Kernel Fisher discriminant for shape-based classification in epilepsy

Supervised filters for EEG signal in naturally occurring epilepsy forecasting

Nearly 1% of the global population has Epilepsy. Forecasting epileptic seizures with an acceptable confidence level, could improve the disease treatment and thus the lifestyle of the people who suffer it. To do that the electroencephalogram (EEG) signal is usually studied through spectral power band filtering, but this paper proposes an alternative novel method of preprocessing the EEG signal based on supervised filters. Such filters have been employed in a machine learning algorithm, such as the K-Nearest Neighbor (KNN), to improve the prediction of seizures. The proposed solution extends with this novel approach an algorithm that was submitted to win the third prize of an international Data Science challenge promoted by Kaggle contest platform and the American Epilepsy Society, the Epilepsy Foundation, National Institutes of Health (NIH) and Mayo Clinic. A formal description of these preprocessing methods is presented and a detailed analysis in terms of Receiver Operating Characteristics (ROC) curve and Area Under ROC curve is performed. The obtained results show statistical significant improvements when compared with the spectral power band filtering (PBF) typical baseline. A trend between performance and the dataset size is observed, suggesting that the supervised filters bring better information, compared to the conventional PBF filters, as the dataset grows in terms of monitored variables (sensors) and time length. The paper demonstrates a better accuracy in forecasting when new filters are employed and its main contribution is in the field of machine learning algorithms to develop more accurate predictive systems.

Detection of Alzheimer's Disease by Three-Dimensional Displacement Field Estimation in Structural Magnetic Resonance Imaging

BACKGROUND

Within the past decade, computer scientists have developed many methods using computer vision and machine learning techniques to detect Alzheimer's disease (AD) in its early stages.

OBJECTIVE

However, some of these methods are unable to achieve excellent detection accuracy, and several other methods are unable to locate AD-related regions. Hence, our goal was to develop a novel AD brain detection method.

METHODS

In this study, our method was based on the three-dimensional (3D) displacement-field (DF) estimation between subjects in the healthy elder control group and AD group. The 3D-DF was treated with AD-related features. The three feature selection measures were used in the Bhattacharyya distance, Student's t-test, and Welch's t-test (WTT). Two non-parallel support vector machines, i.e., generalized eigenvalue proximal support vector machine and twin support vector machine (TSVM), were then used for classification. A 50 × 10-fold cross validation was implemented for statistical analysis.

RESULTS

The results showed that "3D-DF+WTT+TSVM" achieved the best performance, with an accuracy of 93.05 ± 2.18, a sensitivity of 92.57 ± 3.80, a specificity of 93.18 ± 3.35, and a precision of 79.51 ± 2.86. This method also exceled in 13 state-of-the-art approaches. Additionally, we were able to detect 17 regions related to AD by using the pure computer-vision technique. These regions include sub-gyral, inferior parietal lobule, precuneus, angular gyrus, lingual gyrus, supramarginal gyrus, postcentral gyrus, third ventricle, superior parietal lobule, thalamus, middle temporal gyrus, precentral gyrus, superior temporal gyrus, superior occipital gyrus, cingulate gyrus, culmen, and insula. These regions were reported in recent publications.

CONCLUSIONS

The 3D-DF is effective in AD subject and related region detection.

Detection of Alzheimer's disease by displacement field and machine learning

Aim. Alzheimer's disease (AD) is a chronic neurodegenerative disease. Recently, computer scientists have developed various methods for early detection based on computer vision and machine learning techniques. Method. In this study, we proposed a novel AD detection method by displacement field (DF) estimation between a normal brain and an AD brain. The DF was treated as the AD-related features, reduced by principal component analysis (PCA), and finally fed into three classifiers: support vector machine (SVM), generalized eigenvalue proximal SVM (GEPSVM), and twin SVM (TSVM). The 10-fold cross validation repeated 50 times. Results. The results showed the "DF + PCA + TSVM" achieved the accuracy of 92.75 ± 1.77, sensitivity of 90.56 ± 1.15, specificity of 93.37 ± 2.05, and precision of 79.61 ± 2.21. This result is better than or comparable with not only the other proposed two methods, but also ten state-of-the-art methods. Besides, our method discovers the AD is related to following brain regions disclosed in recent publications: Angular Gyrus, Anterior Cingulate, Cingulate Gyrus, Culmen, Cuneus, Fusiform Gyrus, Inferior Frontal Gyrus, Inferior Occipital Gyrus, Inferior Parietal Lobule, Inferior Semi-Lunar Lobule, Inferior Temporal Gyrus, Insula, Lateral Ventricle, Lingual Gyrus, Medial Frontal Gyrus, Middle Frontal Gyrus, Middle Occipital Gyrus, Middle Temporal Gyrus, Paracentral Lobule, Parahippocampal Gyrus, Postcentral Gyrus, Posterior Cingulate, Precentral Gyrus, Precuneus, Sub-Gyral, Superior Parietal Lobule, Superior Temporal Gyrus, Supramarginal Gyrus, and Uncus. Conclusion. The displacement filed is effective in detection of AD and related brain-regions.

Evidence-based review on epilepsy and driving

OBJECTIVE

The aim of this study was to synopsize the evidence on predictors of crashes and driving status in people with epilepsy (PWE).

METHODS

Evidence-based review of the published English literature was the method used. We searched various databases and extracted data from 16 (of 77) primary studies. On the basis of American Academy of Neurology criteria, we assigned each study a class of evidence (I-IV, where I indicates the highest level of evidence) and made recommendations (Level A: predictive or not; Level B: probably predictive or not; Level C: possibly predictive or not; Level U: no recommendations).

RESULTS

For PWE, the following characteristics are considered useful: For identifying crash risk, epilepsy (level B) and short seizure-free intervals (≥3 months) (Level C) are not predictive of motor vehicle crash (MVC). For self/proxy-reported crash risk, epilepsy surgery (Level B), seizure-free intervals (6-12 months) (Level B), few prior non-seizure-related crashes (Level B), and regular antiepileptic drug adjustments (Level B) are protective against crashes; seizures contribute to MVCs (Level C); mandatory reporting does not contribute to reduced crashes (Level C). No recommendations for reliable auras, age, and gender (Level U), as data are inadequate to make determinations. For self-reported driving or licensure status, employment and epilepsy surgery are predictive of driving (Level C); there are no recommendations for antiepileptic drug use, self-reported driving, gender, age, receiving employment benefits, or having reduced seizure frequency (Level U).

CONCLUSION

Limitations, that is, heterogeneity among studies, examining the English literature from 1994 to 2010, must be considered. Yet, this is the first evidence-based review to synopsize the current PWE and driving literature and to provide recommendation(s) to clinicians and policy makers. Class I studies, matched for age and gender, yielding Level A recommendations are urgently needed to define the risks, benefits, and causal factors underlying driving performance issues in PWE.

RBOOST: RIEMANNIAN DISTANCE BASED REGULARIZED BOOSTING

Boosting is a versatile machine learning technique that has numerous applications including but not limited to image processing, computer vision, data mining etc. It is based on the premise that the classification performance of a set of weak learners can be boosted by some weighted combination of them. There have been a number of boosting methods proposed in the literature, such as the AdaBoost, LPBoost, SoftBoost and their variations. However, the learning update strategies used in these methods usually lead to overfitting and instabilities in the classification accuracy. Improved boosting methods via regularization can overcome such difficulties. In this paper, we propose a Riemannian distance regularized LPBoost, dubbed RBoost. RBoost uses Riemannian distance between two square-root densities (in closed form) - used to represent the distribution over the training data and the classification error respectively - to regularize the error distribution in an iterative update formula. Since this distance is in closed form, RBoost requires much less computational cost compared to other regularized Boosting algorithms. We present several experimental results depicting the performance of our algorithm in comparison to recently published methods, LP-Boost and CAVIAR, on a variety of datasets including the publicly available OASIS database, a home grown Epilepsy database and the well known UCI repository. Results depict that the RBoost algorithm performs better than the competing methods in terms of accuracy and efficiency.

Identifying anatomical shape difference by regularized discriminative direction

Identifying the shape difference between two groups of anatomical objects is important for medical image analysis and computer-aided diagnosis. A method called "discriminative direction" in the literature has been proposed to solve this problem. In that method, the shape difference between groups is identified by deforming a shape along the discriminative direction. This paper conducts a thorough study about inferring this discriminative direction in an efficient and accurate way. First, finding the discriminative direction is reformulated as a preimage problem in kernel-based learning. This provides a complementary but conceptually simpler solution than the previous method. More importantly, we find that a shape deforming along the original discriminative direction cannot faithfully maintain its anatomical correctness. This unnecessarily introduces spurious shape differences and leads to inaccurate analysis. To overcome this problem, this paper further proposes a regularized discriminative direction by requiring a shape to conform to its underlying distribution when it deforms. Two different approaches are developed to impose the regularization, one from the perspective of probability distributions and the other from a geometric point of view, and their relationship is discussed. After verifying their superior performance through controlled experiments, we apply the proposed methods to detecting and localizing the hippocampal shape difference between sexes. We get results consistent with other independent research, providing a more compact representation of the shape difference compared with the established discriminative direction method.

Shape analysis using a point-based statistical shape model built on correspondence probabilities

A fundamental problem when computing statistical shape models is the determination of correspondences between the instances of the associated data set. Often, homologies between points that represent the surfaces are assumed which might lead to imprecise mean shape and variability results. We propose an approach where exact correspondences are replaced by evolving correspondence probabilities. These are the basis for a novel algorithm that computes a generative statistical shape model. We developed an unified MAP framework to compute the model parameters ('mean shape' and 'modes of variation') and the nuisance parameters which leads to an optimal adaption of the model to the set of observations. The registration of the model on the instances is solved using the Expectation Maximization--Iterative Closest Point algorithm which is based on probabilistic correspondences and proved to be robust and fast. The alternated optimization of the MAP explanation with respect to the observation and the generative model parameters leads to very efficient and closed-form solutions for (almost) all parameters. Experimental results on brain structure data sets demonstrate the efficiency and well-posedness of the approach. The algorithm is then extended to an automatic classification method using the k-means clustering and applied to synthetic data as well as brain structure classification problems.

Large Margin Pursuit for a Conic Section Classifier

Learning a discriminant becomes substantially more difficult when the datasets are high-dimensional and the available samples are few. This is often the case in computer vision and medical diagnosis applications. A novel Conic Section classifier (CSC) was recently introduced in the literature to handle such datasets, wherein each class was represented by a conic section parameterized by its focus, directrix and eccentricity. The discriminant boundary was the locus of all points that are equi-eccentric relative to each class-representative conic section. Simpler boundaries were preferred for the sake of generalizability.In this paper, we improve the performance of the two-class classifier via a large margin pursuit. When formulated as a non-linear optimization problem, the margin computation is demonstrated to be hard, especially due to the high dimensionality of the data. Instead, we present a geometric algorithm to compute the distance of a point to the nonlinear discriminant boundary generated by the CSC in the input space. We then introduce a large margin pursuit in the learning phase so as to enhance the generalization capacity of the classifier. We validate the algorithm on real datasets and show favorable classification rates in comparison to many existing state-of-the-art binary classifiers as well as the CSC without margin pursuit.