Automatic detection of brain tumor in magnetic resonance images using multi‐texton histogram and support vector machine

Segmentation is the process of labeling objects in image data. It is a decisive phase in several medical imaging processing tasks for operation planning, radio therapy or diagnostics, and widely useful for studying the differences of healthy persons and persons with tumor. Magnetic Resonance Imaging brain tumor segmentation is a complicated task due to the variance and intricacy of tumors. In this article, a tumor segmentation scheme is presented, which focuses on the structural analysis on both tumorous and normal tissues. Our proposed method hits the target with the aid of the following major steps: (i) Tumor Region Location, (ii) Feature Extraction using Multi‐texton Technique, and (iii) Final Classification using support vector machine (SVM). The results for the tumor detection are validated through evaluation metrics such as, sensitivity, specificity, and accuracy. The comparative analysis is carried out by Radial Basis Function neural network and Feed Forward Neural Network. The obtained results depict that the proposed Multi‐texton histogram and support vector machine based brain tumor detection approach is more robust than the other classifiers in terms of sensitivity, specificity, and accuracy. © 2013 Wiley Periodicals, Inc. Int J Imaging Syst Technol, 23, 97–103, 2013     

Brain tumor segmentation and classification via adaptive CLFAHE with hybrid classification

This article exploits a new brain tumor classification model that includes five steps like (a) denoising, (b) skull stripping, (c) segmentation, (d) feature extraction and (e) classification. Initially, the image is subjected under the denoising process, where the noise removal procedure is carried out by employing the entropy-based trilateral filter. Then, the denoised image is applied to the skull stripping process via Otsu thresholding and morphology segmentation. Subsequently, the next step is the segmentation, where the image is segmented by deploying the adaptive CLFAHE (contrast limited fuzzy adaptive histogram equalization) technique. Once the segmentation is completed, gray-level co-occurrence matrix (GLCM) based features are extracted. Finally, the extracted features are processed under hybrid classification model to attain enhanced classification rate. Here, hybrid classification hybrids two classifiers namely deep belief network (DBN) and Bayesian regularization classifier. The vital contribution of this research work exists in the optimal selection of hidden neurons in the DBN. Along with this, the membership function (bounding limits) of fuzzy logic is optimally selected. For this, a new lion exploration based whale optimization (LE-WO) algorithm is proposed in this article that hybrids the concept of (lion algorithm) LA and (whale optimization algorithm) WOA. Finally, the performance of proposed LE-WO is compared over the other methods in terms of accuracy, sensitivity, specificity, precision, negative predictive value (NPV), F1 _ score and Matthews correlation coefficient (MCC), False positive rate (FPR), False negative rate (FNR) and false discovery rate (FDR) and proves the betterments of proposed work. From the outcomes, the accuracy measure of proposed model at 60th population size is 1.98%, 1.81%, 1.32%, 3.46% and 0.75% better than PSO, FF, GWO, WOA and LA, respectively. Similarly, in 80th population size, the performance of the implemented model is 4.47%, 5.04%, 3.96%, 6.29% and 1.37% superior to PSO, FF, GWO, WOA and LA, respectively. Thus, the betterment of the adopted scheme is validated in an effective manner.     

一种基于核主成分分析和组合分类器的虹膜识别方法

提出了一种新的虹膜特征提取与识别方法,该方法利用核主成分分析(KPCA)在高维空间具有较强的特征选择能力来提取虹膜图像的纹理特征。采用了一种距离度量和支持向量机相结合的两级分类方法,前级采用欧式距离来度量图像间的相似性,若符合条件,给出分类结果,否则拒绝,并转入后一级分类器——支持向量机分类,以减少进入支持向量机的样本数目,该组合分类方法充分利用了支持向量机识别率高和距离度量速度快的优点。实验结果表明,该方法提高了虹膜识别率,是一种有效的虹膜识别方法。     

基于特征融合和交叉核SVM的快速行人检测方法

行人检测是目标识别领域的一大难点。现阶段用于行人检测的特征维数都比较高,为克服高维特征对实时性的影响,本文运用主元分析(PCA)对特征进行降维,加快检测速度。单一特征的信息有限,本文运用基于线性鉴别分析(LDA)的线性权重融合原则对一些底层特征(颜色、梯度、直方图)和多层次导向边缘能量特征进行特征融合使特征具有多源信息。且上述特征可采用积分图技术进行快速计算,所以行人检测系统的鲁棒性和实时性得到加强。在目标识别领域直方图交叉核支持向量机(HIKSVM)具有分类快,且准确率高的优点,采用其进行分类,系统实时性更进一步提升。实验表明本文方法检测速度和检测率优于经典的HOG+SVM算法。     

Alzheimer disease classification using KPCA,LDA, and multi‐kernel learning SVM

Early diagnosis of Alzheimer disease (AD) and mild cognitive impairment (MCI) is always useful. Preventive measures might have an impact on reducing AD risk factors. Structural magnetic resonance (MR) imaging, one of the vital sensitive biomarkers for cerebral atrophy in the brain, is used to extract volumetric feature by FreeSurfer and the CIVET toolbox. All of the structural magnetic resonance imaging (s‐MRI) data that we used were downloaded from the Alzheimer's disease Neuroimaging Initiative (ADNI) database (adni.loni.usc.edu) of imaging data. This novel approach is applied for the diagnosis of AD and MCI from healthy controls (HCs) combining extracted features with the MMSE (mini‐mental state examination) scores, applying a two sample t‐test to select a subset of features. The subset of features is fed to kernel principal component analysis (KPCA) module to project data onto the reduced principal component coefficients at higher dimensional kernel space to increase the linear separability. Then, the kernel PCA coefficients are projected into the more efficient linear discriminant space using linear discriminant analysis. A multi‐kernel learning support vector machine (SVM) is used on newly projected data for stratification of AD and MCI from HCs. Using this approach, we obtain 93.85% classification accuracy when detecting AD from HCs for segmented volumetric features (using FreeSurfer) with high sensitivity and specificity. When distinguishing MCI from HCs and AD using volumetric features after subcortical segmentation, the detection rate reaches 86.54% and 75.12%, respectively.     

Feature selection and fault‐severity classification–based machine health assessment methodology for point machine sliding‐chair degradation

In this paper, we propose an offline and online machine health assessment (MHA) methodology composed of feature extraction and selection, segmentation‐based fault severity evaluation, and classification steps. In the offline phase, the best representative feature of degradation is selected by a new filter‐based feature selection approach. The selected feature is further segmented by utilizing the bottom‐up time series segmentation to discriminate machine health states, ie, degradation levels. Then, the health state fault severity is extracted by a proposed segment evaluation approach based on within segment rate‐of‐change (RoC) and coefficient of variation (CV) statistics. To train supervised classifiers, a priori knowledge about the availability of the labeled data set is needed. To overcome this limitation, the health state fault‐severity information is used to label (eg, healthy, minor, medium, and severe) unlabeled raw condition monitoring (CM) data. In the online phase, the fault‐severity classification is carried out by kernel‐based support vector machine (SVM) classifier. Next to SVM, the k‐nearest neighbor (KNN) is also used in comparative analysis on the fault severity classification problem. Supervised classifiers are trained in the offline phase and tested in the online phase. Unlike to traditional supervised approaches, this proposed method does not require any a priori knowledge about the availability of the labeled data set. The proposed methodology is validated on infield point machine sliding‐chair degradation data to illustrate its effectiveness and applicability. The results show that the time series segmentation‐based failure severity detection and SVM‐based classification are promising.     

Classification of Coronavirus (COVID‐19) from X‐ray and CT images using shrunken features

Necessary screenings must be performed to control the spread of the COVID‐19 in daily life and to make a preliminary diagnosis of suspicious cases. The long duration of pathological laboratory tests and the suspicious test results led the researchers to focus on different fields. Fast and accurate diagnoses are essential for effective interventions for COVID‐19. The information obtained by using X‐ray and Computed Tomography (CT) images is vital in making clinical diagnoses. Therefore it is aimed to develop a machine learning method for the detection of viral epidemics by analyzing X‐ray and CT images. In this study, images belonging to six situations, including coronavirus images, are classified using a two‐stage data enhancement approach. Since the number of images in the dataset is deficient and unbalanced, a shallow image augmentation approach was used in the first phase. It is more convenient to analyze these images with hand‐crafted feature extraction methods because the dataset newly created is still insufficient to train a deep architecture. Therefore, the Synthetic minority over‐sampling technique algorithm is the second data enhancement step of this study. Finally, the feature vector is reduced in size by using a stacked auto‐encoder and principal component analysis methods to remove interconnected features in the feature vector. According to the obtained results, it is seen that the proposed method has leveraging performance, especially to make the diagnosis of COVID‐19 in a short time and effectively. Also, it is thought to be a source of inspiration for future studies for deficient and unbalanced datasets.     

Epileptic seizure detection by combining robust‐principal component analysis and least square‐support vector machine

The feature extraction from electroencephalogram (EEG) signals is widely used for computer‐aided epileptic seizure detection. However, multiple channels of EEG signals and their correlations have not been completely harnessed. In this article, a novel automatic seizure detection approach is proposed by analyzing the spatiotemporal correlation of multi‐channel EEG signals. This approach combines the maximum cross‐correlation, robust‐principal component analysis, and least square‐support vector machine to detect the events. Our proposed method delivers higher detection sensitivity, specificity, and accuracy than the state‐of‐the‐art approaches based on the 19 channels’ EEG signals of 37 absence epilepsy patients experiencing 57 seizure events.