Co-occurrence Matrix Approach Research Articles

Advanced skin disease detection: Image processing and modified genetic optimization with supervised k-nearest neighbors

The use of modern technology to improve skin disease diagnosis includes things like artificial intelligence (AL), deep learning (DL) and computer vision. Medical images of skin lesions, dermatoscopic images, or thermal imaging can be analyzed by automated algorithms and image processing techniques to diagnose skin diseases. Diseases can cause physical and emotional suffering, making them silent killers. Extreme instances might cause skin cancer. skin disease diagnosis from clinical photographs is a key medical image processing challenge. Manual skin diagnosis takes time and it is subjective for doctors. Computerized skin disease prediction can simplify patient and dermatologist treatment planning. To tackle these issues, we proposed a genetic optimization and supervised K-Nearest Neighbor (MGO-SKNN) technique for detecting advanced skin diseases. The research gathers clinical data for detecting advanced skin diseases. Three methods were used to preprocess our data: noise reduction, hair removal and image resizing. The Grey Level Co-Occurrence Matrix (GLCM) approach was used in this work to extract features. The integration of image processing into MGO-SKNN represents a significant step forward in the quest for accurate, efficient and cutting-edge skin disease diagnosis. The metrics like accuracy (97.53%), precision (95.20%), recall (96.74%) and f1-score (98.06%) of our suggested technique, MGO-SKNN, exceed the traditional approaches for skin detection.

Identification of document paper using hybrid feature extraction.

Document forgery is a significant issue in Korea, with around ten thousand cases reported every year. Analyzing paper plays a crucial role in examining questionable documents such as marketable securities and contracts, which can aid in solving criminal cases of document forgery. Paper analysis can also provide essential insights in other types of criminal cases, serving as an important clue for solving cases such as the source of a blackmail letter. The papermaking process generates distinct forming fabric marks and formations, which are critical features for paper classification. These characteristics are observable under transmitted light and are created by the forming fabric pattern and the distribution of pulp fibers, respectively. In this study, we propose a novel approach for paper identification based on hybrid features. This method combines texture features extracted from images converted using the gray-level co-occurrence matrix (GLCM) approach and a convolutional neural network (CNN), with another set of features extracted by the CNN using the same images as input. We applied the proposed method to classification tasks for seven major paper brands available in the Korean market, achieving an accuracy of 97.66%. The results confirm the applicability of this method for visually inspecting paper products and demonstrate its potential for assisting in solving criminal cases involving document forgery.

UAV-derived photogrammetric point clouds and multispectral indices for fuel estimation in Mediterranean forests

Sensors attached to unmanned aerial vehicles (UAVs) allow estimating a large number of forest attributes related to forest fuels. This study assesses photogrammetric point clouds and multispectral indices obtained from a fixed-wing UAV for the classification of Prometheus fuel types in 82 forest plots in Aragón (NE Spain). Images captured by an RGB camera and a multispectral sensor allowed generating high density photogrammetric point clouds (RGB: 3000 points/m2; multispectral: 85 points/m2), which were normalized using alternatively a Digital Elevation Model (DEM) of 0.5, 1, and 2 m resolution. A set of structural and textural variables were derived from the normalized point cloud heights, and for the latter, the gray-level co-occurrence matrix (GLCM) approach was used. Multispectral images were also used to create seven spectral vegetation indices. The most relevant structural, textural, and spectral variables to introduce into the fuel types classification models were selected using Dunn's test, which included: the vegetation height at the 50th percentile, the coefficient of variation of the heights, the percentage of returns above 4 m, the mean textural dissimilarity, and the mean of the Green Chlorophyll Index. Three different data samples were introduced in the models: i) the relevant structural and textural variables from the RGB camera (RGB data sample); ii) the relevant structural, textural, and spectral variables from the multispectral sensor (MS data sample); and iii) the relevant structural and textural variables from the RGB camera plus the relevant spectral variable from the multispectral sensor (integrated data sample). After comparing three machine learning classification techniques (Random Forest, and Linear and Radial Support Vector Machine), the best results were obtained with Random Forest with k-fold cross-validation (k-10) and the integrated data sample with normalized point clouds at 0.5 m DEM resolution (overall accuracy = 71%). The variables successfully identified the Prometheus main fire carriers (i.e., shrubs or trees) and confusions were mainly located within the fuel types of the same dominant stratum, especially in fuel types 3 and 6. These results demonstrate the ability of UAV imagery to classify forest fuels in Mediterranean environments when RGB and multispectral data are combined.

Implementasi Jaringan Syaraf Tiruan Menggunakan Metode Self-Organizing Map Pada Klasifikasi Citra Jenis Ikan Kakap

Snapper is one of the favorite fish for consumption because it has a myriad of benefits for the human body. There are many types of snapper, especially snapper which is often found in Indonesian waters. Knowing the types of snapper is important knowledge because snapper has different characteristics, for example there are snapper that can be consumed and there are also types of snapper that can be cultivated. However, the lack of information and similar types of snapper makes it difficult for people to identify the type of snapper. This study aims to implement a Self-Organizing Map (SOM) artificial neural network for classification of snapper species based on color and texture characteristics. In order to provide information about the snapper object to be classified, color and texture feature extraction is used. In color feature extraction, RGB and HSV parameters are used and for texture features, the Gray Level Co-occurrence Matrix (GLCM) approach is applied. Furthermore, the characteristic results obtained will be classified using the Self-Organizing Map (SOM) algorithm which divides the input patterns into certain classes so that the network output is in the form of classes that have similarities to the given input. Based on the results of the accuracy test, the built model is capable of producing an accuracy of 89.89%. Thus, the SOM model built for image classification of snapper species is in the good category.

Detection of Sea Surface Temperature Fronts from SAR Images

Abstract Sea surface temperature (SST) fronts are important for fisheries and marine ecology, as well as upper-ocean dynamics, weather forecasting, and climate monitoring. In this paper, we propose a new approach to detect SST fronts from RADARSAT-2 ScanSAR images, based on the correlation of SAR-derived wind speeds using the gray level cooccurrence matrix (GLCM) approach. Due to the large differences between the correlation of wind speeds for SST fronts compared to other areas, SST fronts can be detected by the threshold method. To eliminate small-scale features (or noise), the 30 km scale is used as the length threshold for the detection of the SST fronts. The proposed method is effective when wind speeds are between 3 and 13 m s−1. The overall accuracy of our method is about 93.6%, which is sufficient for operational applications.

Visual perception of surface roughness via maximum variance direction of image patches

Most existing visual roughness perception algorithms are pixel-wised operations, which lead to unstable roughness measurements. To address this problem, a novel visual roughness perception in the maximum variance direction of image patches is proposed in this article. Specifically, each patch is assumed to be a point in a multi-dimensional Euclidean space. To improve the signal-to-noise ratio of roughness, all points are projected onto its maximum variance direction based on principal component analysis. In this direction, the variance of these points is characterized as roughness. A new roughness metric dataset is constructed by scanned images of sandpapers with different mesh sizes to verify the effectiveness of the proposed algorithm. Experiments on the dataset show the proposed method outperforms many computer vision-based methods, such as the gray-level co-occurrence matrix approach and the approach.

The Effect of Rider:Horse Bodyweight Ratio on the Superficial Body Temperature of Horse's Thoracolumbar Region Evaluated by Advanced Thermal Image Processing.

Simple SummaryOverloading of the horse’s thoracolumbar region is a serious problem mainly affecting sport and school horses during their daily under-saddle work. As the human population becomes heavier, the effect of rider bodyweight on equine welfare and performance requires further investigation. This study used infrared thermography to assess the effect of rider:horse bodyweight ratio on the horse’s thoracolumbar region by introducing advanced digital image processing. Twelve horses during regular work were ridden by each of six riders assigned to light (L), moderate (M), and heavy (H) groups. Thermal images of the back region were taken before and after standard exercise and underwent conventional analysis and texture analysis where the thermal images were separated into red, green, and blue components. Four areas of the horse’s thoracolumbar region were annotated to represent the withers area, the thoracic spine area, and the left and right areas of back muscles. Among 372 returned features, 75 texture features differed between bodyweight ratio groups, whereas the conventional thermal features did not. Contrary to conventional thermal features, the consistent measurable differences in texture features were evidenced predominantly in the red component of thermal images when the texture heterogeneity measures, such as InvDefMom, SumEntrp, Entropy, DifVarnc, and DifEntrp, were considered.Appropriate matching of rider–horse sizes is becoming an increasingly important issue of riding horses’ care, as the human population becomes heavier. Recently, infrared thermography (IRT) was considered to be effective in differing the effect of 10.6% and 21.3% of the rider:horse bodyweight ratio, but not 10.1% and 15.3%. As IRT images contain many pixels reflecting the complexity of the body’s surface, the pixel relations were assessed by image texture analysis using histogram statistics (HS), gray-level run-length matrix (GLRLM), and gray level co-occurrence matrix (GLCM) approaches. The study aimed to determine differences in texture features of thermal images under the impact of 10–12%, >12 ≤15%, >15 <18% rider:horse bodyweight ratios, respectively. Twelve horses were ridden by each of six riders assigned to light (L), moderate (M), and heavy (H) groups. Thermal images were taken pre- and post-standard exercise and underwent conventional and texture analysis. Texture analysis required image decomposition into red, green, and blue components. Among 372 returned features, 95 HS features, 48 GLRLM features, and 96 GLCH features differed dependent on exercise; whereas 29 HS features, 16 GLRLM features, and 30 GLCH features differed dependent on bodyweight ratio. Contrary to conventional thermal features, the texture heterogeneity measures, InvDefMom, SumEntrp, Entropy, DifVarnc, and DifEntrp, expressed consistent measurable differences when the red component was considered.

Non-Destructive Egg Fertility Detection in Incubation Using SVM Classifier Based on GLCM Parameters

The research presented in this paper aims at egg fertility detection during incubation based on the presence of the embryo. To obtain an optimal detection method that does not adversely affect the incubation process, the presented approach uses computer technology to analyze the images obtained from the egg candling process, and to obtain information about the presence of an egg embryo. This study applies the Support Vector Machine (SVM) classifier method using the second-order statistical feature extraction input to detect the chicken egg's fertility. The feature extraction is based on the Gray-Level Co-occurrence Matrix (GLCM) approach with 6 parameters: Energy (En), Contrast (Ct), Entropy (Et), Variance (V), Correlation (Cr), and Homogeneity (H). This study develops a manual detection process that takes a long time and improves the research accuracy of the backpropagation method. The dataset used consisted of 100 images of chicken eggs, including 50 images for each type: fertile and infertile. The preprocessing of the images included cropping, grayscaling, and image enhancement using CLAHE (Contrast Limited Adaptive Histogram Equalization) and HE (Histogram Equalization) methods. Such process can improve the image to get its GLCM parameters. The extracted GLCM parameters are input to the egg fertility detection process performed by the SVM classifier-based method. The presented SVM-GLCM approach was able to detect fertile and infertile eggs with a success rate of 98.20%, which was an improvement over the previous research. This research can be a reference for implementing the detection of chicken egg fertility in the incubation machine to obtain optimal hatching results.

Meta-analysis of the factor structure of the Brief Symptom Inventory (BSI-18) using an aggregated co-occurrence matrix approach

Purpose The Brief Symptom Inventory-18 (BSI-18) is a tool used to measure clinically relevant psychological symptoms to support clinical decision-making at intake and during the course of treatment in various settings. The BSI-18 has frequently been evaluated for construct validity via analysis of its structure. However, these studies showed mixed results of the factor solutions and no consensus on the dimensionality. Therefore, the purpose of this paper is to synthesize the empirical findings about the factor structure to reach an overall conclusion about the factor structure of the BSI-18. Design/methodology/approach A meta-analysis of factor analysis results using an aggregated co-occurrence matrix approach was conducted to synthesize the factor structure. The item factor loading information from seven published studies is gathered, combined and summarized to conclude the factor structure of the instrument. Multidimensional scaling (MDS) was used to quantify the similarity between the underlying factor structures of BSI-18 from different empirical articles. Findings The perceptual map from MDS-found items was clustered into three distinctive factors matching the original intent. The findings highlight the consistency of the BSI-18’s factor structure. However, the findings should be used with caution owing to the small sample size and conclusions made from visual representation. Originality/value This original study contributes to research in the provision of empirically tested measures that take a focus on factor analysis and the use of meta-analysis technique to account for an understanding of the factor structure.

Copy Move Forgery Detection Through Differential Excitation Component-Based Texture Features

Copy-move forgery (CMF) is an established process to copy an image segment and pastes it within the same image to hide or duplicate a portion of the image. Several CMF detection techniques are available; however, better detection accuracy with low feature vector is always substantial. For this, differential excitation component (DEC) of Weber Law descriptor in combination with the gray level co-occurrence matrix (GLCM) approach of texture feature extraction for CMFD is proposed. GLCM Texture features are computed in four directions on DEC and this acts as a feature vector for support vector machine classifier. These texture features are more distinguishable and it is validated through other two proposed methods based on discrete wavelet transform-GLCM (DWT-GLCM) and GLCM. Experimentation is carried out on CoMoFoD and CASIA databases to validate the efficacy of proposed methods. Proposed methods exhibit resilience against many post-processing attacks. Comparative analysis with existing methods shows the superiority of the proposed method (DEC-GLCM) with regard to detection accuracy.

Abstract P1-02-08: Whole breast tissue stiffness and mass characterization by ultrasound tomography

Abstract PURPOSE. Ultrasound tomography (UST) using SoftVue (Delphinus Medical Technologies, Inc.) has the unique ability to provide quantitative whole breast tissue stiffness, including localized measurements on masses. Conversely, handheld ultrasound (HHUS) only provides localized diagnostic information of tissue stiffness, or elasticity. Screening requires global assessment of tissue properties for which HHUS is not suitable, while automated breast ultrasound does not measure stiffness. This study is the first to evaluate imaging of tissue stiffness by SoftVue for common breast masses. METHOD AND MATERIALS. Patients with findings on mammography during the time period of January 2017 to November 2018, were scanned with SoftVue. Patients were selected on the basis of having dense breasts and having either benign or malignant breast masses. All women received standard breast imaging evaluation prior to biopsy. Pathology and/or radiology reports were used as the ground truth for verifying lesion type, which included 195 masses &amp;lt;1.5cm in size, (41 cancers, 79 fibroadenomas, 65 cysts and 10 other benign findings). Lesion localization and UST assessments were provided by a board-certified breast radiologist. UST stiffness measurements by SoftVue extracted information on the tissue bulk modulus which was then converted to an index of relative tissue stiffness (from 0 = very soft to 1 = extremely stiff). Additionally, the mean homogeneity of the stiffness was calculated for each mass using the Gray-Level Co-Occurrence Matrix (GLCM) approach. RESULTS. SoftVue demonstrated the ability to measure tissue stiffness throughout the breast and to characterize mass stiffness in all 195 patients. Table 1 lists the average stiffness index for each type of mass. Cysts, fibroadenomas and cancers were found to have mean stiffness indices of (0.10; 95% CI: 0.05 to 0.30), (0.35; 0.25 to 0.77) and (0.60; 0.41 to 1.00) respectively (p&amp;lt;0.001). The mean homogeneity of stiffness (Table 1), showed less overlap in variability than mean stiffness with values of (0.83; 0.72 to 0.95), (0.77: 0.65 to 0.86) and (0.68; 0.51 to 0.87), respectively (p&amp;lt;0.001). DISCUSSION. Masses were characterized using mean stiffness and mean homogeneity of stiffness. Both measures were able to separate the populations of the three types of masses, but the homogeneity texture parameter showed less overlap between benign and malignant masses. Further radiomics analyses of texture features will assure inclusion in a future CAD tool for improved diagnostic performance. During dense breast screening by SoftVue, whole breast tissue stiffness improves cancer conspicuity throughout a breast volume for initial detection during screening, while mass characterization on the basis of stiffness may improve screening specificity, which is not possible with current ultrasound. CONCLUSION. Measuring tissue stiffness throughout the whole breast is not currently available clinically. The study demonstrates that stiffness characterization of lesions derived from whole breast stiffness imaging with UST SoftVue is feasible for future screening of women with dense breasts. Using SoftVue stiffness has the potential to reduce call backs and biopsies, in combination with other parameters, to improve specificity. Table 1Type of MassStiffness index valueStandard deviation95% CIMean HomogeneityStandard Deviation95% CICyst0.100.200.05-0.300.830.050.73 - 0.91FB0.350.240.25-0.770.770.060.65 - 0.85Ca0.610.190.41-1.000.660.090.52 - 0.79 Citation Format: Neb Duric, Peter J Littrup, Cuiping Li, Rachel Brem. Whole breast tissue stiffness and mass characterization by ultrasound tomography [abstract]. In: Proceedings of the 2019 San Antonio Breast Cancer Symposium; 2019 Dec 10-14; San Antonio, TX. Philadelphia (PA): AACR; Cancer Res 2020;80(4 Suppl):Abstract nr P1-02-08.

Recent Deforestation Pattern Changes (2000–2017) in the Central Carpathians: A Gray-Level Co-Occurrence Matrix and Fractal Analysis Approach

The paper explores the distribution of tree cover and deforested areas in the Central Carpathians in the central-east part of Romania, in the context of the anthropogenic forest disturbances and sustainable forest management. The study aims to evaluate the spatiotemporal changes in deforested areas due to human pressure in the Carpathian Mountains, a sensitive biodiverse European ecosystem. We used an analysis of satellite imagery with Landsat-7 Enhanced Thematic Mapper Plus (Landsat-7 ETM+) from the University of Maryland (UMD) Global Forest Change (GFC) dataset. The workflow started with the determination of tree cover and deforested areas from 2000–2017, with an overall accuracy of 97%. For the monitoring of forest dynamics, a Gray-Level Co-occurrence Matrix analysis (Entropy) and fractal analysis (Fractal Fragmentation-Compaction Index and Tug-of-War Lacunarity) were utilized. The increased fragmentation of tree cover (annually 2000–2017) was demonstrated by the highest values of the Fractal Fragmentation-Compaction Index, a measure of the degree of disorder (Entropy) and heterogeneity (Lacunarity). The principal outcome of the research reveals the dynamics of disturbance of tree cover and deforested areas expressed by the textural and fractal analysis. The results obtained can be used in the future development and adaptation of forestry management policies to ensure sustainable management of exploited forest areas.

Improvement of Moderate Resolution Land Use and Land Cover Classification by Introducing Adjacent Region Features

Landsat-like moderate resolution remote sensing images are widely used in land use and land cover (LULC) classification. Limited by coarser resolutions, most of the traditional LULC classifications that are based on moderate resolution remote sensing images focus on the spectral features of a single pixel. Inspired by the spatial evaluation methods in landscape ecology, this study proposed a new method to extract neighborhood characteristics around a pixel for moderate resolution images. 3 landscape-metric-like indexes, i.e., mean index, standard deviation index, and distance weighted value index, were defined as adjacent region features to include the surrounding environmental characteristics. The effects of the adjacent region features and the different feature set configurations on improving the LULC classification were evaluated by a series of well-controlled LULC classification experiments using K nearest neighbor (KNN) and support vector machine (SVM) classifiers on a Landsat 8 Operational Land Imager (OLI) image. When the adjacent region features were added, the overall accuracies of both the classifiers were higher than when only spectral features were used. For the KNN and SVM classifiers that used only spectral features, the overall accuracies of the LULC classification were 85.45% and 88.87%, respectively, and the accuracies were improved to 94.52% and 96.97%. The classification accuracies of all the LULC types improved. Highly heterogeneous LULC types that are easily misclassified achieved greater improvements. As comparisons, the grey-level co-occurrence matrix (GLCM) and convolutional neural network (CNN) approaches were also implemented on the same dataset. The results revealed that the new method outperformed GLCM and CNN approaches and can significantly improve the classification performance that is based on moderate resolution data.

Image processing based rice plant leaves diseases in Thanjavur, Tamilnadu

India is a highly populated agricultural country which has land area of 60.3% for agriculture purpose. The production of rice plant is decreased up to 20–30% because of various diseases. The most frequent diseases occurred in paddy leaves are leaf blast, leaf blight, false smut, brown spot and leaf streak. This paper mainly considers a method to detect the leaf diseases automatically using image processing techniques. To determine these diseases, the proposed methodology involves image Acquisition, image pre-processing, segmentation and classification of paddy leaf disease. In this proposed system, the features are extracted using hybrid method of discrete wavelet transform, scale invariant feature transform and gray scale co-occurrence matrix approach. Finally, the extracted features are given to various classifiers such as K nearest neighborhood neural network, back propagation neural network, Naive Bayesian and multiclass SVM to categorize disease and non-disease plants. Many classification techniques are examined to classify the leaf disease. In experimental result, the proposed work is implemented in MATLAB software and performance of this work is measured in terms of accuracy. It is observed that multi class SVM provides the better accuracy of 98.63% when compared to other classifiers.

Assessment of Tear Film Using Videokeratoscopy Based on Fractal Dimension.

The proposed automated approach for estimating the quality of the tear film closes the gap between the manual and automated assessment, translating the high-speed videokeratoscopy technology from scientific laboratories to a clinical practice. To develop and test a new method for characterizing Tear Film Surface Quality with high-speed videokeratoscopy utilizing a fractal dimension approach. The regularity of the reflected pattern in high-speed videokeratoscopy (E300; Medmont) depends on tear film stability. Thus, determining tear film stability can be addressed by estimating the fractal dimension of the reflected pattern. The method is tested on 39 normal subjects. The results of the fractal dimension approach are compared with those obtained using previously proposed automated method, based on a gray-level co-occurrence matrix approach, and with subjective results obtained by two operators that were assessing the video recordings in ideal conditions. Fractal dimension method was less affected by eye movements and changes in the videokeratoscopic image background than gray-level co-occurrence matrix method. Median difference of the noninvasive break-up time between manual and automated methods was 0.03 s (IQR = 4.47 s) and 0.0 s (IQR = 2.22 s) for gray-level co-occurrence matrix and fractal dimension approaches, respectively. Correlation coefficient with manual noninvasive break-up time was r = 0.86 (P < 0.001) for gray-level co-occurrence matrix approach, and r = 0.82 (P < 0.001) for fractal dimension approach. Significant statistical difference was found between noninvasive break-up measurements of manual and gray-level co-occurrence matrix method (P = 0.008). The proposed method has the potential to characterize tear film dynamics in more detail compared to previous methods based on high-speed videokeratoscopy. It showed good correlation with manual assessment of tear film.

Mean of Correlation Method for Optimization of Affective States Detection in Children

At the moment, most of the studies on classification of affective states for children focus on visual observations and physiological cues, where all data collection for measuring physiological signals are contact-based and invasive. With the requirement of having the measuring device attached to the body approach, distraction of the subject normally masks the true affective states of the subject due to discomfort. In this paper, a non-invasive, contactless, and less distraction method is proposed to measure the physiological cues of the subjects using their thermal imprints from frontal face imaging. A thermal image camera is used to identify basic affective states, where it is a contactless and seamless device with ability to read the radiated thermal imprint of the subjects’ facial skin temperature. This paper proposes an effective algorithm of texture analysis based on novel technique using Gray Level Co-occurrence Matrix approach to be applied so as to identify blood-flow region. The cues from the first order statistics are computed in the identified blood flow region and concatenated along with second order statistics cues, in order to construct feature vectors to administer the vital and distinguishable characteristic pattern between affective states in thermal images. Result from the fine k-NN classifier obtained promises the efficacy of the proposed approach to be applied in our future work in human–robot interaction for autistic children learning and training.

Textural pattern classification for oral squamous cell carcinoma.

Despite being an area of cancer with highest worldwide incidence, oral cancer yet remains to be widely researched. Studies on computer-aided analysis of pathological slides of oral cancer contribute a lot to the diagnosis and treatment of the disease. Some researches in this direction have been carried out on oral submucous fibrosis. In this work an approach for analysing abnormality based on textural features present in squamous cell carcinoma histological slides have been considered. Histogram and grey-level co-occurrence matrix approaches for extraction of textural features from biopsy images with normal and malignant cells are used here. Further, we have used linear support vector machine classifier for automated diagnosis of the oral cancer, which gives 100% accuracy.

Texture analysis of parasitological liver fibrosis images.

Liver fibrosis accurate staging is vital to define the state of the Schistosomiasis disease for further treatment. The present work analyzed the microscopic liver images to identify and to differentiate between healthy, cellular, fibrocellular, and fibrous liver pathologies by proposing a fast, robust, and highly discriminative method based on texture analysis. The multiclass classification based on the "one-versus- all" method that built a voting rule approach to classify the liver images based on the liver state. Specifically, quantitative parameters, such as the anisotropy and laminarity are proposed based on the relative orientation of the pixel pairs in a global and local coherence of gradient vectors approach. Analysis of the tissue texture data using both gradient vector and gradient angle co-occurrence matrix approaches facilitated more definitive identification of the abnormal tissue. The experimental results established that the local anisotropy based texture measures are appropriated for the microtexture analysis in order to discriminate between pathologies. Macrotexture description using the global features provided only integral anisotropy coefficient that has a confidence level similar to those provided by the local feature.

Dual-polarimetric C-band SAR data for land use/land cover classification by incorporating textural information

The work presented here showed a comprehensive evaluation of dual-polarimetric RISAT-1 data for land use/land cover (LULC) classification. The textural images were extracted with the help of gray-level co-occurrence matrix approach. Analysis of inter-class separability using transformed divergence method was performed to recognize the potential textural images. The best combination of textural images was also identified on the basis of standard deviation of preferred textural images and correlation coefficients. The maximum likelihood classifier-based classification results for different scenarios were compared. Furthermore, various classification algorithms, maximum likelihood classifier (MLC), artificial neural network (ANN), random forest (RF) and support vector machine (SVM), were performed on the best identified scenario in order to observe the most suitable algorithm for LULC classification. The combination of radiometric and their related textural images was found improving the overall classification accuracy than individual datasets. The highest overall classification accuracy was found using SVM (88.97%) followed by RF (88.45%), ANN (83.65%) and MLC (78.18%).

Extracted magnetic resonance texture features discriminate between phenotypes and are associated with overall survival in glioblastoma multiforme patients.

GBM is a markedly heterogeneous brain tumor consisting of three main volumetric phenotypes identifiable on magnetic resonance imaging: necrosis (vN), active tumor (vAT), and edema/invasion (vE). The goal of this study is to identify the three glioblastoma multiforme (GBM) phenotypes using a texture-based gray-level co-occurrence matrix (GLCM) approach and determine whether the texture features of phenotypes are related to patient survival. MR imaging data in 40 GBM patients were analyzed. Phenotypes vN, vAT, and vE were segmented in a preprocessing step using 3D Slicer for rigid registration by T1-weighted imaging and corresponding fluid attenuation inversion recovery images. The GBM phenotypes were segmented using 3D Slicer tools. Texture features were extracted from GLCM of GBM phenotypes. Thereafter, Kruskal-Wallis test was employed to select the significant features. Robust predictive GBM features were identified and underwent numerous classifier analyses to distinguish phenotypes. Kaplan-Meier analysis was also performed to determine the relationship, if any, between phenotype texture features and survival rate. The simulation results showed that the 22 texture features were significant with p value <0.05. GBM phenotype discrimination based on texture features showed the best accuracy, sensitivity, and specificity of 79.31, 91.67, and 98.75%, respectively. Three texture features derived from active tumor parts: difference entropy, information measure of correlation, and inverse difference were statistically significant in the prediction of survival, with log-rank p values of 0.001, 0.001, and 0.008, respectively. Among 22 features examined, three texture features have the ability to predict overall survival for GBM patients demonstrating the utility of GLCM analyses in both the diagnosis and prognosis of this patient population.