1
|
Shishegar R, Gandomkar Z, Fallahi A, Nazem-Zadeh MR, Soltanian-Zadeh H. Global and local shape features of the hippocampus based on Laplace–Beltrami eigenvalues and eigenfunctions: a potential application in the lateralization of temporal lobe epilepsy. Neurol Sci 2022; 43:5543-5552. [DOI: 10.1007/s10072-022-06204-7] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 11/07/2021] [Accepted: 05/14/2022] [Indexed: 10/17/2022]
|
2
|
Muñoz-Almaraz FJ, Zamora-Martínez F, Botella-Rocamora P, Pardo J. Supervised filters for EEG signal in naturally occurring epilepsy forecasting. PLoS One 2017. [PMID: 28632737 PMCID: PMC5478122 DOI: 10.1371/journal.pone.0178808] [Citation(s) in RCA: 3] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [MESH Headings] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/22/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Francisco Javier Muñoz-Almaraz
- ESAI - Embedded Systems and Artificial Intelligence Group Dept. of Physical Sciences, Mathematics and Computing Universidad CEU Cardenal Herrera, Valencia, Spain
- * E-mail:
| | - Francisco Zamora-Martínez
- ESAI - Embedded Systems and Artificial Intelligence Group Dept. of Physical Sciences, Mathematics and Computing Universidad CEU Cardenal Herrera, Valencia, Spain
| | - Paloma Botella-Rocamora
- ESAI - Embedded Systems and Artificial Intelligence Group Dept. of Physical Sciences, Mathematics and Computing Universidad CEU Cardenal Herrera, Valencia, Spain
| | - Juan Pardo
- ESAI - Embedded Systems and Artificial Intelligence Group Dept. of Physical Sciences, Mathematics and Computing Universidad CEU Cardenal Herrera, Valencia, Spain
| |
Collapse
|
3
|
Wang S, Zhang Y, Liu G, Phillips P, Yuan TF. Detection of Alzheimer's Disease by Three-Dimensional Displacement Field Estimation in Structural Magnetic Resonance Imaging. J Alzheimers Dis 2016; 50:233-48. [PMID: 26682696 DOI: 10.3233/jad-150848] [Citation(s) in RCA: 38] [Impact Index Per Article: 4.8] [Reference Citation Analysis] [Abstract] [Key Words] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 12/12/2022]
Abstract
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.
Collapse
Affiliation(s)
- Shuihua Wang
- School of Computer Science and Technology & School of Psychology, Nanjing Normal University, Nanjing, Jiangsu, China.,School of Electronic Science and Engineering, Nanjing University, Nanjing, Jiangsu, China.,Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing, Nanjing, Jiangsu, China
| | - Yudong Zhang
- School of Computer Science and Technology & School of Psychology, Nanjing Normal University, Nanjing, Jiangsu, China.,Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing, Nanjing, Jiangsu, China
| | - Ge Liu
- Translational Imaging Division & MRI Unit, Columbia University & New York State Psychiatric Institute, New York, NY, USA
| | - Preetha Phillips
- School of Natural Sciences and Mathematics, Shepherd University, Shepherdstown, WV, USA
| | - Ti-Fei Yuan
- School of Computer Science and Technology & School of Psychology, Nanjing Normal University, Nanjing, Jiangsu, China
| |
Collapse
|
4
|
Zhang Y, Wang S. Detection of Alzheimer's disease by displacement field and machine learning. PeerJ 2015; 3:e1251. [PMID: 26401461 PMCID: PMC4579022 DOI: 10.7717/peerj.1251] [Citation(s) in RCA: 41] [Impact Index Per Article: 4.6] [Reference Citation Analysis] [Abstract] [Key Words] [Grants] [Track Full Text] [Download PDF] [Figures] [Journal Information] [Subscribe] [Scholar Register] [Received: 07/28/2015] [Accepted: 08/29/2015] [Indexed: 12/26/2022] Open
Abstract
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.
Collapse
Affiliation(s)
- Yudong Zhang
- School of Computer Science and Technology, Nanjing Normal University, Nanjing, Jiangsu, China
- Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing, Nanjing, Jiangsu, China
| | - Shuihua Wang
- School of Electronic Science and Engineering, Nanjing University, Nanjing, Jiangsu, China
- Jiangsu Key Laboratory of 3D Printing Equipment and Manufacturing, Nanjing, Jiangsu, China
| |
Collapse
|
5
|
Chen T, Rangarajan A, Eisenschenk SJ, Vemuri BC. Construction of a neuroanatomical shape complex atlas from 3D MRI brain structures. Neuroimage 2012; 60:1778-87. [DOI: 10.1016/j.neuroimage.2012.01.095] [Citation(s) in RCA: 9] [Impact Index Per Article: 0.8] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Received: 06/23/2011] [Revised: 01/14/2012] [Accepted: 01/18/2012] [Indexed: 11/24/2022] Open
|
6
|
Classen S, Crizzle AM, Winter SM, Silver W, Eisenschenk S. Evidence-based review on epilepsy and driving. Epilepsy Behav 2012; 23:103-12. [PMID: 22227593 DOI: 10.1016/j.yebeh.2011.11.015] [Citation(s) in RCA: 66] [Impact Index Per Article: 5.5] [Reference Citation Analysis] [Abstract] [Track Full Text] [Journal Information] [Submit a Manuscript] [Subscribe] [Scholar Register] [Received: 08/29/2011] [Revised: 11/07/2011] [Accepted: 11/08/2011] [Indexed: 10/14/2022]
Abstract
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.
Collapse
Affiliation(s)
- Sherrilene Classen
- Institute for Mobility, Activity and Participation, College of Public Health and Health Professions, University of Florida, Gainesville, FL 32610, USA.
| | | | | | | | | |
Collapse
|
7
|
Liu M, Vemuri BC. RBOOST: RIEMANNIAN DISTANCE BASED REGULARIZED BOOSTING. PROCEEDINGS. IEEE INTERNATIONAL SYMPOSIUM ON BIOMEDICAL IMAGING 2011; 2011:1831-1834. [PMID: 21927643 DOI: 10.1109/isbi.2011.5872763] [Citation(s) in RCA: 1] [Impact Index Per Article: 0.1] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 11/10/2022]
Abstract
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.
Collapse
Affiliation(s)
- Meizhu Liu
- Department of CISE, University of Florida, Gainesville, FL 32611
| | | |
Collapse
|
8
|
Zhou L, Hartley R, Wang L, Lieby P, Barnes N. Identifying anatomical shape difference by regularized discriminative direction. IEEE TRANSACTIONS ON MEDICAL IMAGING 2009; 28:937-950. [PMID: 19164083 DOI: 10.1109/tmi.2009.2012556] [Citation(s) in RCA: 5] [Impact Index Per Article: 0.3] [Reference Citation Analysis] [Abstract] [MESH Headings] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/27/2023]
Abstract
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.
Collapse
Affiliation(s)
- Luping Zhou
- RSISE, Australian National University, Canberra, ACT 0200, Australia
| | | | | | | | | |
Collapse
|
9
|
Hufnagel H, Pennec X, Ehrhardt J, Ayache N, Handels H. Generation of a statistical shape model with probabilistic point correspondences and the expectation maximization- iterative closest point algorithm. Int J Comput Assist Radiol Surg 2008. [DOI: 10.1007/s11548-007-0138-9] [Citation(s) in RCA: 36] [Impact Index Per Article: 2.3] [Reference Citation Analysis] [Track Full Text] [Journal Information] [Subscribe] [Scholar Register] [Indexed: 11/27/2022]
|
10
|
Hufnagel H, Pennec X, Ehrhardt J, Handels H, Ayache N. Shape analysis using a point-based statistical shape model built on correspondence probabilities. MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION : MICCAI ... INTERNATIONAL CONFERENCE ON MEDICAL IMAGE COMPUTING AND COMPUTER-ASSISTED INTERVENTION 2008; 10:959-67. [PMID: 18051151 DOI: 10.1007/978-3-540-75757-3_116] [Citation(s) in RCA: 6] [Impact Index Per Article: 0.4] [Reference Citation Analysis] [Abstract] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 02/16/2023]
Abstract
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.
Collapse
|
11
|
Kodipaka S, Banerjee A, Vemuri BC. Large Margin Pursuit for a Conic Section Classifier. PROCEEDINGS. IEEE COMPUTER SOCIETY CONFERENCE ON COMPUTER VISION AND PATTERN RECOGNITION 2008; 2008:1-6. [PMID: 19255652 PMCID: PMC2638098 DOI: 10.1109/cvpr.2008.4587406] [Citation(s) in RCA: 0] [Impact Index Per Article: 0] [Reference Citation Analysis] [Abstract] [Grants] [Track Full Text] [Subscribe] [Scholar Register] [Indexed: 05/27/2023]
Abstract
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.
Collapse
Affiliation(s)
- Santhosh Kodipaka
- Department of Computer & Information Science & Engineering, University of Florida, Gainesville, FL 32611
| | | | | |
Collapse
|