Gray Level Run Length Matrix Features Research Articles

GPU-Accelerated GLRLM Algorithm for Feature Extraction of MRI

The gray level run length matrix (GLRLM) whose entries are statistics recording distribution and relationship of images pixels is a widely used method for extracting statistical features for medical images, e.g., magnetic resonance (MR) images. Recently these features are usually employed in some artificial neural networks to identify and distinguish texture patterns. But GLRLM construction and features extraction are tedious and computationally intensive while the images are too big with high resolution, or there are too many small or intermediate Regions of Interest (ROI) to process in a single image, which makes the preprocess a time consuming stage. Hence, it is of great importance to accelerate the procedure which is nowadays possible with the rapid development of massively parallel Graphics Processing Unit, i.e. the GPU computing technology. In this article, we propose a new paradigm based on mature parallel primitives for generating GLRLMs and extracting multiple features for many ROIs simultaneously in a single image. Experiments show that such a paradigm is easy to implement and offers an acceleration over 5 fold increase in speed than an optimized serial counterpart.

GLRLM features in CT texture analysis are prognostic factors: Evaluation of pancreatic cancer heterogeneity, retrospective cohort study

Introduction: Pancreatic cancer is an lethal disease. Tumor heterogeneity is an important indicator of the progression of chemoresistance. Although texture analyses can allow quantification of tumor heterogeneity, only a few studies reported the use of texture analysis in cases of pancreatic cancer. Therefore, we analyzed tumor heterogeneity in preoperative computed tomography (CT) scans by performing texture analysis using the gray-level run-length matrix (GLRLM). Method: We analyzed 116 consecutive patients who underwent surgical resection during 2001-2017 and had preoperative CT data available for analysis. An ROI was drawn on slices with a visible tumor and normal pancreas on the arterial phase CT scans and the correlation of pathological characteristics and GLRLM features was analyzed. We then performed Kaplan—Meier survival curve analysis among pancreatic cancer patients. Result: The gray-level non-uniformity (GLN) values in GLRLM features for tumors were higher than those for normal pancreas. High GLN values represent a non-uniform texture, i.e., heterogeneity. Recurrence-free survival was shorter in the group with high GLN135 values (p = 0.025). Conclusion: Tumor heterogeneity is a significant prognostic factor. Our analyses of the correlation between pathological outcomes and GLRLM features in pancreatic cancer patients showed that GLN values were a powerful indicator of prognosis.

Feature subset selection for classification of malignant and benign breast masses in digital mammography

Computer-aided diagnosis of breast cancer is becoming increasingly a necessity given the exponential growth of performed mammograms. In particular, the breast mass diagnosis and classification arouse nowadays a great interest. Texture and shape are the most important criteria for the discrimination between benign and malignant masses. Various features have been proposed in the literature for the characterization of breast masses. The performance of each feature is related to its ability to discriminate masses from different classes. The feature space may include a large number of irrelevant ones which occupy a lot of storage space and decrease the classification accuracy. Therefore, a feature selection phase is usually needed to avoid these problems. The main objective of this paper is to select an optimal subset of features in order to improve masses classification performance. First, a study of various descriptors which are commonly used in the breast cancer field is conducted. Then, selection techniques are used in order to determine the most relevant features. A comparative study between selected features is performed in order to test their ability to discriminate between malignant and benign masses. The database used for experiments is composed of mammograms from the MiniMIAS database. Obtained results show that Gray-Level Run-Length Matrix features provide the best result.

AN AUTOMATED COMPUTER-AIDED DETECTION (CADe) AND DIAGNOSIS (CADx) SYSTEM FOR BREAST MICROCALCIFICATIONS IN MAMMOGRAMS

ABSTRACT An automated computer aided diagnosis system has been proposed for detection of microcalcification (MC) clusters in mammograms. The proposed system is a whole system including suspicious regions identification, MCs detection, false positive reduction and benign/malign classification. For classification of suspicious microcalcification regions, a multilayer perceptron (MLP) neural network was used with grey level co-occurrence matrix (GLCM) and statistical features. Then to decrease the false positive classification ratio, we used cascade correlation neural network (CCNN) with grey level run length matrix (GLRLM) features. In the last step, hybrid form of discriminant analysis and support vector machine (SVM) methods were used with GLRLM features for benign/malign classification of detected MC clusters. The open access Mammographic Image Analysis Society (MIAS) database was used for the study. Experimental results show that the proposed algorithm obtained 86% sensitivity, 98.3% specificity and 1.163 FPpI rates for detection an for diagnosis of breast cancer, the obtained sensitivity and specificity values are 100% and 100% respectively. Despite the vision difficulty of MC clusters, the novel system provides very satisfactory results. Furthermore, the developed system is fully automatic whole system which gives outputs as percentages and transformed assessment categories. Keywords: Mammograms, Breast cancer, Computer aided diagnosis, Cascade correlation neural network (CCNN), Grey level co-occurrence matrix ( GLCM), Grey level run length matrix (GLRLM).

GLCM and GLRLM based Feature Extraction Technique in Mammogram Images

A mammogram is an x-ray that allows a qualified specialist to examine the breast tissue for any suspicious areas. Mammogram helps for early diagnosis before showing symptoms of cancer. The aim of this paper is to extract the various features of pre-processed mammogram images to improve the performance of the diagnosis, which helps the radiologists in reducing the false positive predictions. Mammogram images are pre-processed using hybrid filter MAX_AVM. Shape, Intensity, Gray Level Co-occurrence Matrix and Gray Level Run-Length Matrix features that help to represent the various classes of objects are extracted and used as inputs to the classifier. The classifier helps to classify the mammogram images into a normal or abnormal pattern. Experiments were conducted on MIAS database. The result shows that the combination of GLCM and GLRLM features are efficient and achieved the maximum classification accuracy rate when compared to other features.

Comparative Study of Classification of Split Bulk Grams Using Different Significant Feature Selection Techniques

This paper presents the comparative study of similar looking split bulk grams using two major feature extraction methods, Gray Level Co-occurrence Matrix (GLCM) and Gray Level Run Length Matrix (GLRLM). For comparison 22 GLCM features, 11 GLRLM features and 33 combined features (GLCM+GLRLM) are extracted from five different types of similar looking split bulk grams. As a part of significant feature selection step, two approaches, namely Correlation-based Feature Selection (CFS) evaluator and consistency-based subset (CSE) evaluator have been applied separately with six different searching methods. The evaluation of significant features selected is done using six different classifiers. Result proves that feature set selected by the GLCM is better when compared to that with GLRLM features. Further, CFS with Best First Search (BFS) identified features (from combined GLCM+GLRLM)resulted in best accuracy of 88% for Multilayer Perceptron classifier. In addition, CSE with Genetic Algorithm (GA)-based search identified features (from combined GLCM+GLRLM) resulted in best accuracy of 87% for Multilayer Perceptron classifier.

Texture analysis of acute myocardial infarction with CT: First experience study.

ObjectiveTo investigate the feasibility and accuracy of texture analysis to distinguish through objective and quantitative image information between healthy and infarcted myocardium with computed tomography (CT).Materials and methodsTwenty patients (5 females; mean age 56±10years) with proven acute myocardial infarction (MI) and 20 patients (8 females; mean age 42±15years) with no cardiac abnormalities (hereafter termed controls) underwent contrast-enhanced cardiac CT. Short axis CT images of the left ventricle (LV) were reconstructed at the slice thicknesses 1mm, 2mm, and 5mm. Two independent, blinded readers segmented the LV in controls and patients. Texture analysis was performed yielding first-level features based on the histogram (variance, skewness, kurtosis, entropy), second-level features based on the gray-level co-occurrence matrix (GLCM) (contrast, correlation, energy and homogeneity), and third-level features based on the gray-level run-length matrix (GLRLM).ResultsInter-and intrareader agreement was good to excellent for all histogram (intraclass correlation coefficient (ICC):0.70–0.93) and for all GLCM features (ICC:0.66–0.99), and was variable for the GLRLM features (ICC:-0.12–0.99). Univariate analysis showed significant differences between patients and controls for 2/4 histogram features, 3/4 GLCM and for 6/11 GLRLM features and all assessed slice thicknesses (all,p<0.05). In a multivariate logistic regression model, the single best variable from each level, determined by ROC analysis, was included stepwise. The best model included kurtosis (OR 0.08, 95%CI:0.01–0.65,P = 0.018) and short run high gray-level emphasis (SRHGE, OR 0.97, 95%CI:0.94–0.99,P = 0.007), with an area-under-the-curve (AUC) of 0.90 (95%CI:0.80–0.99). The best results for kurtosis and SRHGE (AUC = 0.78) were obtained at a 5mm slice thickness. A cut-off value of 14.4 for kurtosis+0.013*SRHGE predicted acute MI with a sensitivity of 95% (specificity 55%).ConclusionOur study illustrates the feasibility of texture analysis for distinguishing healthy from acutely infarcted myocardium with cardiac CT using objective, quantitative features, with most reproducible and accurate results at a short axis slice thickness of 5mm.

Characterization of Pancreas at Diabetic Patients in CT images using Texture Analysis

This study concern to characterize the pancreas areato head, body and tail using Gray Level Run Length Matrix (GLRLM) and extract classification features from CT images. The GLRLM techniques included eleven’s features. To find the gray level distribution in CT images it complements the GLRLM features extracted from CT images with runs of gray level in pixels and estimate the size distribution of thesubpatterns. analyzing the image with Interactive Data Language IDL software to measure the grey level distribution of images. The results show that the Gray Level Run Length Matrix and features give classification accuracy of pancreashead 89.2%, body 93.6 and the tail classification accuracy 93.5%. The overall classification accuracy of pancreas area 92.0%.These relationships are stored in a Texture Dictionary that can be later used to automatically annotate new CT images with the appropriate pancreas area names.

Hybrid approach to classification of focal and diffused liver disorders using ultrasound images with wavelets and texture features

This study presents a computer-based approach to classify ten different kinds of focal and diffused liver disorders using ultrasound images. The diseased portion is isolated from the ultrasound image by applying active contour segmentation technique. The segmented region is further decomposed into horizontal, vertical and diagonal component images by applying biorthogonal wavelet transform. From the above wavelet filtered component images, grey level run-length matrix features are extracted and classified using random forests by applying ten-fold cross-validation strategy. The results are compared with spatial feature extraction techniques such as intensity histogram, invariant moment features and spatial texture features such as grey-level co-occurrence matrices, grey-level run length matrices and fractal texture features. The proposed technique, which is an application of texture feature extraction on transform domain images, gives an overall classification accuracy of 91% for a combination of ten classes of similar looking diseases which is appreciable than the spatial domain only techniques for liver disease classification from ultrasound images.

Copy-Move forgery detection in images using grey-level run length matrix features

Copy-move detection also known as region duplication detection is a well-recognised and active area of research owing to great demand of authenticating genuineness of images. Currently available techniques for copy-move detection fail to accurately locate the tampered region and lack robustness against common post-processing operations like compression, blurring and brightness changes. This paper proposes a novel technique for detection and localisation of copy-move regions in image using grey-level run length matrix (GLRLM) features. In the proposed method, we first divide the forged image into overlapping blocks and GLRLM features are calculated for each block. Features calculated for each block form feature vectors. Feature vectors thus obtained are lexicographically sorted. Blocks with similar features are identified using Euclidean feature distances. Post-processing isolates similar blocks. The results demonstrate the effectiveness of the proposed scheme to locate copy-move forgery and robustness against operations like jpeg compression, blurring and contrast adjustments.

Copy-Move forgery detection in images using grey-level run length matrix features

Copy-move detection also known as region duplication detection is a well-recognised and active area of research owing to great demand of authenticating genuineness of images. Currently available techniques for copy-move detection fail to accurately locate the tampered region and lack robustness against common post-processing operations like compression, blurring and brightness changes. This paper proposes a novel technique for detection and localisation of copy-move regions in image using grey-level run length matrix (GLRLM) features. In the proposed method, we first divide the forged image into overlapping blocks and GLRLM features are calculated for each block. Features calculated for each block form feature vectors. Feature vectors thus obtained are lexicographically sorted. Blocks with similar features are identified using Euclidean feature distances. Post-processing isolates similar blocks. The results demonstrate the effectiveness of the proposed scheme to locate copy-move forgery and robustness against operations like jpeg compression, blurring and contrast adjustments.

Texture Analysis of Supraspinatus Ultrasound Image for Computer Aided Diagnostic System.

ObjectivesIn this paper, we proposed an algorithm for recognizing a rotator cuff supraspinatus tendon tear using a texture analysis based on a histogram, gray level co-occurrence matrix (GLCM), and gray level run length matrix (GLRLM).MethodsFirst, we applied a total of 57 features (5 first order descriptors, 40 GLCM features, and 12 GLRLM features) to each rotator cuff region of interest. Our results show that first order statistics (mean, skewness, entropy, energy, smoothness), GLCM (correlation, contrast, energy, entropy, difference entropy, homogeneity, maximum probability, sum average, sum entropy), and GLRLM features are helpful to distinguish a normal supraspinatus tendon and an abnormal supraspinatus tendon. The statistical significance of these features is verified using a t-test. The support vector machine classification showed accuracy using feature combinations. Support Vector Machine offers good performance with a small amount of training data. Sensitivity, specificity, and accuracy are used to evaluate performance of a classification test.ResultsFrom the results, first order statics features and GLCM and GLRLM features afford 95%, 85%, and 100% accuracy, respectively. First order statistics and GLCM and GLRLM features in combination provided 100% accuracy. Combinations that include GLRLM features had high accuracy. GLRLM features were confirmed as highly accurate features for classified normal and abnormal.ConclusionsThis algorithm will be helpful to diagnose supraspinatus tendon tear on ultrasound images.

Statistical Methods for Quantitatively Detecting Fungal Disease from Fruits' Images

In this paper we have proposed statistical methods for detecting fungal disease and classifying based on disease severity levels. Most fruits diseases are caused by bacteria, fungi, virus, etc of which fungi are responsible for a large number of diseases in fruits. In this study images of fruits, affected by different fungal symptoms are collected and categorized based on disease severity. Statistical features like block wise, gray level co-occurrence matrix (GLCM), gray level runlength matrix (GLRLM) are extracted from these images. The nearest neighbor classifier using Euclidean distance was used to classify images as partially affected, moderately affected, severely affected and normal. The average classification accuracies are 91.37% and 86.715% using GLCM and GLRLM features. The average classification accuracy has increased to 94.085% using block wise features.

Evaluation of Texture for Classification of Abdominal Aortic Aneurysm After Endovascular Repair

The use of the endovascular prostheses in abdominal aortic aneurysm has proven to be an effective technique to reduce the pressure and rupture risk of aneurysm. Nevertheless, in a long-term perspective, complications such as leaks inside the aneurysm sac (endoleaks) could appear causing a pressure elevation and increasing the danger of rupture consequently. At present, computed tomographic angiography (CTA) is the most common examination for medical surveillance. However, endoleak complications cannot always be detected by visual inspection on CTA scans. The investigation on new techniques to detect endoleaks and analyse their effects on treatment evolution is of great importance for endovascular aneurysm repair (EVAR) technique. The purpose of this work was to evaluate the capability of texture features obtained from the aneurysmatic thrombus CT images to discriminate different types of evolutions caused by endoleaks. The regions of interest (ROIs) from patients with different post-EVAR evolution were extracted by experienced radiologists. Three techniques were applied to each ROI to obtain texture parameters, namely the grey level co-occurrence matrix (GLCM), the grey level run length matrix (GLRLM) and the grey level difference method (GLDM). The results showed that GLCM, GLRLM and GLDM features presented a good discrimination ability to differentiate between favourable or unfavourable evolutions. GLCM was the most efficient in terms of classification accuracy (93.41% ± 0.024) followed by GLRLM (90.17% ± 0.077) and finally by GLDM (81.98% ± 0.045). According to the results, we can consider texture analysis as complementary information to classified abdominal aneurysm evolution after EVAR.