Structural Co-occurrence Matrix Research Articles

HEALTH OF THINGS MODEL FOR CLASSIFYING HUMAN HEART SOUND SIGNALS USING CO-OCCURRENCE MATRIX AND SPECTROGRAM

Cardiovascular diseases have become one of the world’s leading causes of death today. Several decision-making systems have been developed with computer-aided support to help the cardiologists in detecting heart disease and thereby minimizing the mortality rate. This paper uses an unexplored sub-domain related to textural features for classifying phonocardiogram (PCG) as normal or abnormal using Grey Level Co-occurrence Matrix (GLCM). The matrix has been applied to extract features from spectrogram of the PCG signals taken from the Physionet 2016 benchmark dataset. Random Forest, Support Vector Machine, Neural Network, and XGBoost have been applied to assess the status of the human heart using PCG signal spectrogram. The result of GLCM is compared with the two other textural feature extraction methods, viz. structural co-occurrence matrix (SCM), and local binary patterns (LBP). Experimental results have proved that applying machine learning model to classify PCG signal on the dataset where GLCM has extracted the feature-set, the accuracy attained is greater as compared to its peer approaches. Thus, this methodology can go a long way to help the medical specialists in precisely and accurately assessing the heart condition of a patient.

Heart Arrhythmia Classification Based on Statistical Moments and Structural Co-occurrence

The electrocardiogram (ECG) is a widely disseminated method for detecting heart diseases due to its lower cost than other tests. But, some steps are important for detecting cardiac arrhythmias in ECG signals, which are: preprocessing, segmentation, feature extraction and classification. In this work, we assess how four non-morphological feature extraction methods provide useful ECG classification. Moreover, we propose an innovation in the configuration of the structural co-occurrence matrix (SCM), by combining it with the Fourier transform to extract the main frequencies of the signal. We tested theses methods on four well-known classifiers used in the literature and compare the results with six classical feature extraction methods. Moreover, we followed high standard protocols for developing expert systems for clinical usage. The database chosen for evaluation is the MIT-BIH arrhythmia database. We increased the identification of heart dysrhythmia by 2%, representing an advance on reports on the literature. The developed system is 1.3% more reliable than the current best approach reported, being \(10^6\) times faster, as well. The HOS with naive Bayes classified pathologies in 22 patients with 94.3% of accuracy. We perceived that SCM–Fourier is 1.5% more accurate than the SCM or Fourier standalone. The feature extractor proposed in this paper compress 97% of the useful information to provide a reliable arrhythmia classification.

A novel electrocardiogram feature extraction approach for cardiac arrhythmia classification

In this work, we propose a novel approach to detect cardiac arrhythmias in electrocardiograms (ECG). The proposal focuses on different feature extractors and machine learning methods. The feature extraction techniques evaluated were Fourier, Goertzel, Higher Order Statistics (HOS), and Structural Co-Occurrence Matrix (SCM). As far as the authors know, this is the first time that SCM has been applied to the feature extraction task with ECG signals. Four well-known classifiers, commonly referred to in the literature (Support Vector Machine, Multi-Layer Perceptron, Bayesian, and Optimum-Path Forest) were tested and we compared our results with six classical feature extraction methods. Furthermore, the Association for the Advancement of Medical Instrumentation protocol was adopted and we made use of the MIT-BIH Arrhythmia Database for producing reliable results for clinical analysis. The confidence level to identify heart dysrhythmia in our results was 2% greater than other approaches in the literature. The proposed system is 1.3% more accurate than the best approach reported to date, and is 106 times faster. blackIn short, it is clinical reliable to use HOS for describing types of arrhythmia, since achieved 94.3% of accuracy.

Automatic classification of pulmonary diseases using a structural co-occurrence matrix

The World Health Organization (WHO) estimates that 300 million people have asthma and that this disease causes about 250 thousand deaths per year worldwide. The number of deaths from chronic obstructive pulmonary disease increased by 30% in 2015, and this disease will, according to WHO, be the third major cause of death worldwide in 2030. The identification of diseases using medical image processing techniques is in high demand to assist medical doctors to make more accurate diagnoses. However, although these techniques contribute in making medical diagnoses, most of them still need to have some parameters set and this can be a difficult and tedious process. In this paper, a new automatic approach to identify and classify lung diseases from a structural co-occurrence matrix (SCM) in chest computed tomography images is proposed. The most important novelty of this approach is that only the image is used as the input data and extract the structural information of the disease which, in this case, is related to the lower frequencies. In order to demonstrate the efficiency of the proposed technique, it was compared with other well-known state-of-art feature extractors. In addition, the SCM was evaluated with four filters (Gaussian, Fourier, Laplace and Sobel) using linear discriminant analysis, multi-layer perceptron, support vector machines and minimal learning machine classifiers. The results showed that the SCM, when using low frequencies, is able to adapt to different images and extract the most significant structural data, without the need of any additional parameters, yet maintaining the diagnostic precision.

Neurologist-level classification of stroke using a Structural Co-Occurrence Matrix based on the frequency domain

This paper presents a new approach to automatically classify hemorrhagic and ischemic strokes using the Structural Co-Occurrence Matrix (SCM) extracted from the main frequencies of computed tomography images of the brain. The main advantage of this approach is that it only uses the image as a parameter. Specificity, sensitivity, positive predictive value, F-Score, harmonic mean, and accuracy were used as metrics to evaluate the efficiency of the SCM. The SCM was compared with local binary patterns, gray-level co-occurrence matrices, invariant moments of Hu and with the feature extraction method based on human tissue density patterns named Analysis of Human Tissue Densities. Multiple machine learning classifiers were used including support vector machine, multilayer perceptron, minimal learning machine and the linear discriminant analysis. The results show that the SCM in the frequency domain can extract the most discriminant structural information of strokes automatically, obtaining good results without the needed of additional parameters.

Automatic histologically-closer classification of skin lesions

According to the American Cancer Society, melanoma is one of the most common types of cancer in the world. In 2017, approximately 87,110 new cases of skin cancer were diagnosed in the United States alone. A dermatoscope is a tool that captures lesion images with high resolution and is one of the main clinical tools to diagnose, evaluate and monitor this disease. This paper presents a new approach to classify melanoma automatically using structural co-occurrence matrix (SCM) of main frequencies extracted from dermoscopy images. The main advantage of this approach consists in transform the SCM in an adaptive feature extractor improving his power of discrimination using only the image as parameter. The images were collected from the International Skin Imaging Collaboration (ISIC) 2016, 2017 and Pedro Hispano Hospital (PH2) datasets. Specificity (Spe), sensitivity (Sen), positive predictive value, F Score, Harmonic Mean, accuracy (Acc) and area under the curve (AUC) were used to verify the efficiency of the SCM. The results show that the SCM in the frequency domain work automatically, where it obtained better results in comparison with local binary patterns, gray-level co-occurrence matrix and invariant moments of Hu as well as compared with recent works with the same datasets. The results of the proposed approach were: Spe 95.23%, 92.15% and 99.4%, Sen 94.57%, 89.9% and 99.2%, Acc 94.5%, 89.93% and 99%, and AUC 92%, 90% and 99% in ISIC 2016, 2017 and PH2 datasets, respectively.

Health of Things Algorithms for Malignancy Level Classification of Lung Nodules

Lung cancer is one of the leading causes of death world wide. Several computer-aided diagnosis systems have been developed to help reduce lung cancer mortality rates. This paper presents a novel structural co-occurrence matrix (SCM)-based approach to classify nodules into malignant or benign nodules and also into their malignancy levels. The SCM technique was applied to extract features from images of nodules and classifying them into malignant or benign nodules and also into their malignancy levels. The computed tomography exams from the lung image database consortium and image database resource initiative datasets provide information concerning nodule positions and their malignancy levels. The SCM was applied on both grayscale and Hounsfield unit images with four filters, to wit, mean, Laplace, Gaussian, and Sobel filters creating eight different configurations. The classification stage used three well-known classifiers: multilayer perceptron, support vector machine, and $k$ -nearest neighbors algorithm and applied them to two tasks: ( $i$ ) to classify the nodule images into malignant or benign nodules and ( $ii$ ) to classify the lung nodules into malignancy levels (1 to 5). The results of this approach were compared to four other feature extraction methods: gray-level co-occurrence matrix, local binary patterns, central moments, and statistical moments. Moreover, the results here were also compared to the results reported in the literature. Our approach outperformed the other methods in both tasks; it achieved 96.7% for both accuracy and F-Score metrics in the first task, and 74.5% accuracy and 53.2% F-Score in the second. These experimental results reveal that the SCM successfully extracted features of the nodules from the images and, therefore may be considered as a promising tool to support medical specialist to make a more precise diagnosis concerning the malignancy of lung nodules.

A New Approach to Diagnose Parkinson's Disease Using a Structural Cooccurrence Matrix for a Similarity Analysis.

Parkinson's disease affects millions of people around the world and consequently various approaches have emerged to help diagnose this disease, among which we can highlight handwriting exams. Extracting features from handwriting exams is an important contribution of the computational field for the diagnosis of this disease. In this paper, we propose an approach that measures the similarity between the exam template and the handwritten trace of the patient following the exam template. This similarity was measured using the Structural Cooccurrence Matrix to calculate how close the handwritten trace of the patient is to the exam template. The proposed approach was evaluated using various exam templates and the handwritten traces of the patient. Each of these variations was used together with the Naïve Bayes, OPF, and SVM classifiers. In conclusion the proposed approach was proven to be better than the existing methods found in the literature and is therefore a promising tool for the diagnosis of Parkinson's disease.

Rotation-invariant feature extraction using a structural co-occurrence matrix

Abstract Feature extraction plays a key role in pattern recognition. Here we present a rotation-invariant feature extraction methodology based on a structural approach using co-occurrence statistics. We assessed the performance of our method comparing it to a gray-level co-occurrence matrix, local binary patterns and invariant moments in pattern recognition experiments. The results show that the proposed method provides an efficient and fast way to analyze digital images.