localization in the brain of the most discriminant deformation voxel sites is in agreement with findings reported in the literature.

A lattice computing approach to Alzheimer's disease computer assisted diagnosis based on MRI data

We present a Computer Assisted Diagnosis (CAD) system for Alzheimers disease (AD). The proposed CAD system employs MRI data features and applies a Lattice Computing (LC) scheme. To this end feature extraction methods are adopted from the literature, toward distinguishing healthy people from Alzheimer diseased ones. Computer assisted diagnosis is pursued by a k-NN classifier in the LC context by handling this task from two different perspectives. First, it performs dimensionality reduction over the high dimensional feature vectors and, second it classifies the subjects inside the lattice space by generating adaptively class boundaries. Computational experiments using a benchmark MRI dataset regarding AD patients demonstrate that the proposed classifier performs well comparatively to state-of-the-art classification models.