Statistical Texture Features Research Articles

Texture analysis of apparent diffusion coefficient maps for treatment response assessment in prostate cancer bone metastases—A pilot study

ObjectiveTo evaluate whole-lesion volumetric texture analysis of apparent diffusion coefficient (ADC) maps for assessing treatment response in prostate cancer bone metastases. Materials and methodsTexture analysis is performed in 12 treatment-naïve patients with 34 metastases before treatment and at one, two, and three months after the initiation of androgen deprivation therapy. Four first-order and 19 second-order statistical texture features are computed on the ADC maps in each lesion at every time point. Repeatability, inter-patient variability, and changes in the feature values under therapy are investigated. Spearman rank’s correlation coefficients are calculated across time to demonstrate the relationship between the texture features and the serum prostate specific antigen (PSA) levels. ResultsWith few exceptions, the texture features exhibited moderate to high precision. At the same time, Friedman’s tests revealed that all first-order and second-order statistical texture features changed significantly in response to therapy. Thereby, the majority of texture features showed significant changes in their values at all post-treatment time points relative to baseline. Bivariate analysis detected significant correlations between the great majority of texture features and the serum PSA levels. Thereby, three first-order and six second-order statistical features showed strong correlations with the serum PSA levels across time. ConclusionThe findings in the present work indicate that whole-tumor volumetric texture analysis may be utilized for response assessment in prostate cancer bone metastases. The approach may be used as a complementary measure for treatment monitoring in conjunction with averaged ADC values.

Pre-treatment magnetic resonance-based texture features as potential imaging biomarkers for predicting event free survival in anal cancer treated by chemoradiotherapy.

To assess regular MRI findings and tumour texture features on pre-CRT imaging as potential predictive factors of event-free survival (disease progression or death) after chemoradiotherapy (CRT) for anal squamous cell carcinoma (ASCC) without metastasis. We retrospectively included 28 patients treated by CRT for pathologically proven ASCC with a pre-CRT MRI. Texture analysis was carried out with axial T2W images by delineating a 3D region of interest around the entire tumour volume. First-order analysis by quantification of the histogram was carried out. Second-order statistical texture features were derived from the calculation of the grey-level co-occurrence matrix using a distance of 1 (d1), 2 (d2) and 5 (d5) pixels. Prognostic factors were assessed by Cox regression and performance of the model by the Harrell C-index. Eight tumour progressions led to six tumour-specific deaths. After adjusting for age, gender and tumour grade, skewness (HR = 0.131, 95% CI = 0-0.447, p = 0.005) and cluster shade_d1 (HR = 0.601, 95% CI = 0-0.861, p = 0.027) were associated with event occurrence. The corresponding Harrell C-indices were 0.846, 95% CI = 0.697-0.993, and 0.851, 95% CI = 0.708-0.994. ASCC MR texture analysis provides prognostic factors of event occurrence and requires additional studies to assess its potential in an "individual dose" strategy for ASCC chemoradiation therapy. • MR texture features help to identify tumours with high progression risk. • Texture feature maps help to identify intra-tumoral heterogeneity. • Texture features are a better prognostic factor than regular MR findings.

Automatic segmentation and classification of olive fruits batches based on discrete wavelet transform and visual perceptual texture features

The quality of olive fruit and its virgin olive oil is a main concern for consumers and fruit industrial companies. The effectiveness and fast detection of olive’s skin defects is the most decisive factor in determining its quality. It is necessary to design and implement image processing tools for segmentation and correct classification of the different fresh incoming olive batches. In this paper, we propose a new automatic image segmentation algorithm, based on discrete wavelets transform. The aim of the segmentation algorithm is to discriminate between olives and the background with the challenge of irregular and dispersive lesion borders, low contrast, artifacts in the olive fruit and variety of colors within the interest region. The second part of our work proposes a scheme for olive fruit classification. The classifier first identifies the olive fruit color and then, based upon discrete wavelets transform and Tamura statistical texture features, the healthy olive fruit is distinguished from the damaged one. The new texture feature vector is, then, compared with the robust Local Binary Pattern feature vector. The simplicity of our segmentation and classification algorithms makes them appropriate for designing a productive and profitable computer vision machine.

Effective Statistical Texture Features for Segmenting Mammogram Images Based on M-ARKFCM with Multi-ROI Segmentation Method

Effective Statistical Texture Features for Segmenting Mammogram Images Based on M-ARKFCM with Multi-ROI Segmentation Method

Hybrid ANN optimized artificial fish swarm algorithm based classifier for classification of suspicious lesions in breast DCE-MRI

Abstract Automatic mass or lesion classification systems are developed to aid in distinguishing between malignant and benign lesions present in the breast DCE-MR images, the systems need to improve both the sensitivity and specificity of DCE-MR image interpretation in order to be successful for clinical use. A new classifier (a set of features together with a classification method) based on artificial neural networks trained using artificial fish swarm optimization (AFSO) algorithm is proposed in this paper. The basic idea behind the proposed classifier is to use AFSO algorithm for searching the best combination of synaptic weights for the neural network. An optimal set of features based on the statistical textural features is presented. The investigational outcomes of the proposed suspicious lesion classifier algorithm therefore confirm that the resulting classifier performs better than other such classifiers reported in the literature. Therefore this classifier demonstrates that the improvement in both the sensitivity and specificity are possible through automated image analysis.

GSA Based Classification of Lung Nodules in CT Images

Medical Image processing techniques are extensively used in several medical fields for former detection of diseases. Computer Aided Diagnosis (CAD) systems give way to a great pact of information to analyze and evaluate the accurate structures at short time period. Image quality with detailed edges is the foundation factors of this research, where low pre-processing technique is used for filtering. The adaptive median filter performs spatial processing to preserve detailed edges and smoothen non-impulsive noises. Image segmentation is done using edge detection techniques in lung CT images for Obtaining the Region of Interest (ROI), which is a prior step for feature extraction and selection. Law of universal gravity is used For detecting the differential structures using a new edge detection algorithm, that is Gravitational search algorithm. In this approach the edges are detected by the local variation of intensity values and the movement of agents is computed using Gravitational Search Algorithm (GSA).It gives fast and accurate framework for feature extraction and feature selection. For Feature Extraction Gray Level Co-occurrence Matrix (GLCM) is applicable in extracting statistical texture feature for motion estimation in CT (Computed Tomography) images. In Feature selection Optimal set of Features are selected through classifiers to overcome the computational time and memory exhaustion.

A Fast and Efficient Image Indexing and Search System based on Color and Texture Features

Content-Based Image Retrieval (CBIR) allows to automatically extracting target images according to objective visual contents of the image itself. Representation of visual features and similarity match are important issues in CBIR. Color, texture and shape information have been the primitive image descriptors in content-based image retrieval systems. This paper presents a fast and efficient image indexing and search system based on color and texture features. The color features are represented by combines 2-D histogram and statistical moments and texture features are represented by combines the direction measure and a gray level co-occurrence matrix (GLCM). The detailed experimental analysis is carried out using precision and recall ondataset Wang. The time analysis is also performed to compare processing speeds of the proposed method with the existing similar best. The experimental results demonstrated that proposed method achieved a better image recognition, and the accuracy of classification based on this method has been significantly improved. The performance is measured in terms of recall and precision; also the obtained performances are compared with several state-of-the-art algorithms and showed that our algorithm is simple, fast, and efficient in terms of results and memory. Keywords: Co-occurrence Matrix, Direction Measure, 2-D Histogram, Statistical Moments, CBIR, GLCM

A NOVEL APPROACH FOR THE EXTRACTION AND CLASSIFICATION OF TUMOR IN MR IMAGES OF THE BRAIN VIA PRINCIPLE COMPONENT ANALYSIS AND KERNEL SUPPORT VECTOR MACHINE

Medical imaging plays an important role in the medical field. In present time there are various computerized methods for medical imaging to diagnose the inner portion of human body. Brain tumor detection is an important application in recent days. In this paper, various methods have been used for brain tumor detection and classification taking magnetic resonance images as input. For tumor classification, we had done experimentation with 50 MRI images taken from “figshare brain data set”. We propose an efficient method for brain tumor classification to classify cancerous and noncancerous tumor. The proposed method has three major steps 1.) Feature extraction 2) Feature reduction and 3) Classification. The present approach extracts the statistical texture features using 2D Discrete Wavelet transformation (Daubechies) and GLCM. PCA (principle Component Analysis) is used for feature reduction. We create a training data set that was carried out with 50 MRI images and applied SVM classifier to classify the tumor whether it is Benign and Malignant and evaluate the performance by Kernel based SVM.

A radiomics evaluation of 2D and 3D MRI texture features to classify brain metastases from lung cancer and melanoma.

Brain metastases are occasionally detected before diagnosing their primary site of origin. In these cases, simple visual examination of medical images of the metastases is not enough to identify the primary cancer, so an extensive evaluation is needed. To avoid this procedure, a radiomics approach on magnetic resonance (MR) images of the metastatic lesions is proposed to classify two of the most frequent origins (lung cancer and melanoma). In this study, 50 T1-weighted MR images of brain metastases from 30 patients were analyzed: 27 of lung cancer and 23 of melanoma origin. A total of 43 statistical texture features were extracted from the segmented lesions in 2D and 3D. Five predictive models were evaluated using a nested cross-validation scheme. The best classification results were achieved using 3D texture features for all the models, obtaining an average AUC > 0.9 in all cases and an AUC = 0.947 ± 0.067 when using the best model (naïve Bayes).

Primary Rectal Cancer: Repeatability of Global and Local-Regional MR Imaging Texture Features.

PurposeTo assess the day-to-day repeatability of global and local-regional magnetic resonance (MR) imaging texture features derived from primary rectal cancer.Materials and MethodsAfter ethical approval and patient informed consent were obtained, two pretreatment T2-weighted axial MR imaging studies performed prospectively with the same imaging unit on 2 consecutive days in 14 patients with rectal cancer (11 men [mean age, 61.7 years], three women [mean age, 70.0 years]) were analyzed to extract (a) global first-order statistical histogram and model-based fractal features reflecting the whole-tumor voxel intensity histogram distribution and repeating patterns, respectively, without spatial information and (b) local-regional second-order and high-order statistical texture features reflecting the intensity and spatial interrelationships between adjacent in-plane or multiplanar voxels or regions, respectively. Repeatability was assessed for 46 texture features, and mean difference, 95% limits of agreement, within-subject coefficient of variation (wCV), and repeatability coefficient (r) were recorded.ResultsRepeatability was better for global parameters than for most local-regional parameters. In particular, histogram mean, median, and entropy, fractal dimension mean and standard deviation, and second-order entropy, homogeneity, difference entropy, and inverse difference moment demonstrated good repeatability, with narrow limits of agreement and wCVs of 10% or lower. Repeatability was poorest for the following high-order gray-level run-length (GLRL) gray-level zone size matrix (GLZSM) and neighborhood gray-tone difference matrix (NGTDM) parameters: GLRL intensity variability, GLZSM short-zone emphasis, GLZSM intensity nonuniformity, GLZSM intensity variability, GLZSM size zone variability, and NGTDM complexity, demonstrating wider agreement limits and wCVs of 50% or greater.ConclusionMR imaging repeatability is better for global texture parameters than for local-regional texture parameters, indicating that global texture parameters should be sufficiently robust for clinical practice.Online supplemental material is available for this article.

Static Signature Verification Based on Texture Analysis Using Support Vector Machine

Off-line hand written signature verification performs at the global level of image. It processes the gray level information in the image using statistical texture features. The textures and co-occurrence matrix are analyzed for features extraction. A first order histogram is also processed to reduce different writing ink pens used by signers. Samples of signature are trained with SVM model where random and skilled forgeries have been used for testing. Experimental results are performed on two databases: MCYT-75 and GPDS Synthetic Signature Corpus.

MRI-aided texture analyses of compressed meat products

Viscoelastic properties of food products can already be assessed by conventional (non-imaging) methods, such as compression-recovery creep (CRC), texture property analysis (TPA) and stress-relaxation (SR) methods. In the study, an alternative to these methods based on MRI of samples in a compression cell is proposed. Different commercial meat products were subjected to two different compression protocols. The first (protocol P1) was designed to mimic a CRC experiment and the second (protocol P2) was based on application of three different constant pressures (0, 160, 400 kPa). The samples were imaged either by consecutive 1D MR intensity profiles (protocol P1) or by 3D T2 mapping (protocol P2). Compression-induced samples changes were characterized by creep compliance obtained from the 1D profiles, while the T2 maps were analyzed by using first- and second-order statistical texture feature analyses. The approach enabled spatially-resolved assessment of viscoelastic properties and compression-induced structural changes of the examined samples.

An extensive analysis of various texture feature extractors to detect Diabetes Mellitus using facial specific regions

Introduction: Researchers have recently discovered that Diabetes Mellitus can be detected through non-invasive computerized method. However, the focus has been on facial block color features. In this paper, we extensively study the effects of texture features extracted from facial specific regions at detecting Diabetes Mellitus using eight texture extractors.Materials and methods: The eight methods are from four texture feature families: (1) statistical texture feature family: Image Gray-scale Histogram, Gray-level Co-occurance Matrix, and Local Binary Pattern, (2) structural texture feature family: Voronoi Tessellation, (3) signal processing based texture feature family: Gaussian, Steerable, and Gabor filters, and (4) model based texture feature family: Markov Random Field. In order to determine the most appropriate extractor with optimal parameter(s), various parameter(s) of each extractor are experimented. For each extractor, the same dataset (284 Diabetes Mellitus and 231 Healthy samples), classifiers (k-Nearest Neighbors and Support Vector Machines), and validation method (10-fold cross validation) are used.Results: According to the experiments, the first and third families achieved a better outcome at detecting Diabetes Mellitus than the other two.Conclusions: The best texture feature extractor for Diabetes Mellitus detection is the Image Gray-scale Histogram with bin number=256, obtaining an accuracy of 99.02%, a sensitivity of 99.64%, and a specificity of 98.26% by using SVM.

Computer Analysis of Knee by Magnetic Resonance Imaging Data

The examination of knee cartilage degradation by magnetic resonance imaging (MRI) data is essential due to the reduction in physical activity of the population and a rising number of patients with osteoarthritis(OA). The main aim of this publication is to show a new approach for analyzing knee tissue by MRI data. The present paper investigates the problems of relaxation times calculation, medical image segmentation and statistical texture features calculation. Proposed paper describes an approach for medical image segmentation, relaxation times calculation and statistical texture features calculation. An important aspect of analysis of articular cartilage relaxation times changing is illustrated in the experimental part. The experimental part of the publication also describes the dependence between organic structure and relaxation times. The proposed approach the obtained results can be useful for early OA diagnostics.

Abrupt skin lesion border cutoff measurement for malignancy detection in dermoscopy images.

BackgroundAutomated skin lesion border examination and analysis techniques have become an important field of research for distinguishing malignant pigmented lesions from benign lesions. An abrupt pigment pattern cutoff at the periphery of a skin lesion is one of the most important dermoscopic features for detection of neoplastic behavior. In current clinical setting, the lesion is divided into a virtual pie with eight sections. Each section is examined by a dermatologist for abrupt cutoff and scored accordingly, which can be tedious and subjective.MethodsThis study introduces a novel approach to objectively quantify abruptness of pigment patterns along the lesion periphery. In the proposed approach, first, the skin lesion border is detected by the density based lesion border detection method. Second, the detected border is gradually scaled through vector operations. Then, along gradually scaled borders, pigment pattern homogeneities are calculated at different scales. Through this process, statistical texture features are extracted. Moreover, different color spaces are examined for the efficacy of texture analysis.ResultsThe proposed method has been tested and validated on 100 (31 melanoma, 69 benign) dermoscopy images. Analyzed results indicate that proposed method is efficient on malignancy detection. More specifically, we obtained specificity of 0.96 and sensitivity of 0.86 for malignancy detection in a certain color space. The F-measure, harmonic mean of recall and precision, of the framework is reported as 0.87.ConclusionsThe use of texture homogeneity along the periphery of the lesion border is an effective method to detect malignancy of the skin lesion in dermoscopy images. Among different color spaces tested, RGB color space’s blue color channel is the most informative color channel to detect malignancy for skin lesions. That is followed by YCbCr color spaces Cr channel, and Cr is closely followed by the green color channel of RGB color space.

Designing a Feature Vector for Statistical Texture Analysis of Mandibular Bone

Objectives: This paper develops an algorithm to generate automatically, a feature vector using various statistical texture features of trabecular mandible from digital Orthopantomogram (OPG). These statistical features are computed using Gray Level Co-occurrence Matrices (GLCM) of mandible structure. Analysis: For this paper, region of interest is trabecular mandible bone present in lower jaw. Mandible Segmented from OPG is taken as input to the algorithm. GLCM of this mandible is calculated at four angles viz., 00, 450, 900 and 1350 and for two gray scale intensities viz., 128 and 256. Various texture features are calculated from each of these GLCMs. These statistical features are compared and analyzed. Findings: 100 digital OPGs are used for analysis of statistical texture features. Four texture features contrast, viz., correlation, energy, homogeneity are calculated for the four angles mentioned above. Improvement: Texture analysis is performed on various types of images since last 50 years. Locating systemic disease features (e.g., Osteoporosis) from OPG is an upcoming research area. In this area, it is observed that comparatively less literature is available which uses GLCM texture features. The algorithm proposed here devices a texture feature vector for mandible. Analysis of the features is also presented in this paper

Hybrid of Statistical and Spectral Texture Features for Vehicle Object Classification System

Objectives: To increase the performance of the classifier for the vehicle object among a mixed and highly texture background using hybrid feature extraction method without pre-processing. Methods/Analysis: Vehicle Object recognition system performance is based on the hybrid of feature vector extraction method and artificial neural network classifier without pre-processing. Every image is divided into single blocks size with 20x20 each. The feature vector is extracted from each single size block of the picture. Normalization is done for the extracted feature vector of the vehicle object in the image. These feature vectors are given as input to the neural network classifier for classification. The feed forward Back Propagation Neural Network (BPNN) algorithm is used to train and test the input feature vector by using Neural Network Classifier (NNC) for the vehicle classification. Findings: The idea of the proposed method is that combining the two different literatures namely statistical and spectral texture features without pre-processing for classification. This method is trained and tested with Illinois at Urbana-Champaign (UIUC) standard databases. UIUC database contains car and non-car images with mixed and highly textured background. The findings indicate that the selected input feature vector improves the classification accuracy rate compared to the previous literature. Also the hybrid features maximize the correct classification and minimize the wrong classification. The improved performance results 90.1% of quantitative evaluation is compared with different literature methods of similar work. Applications/Improvements: In different applications, the proposed method plays vital part in surveillance, security for vehicles, monitoring the traffic, etc.

Hybrid Approach to Extract Text in Natural Scene Images

Extraction from natural scene images has been done with various methodologies. Most of the existing systems mainly use color and edges for detecting the text. We propose a two stage hybrid text extraction approach by combining texture and CC-based information. Text in the image is detected and localized using first and second order statistical texture features. In the next stage CC extraction is used to segment candidate text components from the localized text region. Finally morphological operations and heuristic filters are used to filter out non text components. Experimental results show that the proposed approach detects, localizes and extracts text from natural scene images efficiently and also can handle variations in size, fonts and orientation.

Classification of degradation in oil-impregnated cellulose insulation using texture analysis of optical microscopy images

Oil-impregnated Kraft paper samples normally used for power transformer electrical insulation have been artificially aged thermally to produce a sample set with varying levels of insulation deterioration. The samples were aged in an oven at a temperature above the normal operating temperature of a power transformer.Digital images obtained from optical microscopy measurements on the paper samples have been analyzed using a texture analysis method which converts each image into a spatial gray level dependence matrix (SGLDM). The SGLDM contains information about the statistical variation of pixels gray-level intensities in an image and thereby information about the sample texture. Mathematical operators applied to the SGLDM have been used to extract 22 different statistical texture features for each sample image.Optical microscopy images of the thermally aged samples show that thermal deterioration of the insulation paper produces changes in morphology and physical structure. These changes are detectable by the statistical texture features extracted from the SGLDM texture analysis. Statistical classification is performed on the feature set to demonstrate that differentiation between oil-impregnated paper samples with different levels of thermal degradation is reliable with low error rates. Therefore, development of a practical method to assess condition of oil-impregnated paper insulation using optical microscopy and texture analysis is promising.

Feature Selection for Intelligent Firefighting Robot Classification of Fire, Smoke, and Thermal Reflections Using Thermal Infrared Images

Locating a fire inside of a structure that is not in the direct field of view of the robot has been researched for intelligent firefighting robots. By classifying fire, smoke, and their thermal reflections, firefighting robots can assess local conditions, decide a proper heading, and autonomously navigate toward a fire. Long-wavelength infrared camera images were used to capture the scene due to the camera’s ability to image through zero visibility smoke. This paper analyzes motion and statistical texture features acquired from thermal images to discover the suitable features for accurate classification. Bayesian classifier is implemented to probabilistically classify multiple classes, and a multiobjective genetic algorithm optimization is performed to investigate the appropriate combination of the features that have the lowest errors and the highest performance. The distributions of multiple feature combinations that have 6.70% or less error were analyzed and the best solution for the classification of fire and smoke was identified.