Computed Texture Features Research Articles

Evaluation of wound healing process based on texture image analysis

Wound healing rate remains an interesting and important issue, in which modern imaging techniques have not yet given a definitive answer. In order to guide better therapeutic interventions, a better understanding of the fundamental mechanisms driving tissue repair are required. The wound healing rate is primarily quantified by the rate of change of the wound’s surface area. The objective of this work is to establish a standardized and objective technique to assess the progress of wound healing in wounds appearing on patient’s feet, by means of texture image analysis. Image pre-processing, segmentation, texture and geometrical analysis together with visual expert’s evaluation were used to assess the wound healing process. A total of 77 digital images from 11 different subjects with foot wounds were taken every third day, for 21 days, by an inexpensive digital camera under different lighting conditions. The images were intensity normalized, and wounds were automatic segmented using a segmentation system based on snakes. From the segmented wounds, 56 different texture features and 4 different geometrical measures were extracted in order to identify features that quantify the rate of wound healing. Texture features that may indicate the progression of wound healing process were identified. More specifically, certain texture features increase (mean, contrast, roughness and radial sum), while some other texture features decrease (sum of squares variance, sum variance, sum average, entropy, coarseness, EE-laws texture energy measures and the Hurst coefficients for fractal dimension one and two analysis) with the progression of the wound healing process. These features were found to be significantly different at an observed time point during the wound healing process, when compared to previous different time points, and this could be used to indicate the rate of wound healing. No significant differences were found for all geometrical measures extracted from the wounds between different time points. Based on the results of this study, it is suggested that some texture features might be used to monitor the wound healing process, thus reducing the workload of experts, provide standardization, reduce costs, and improve the treatment quality for patients. The simplicity of the method also suggests that it may be a valuable tool in clinical wound evaluation. A larger scale study is needed to establish the application in clinical practice and for computing texture features and geometrical measures that may provide information for better and earlier differentiation of the wound healing process. Future work will incorporate additional texture features and geometrical measures for assessing the wound healing process in order to be used in the real clinical practice.

Computerized Analysis of Mammographic Parenchymal Patterns on a Large Clinical Dataset of Full-Field Digital Mammograms: Robustness Study with Two High-Risk Datasets

The purpose of this study was to demonstrate the robustness of our prior computerized texture analysis method for breast cancer risk assessment, which was developed initially on a limited dataset of screen-film mammograms. This current study investigated the robustness by (1) evaluating on a large clinical dataset, (2) using full-field digital mammograms (FFDM) as opposed to screen-film mammography, and (3) incorporating analyses over two types of high-risk patient sets, as well as patients at low risk for breast cancer. The evaluation included the analyses on the parenchymal patterns of women at high risk of developing of breast cancer, including both BRCA1/2 gene mutation carriers and unilateral cancer patients, and of women at low risk of developing breast cancer. A total of 456 cases, including 53 women with BRCA1/2 gene mutations, 75 women with unilateral cancer, and 328 low-risk women, were retrospectively collected under an institutional review board approved protocol. Regions-of-interest (ROIs), were manually selected from the central breast region immediately behind the nipple. These ROIs were subsequently used in computerized feature extraction to characterize the mammographic parenchymal patterns in the images. Receiver operating characteristic analysis was used to assess the performance of the computerized texture features in the task of distinguishing between high-risk and low-risk subjects. In a round robin evaluation on the FFDM dataset with Bayesian artificial neural network analysis, AUC values of 0.82 (95% confidence interval [0.75, 0.88]) and 0.73 (95% confidence interval [0.67, 0.78]) were obtained between BRCA1/2 gene mutation carriers and low-risk women, and between unilateral cancer and low-risk women, respectively. These results from computerized texture analysis on digital mammograms demonstrated that high-risk and low-risk women have different mammographic parenchymal patterns. On this large clinical dataset, we validated our methods for quantitative analyses of mammographic patterns on FFDM, statistically demonstrating again that women at high risk tend to have dense breasts with coarse and low-contrast texture patterns.

Sensory traits prediction in dry-cured hams from fresh product via MRI and lipid composition

The aim of this paper is to describe a methodology that can predict Iberian dry-cured ham sensory traits from raw material characteristics, lipid composition and Magnetic Resonance Imaging-based analysis, by using Multiple Linear Regression statistics. Thus, 18 sensory traits are tried to be defined from 10 fatty acids and 17 computational texture features. Dependence linearity within each group of independent variables is determined. Then, Multiple Linear Regression (MLR) is applied, obtaining allowable statistical coefficients (adjusted coefficient of determination, R 2 ¯ > 0.750 and p-value < 0.05) for five sensory traits defined from fatty acids (fat hardness, lean hardness, flavour intensity, brightness and juiciness), and four traits from computational texture features (marbling, odour intensity, flavour intensity and redness). Finally, prediction analysis is validated with a display of statistical data ( R 2 ¯ LOO and p-value LOO). Therefore, some sensory traits in Iberian dry-cured hams can be predicted from fatty acids and computational texture characteristics in fresh products.

Robust texture features for response monitoring of glioblastoma multiforme on T1-weighted and T2-FLAIR MR images: A preliminary investigation in terms of identification and segmentation

Image texture has recently attracted much attention in providing quantitative features that are unique to various different tissue types, in particular, in MR images of the brain. Such image features may be useful for tumor response quantification. As a first step, one needs to establish if these features are sensitive to different tissues of clinical relevance. Here, a novel method of texture analysis based on the Hartley transform has been investigated and applied to MR images of glioblastoma multiforme (GBM). Contrast-enhanced T1-weighted gradient-echo and T2-FLAIR spin-echo MR images of 27 GBM patients acquired prior to radiation therapy were available for analysis. Before computing texture features on these images, a novel image transformation was employed in the form of a power map computed from the localized Hartley transform of the image. Haralick statistical texture features were then computed based on the power map. This method was compared to the standard approach of obtaining texture features directly from the image. Twelve different features were computed on different resolution levels. On a regional resolution level, image texture features were identified that are able to correctly classify entire regions within T1-weighted and T2-FLAIR brain MR images of GBM patients into abnormal (containing contrast-enhancing GBM tumor) and brain tissue. Various metrics [area under the ROC curve (AUC), maximum accuracy, and Canberra distance] have been computed to quantify the usefulness of these features. On a local resolution level, it was investigated which of these features are able to provide a voxel-by-voxel enhancement that could be used for assisting the segmentation of the gross tumor volume on T1 images. The "gold standard" for this analysis was a gross tumor volume corresponding to the contrast-enhancing lesion visualized on T1-weighted images as segmented by a radiation oncologist. The Sum-mean and Variance features demonstrated the best performance overall. For the T1-weighted images, the identification performance of Sum-mean and Variance features computed from the power map was higher (AUC = 0.9959 and AUC = 0.9918, respectively) and with higher Canberra distances as compared to features computed directly from the images (AUC = 0.8930 and AUC = 0.9163, respectively). These results in T2-FLAIR images were even superior. The features computed from the power map showed an unequivocal identification (AUC = 1) with higher Canberra distances, whereas the performance of the features from the original images was slightly lower (AUC = 0.9739 and AUC = 0.9904, respectively). The same features computed on the power map of the T1-weighted images also provided superior enhancement in individual tumor voxels as compared to the features computed on the original images. The Sum-mean and Variance features are both useful for identifying and segmenting GBM tumors on localized Hartley transformed MR images.

MRI-based analysis, lipid composition and sensory traits for studying Iberian dry-cured hams from pigs fed with different diets

The present work was aimed to study Iberian dry-cured hams from pigs reared outdoors and either fed with acorns and grass (AG) or with oleic acid enriched concentrates (HO), by means of their fatty acid profile, sensory traits and Magnetic Resonance Imaging (MRI). The level of total saturated fatty acids (SFA) was higher in HO than in AG hams, whereas total monounsaturated (MUFA) and polyunsaturated fatty acids (PUFA) showed higher proportions in AG than in HO Iberian dry-cured hams. Besides, lower levels of the n − 6/ n − 3 ratio were found in AG than in HO dry-cured hams. Sensory analyses only showed differences between AG and HO Iberian dry-cured hams in pastiness (higher in AG hams, p = 0.039) and marbling (lower in AG hams, p = 0.002). Pig feeding also leads to differences in two computational texture features obtained by MRI-based analysis. Thus, analysis of the fatty acid profile and MRI-based analysis might be used for classifying dry-cured hams from pigs fattened with different diets.

Modeling human aesthetic perception of visual textures

Texture is extensively used in areas such as product design and architecture to convey specific aesthetic information. Using the results of a psychological experiment, we model the relationship between computational texture features and aesthetic properties of visual textures. Contrary to previous approaches, we build a layered model, which provides insights into hierarchical relationships involved in human aesthetic texture perception. This model uses a set of intermediate judgements to link computational texture features with aesthetic texture properties. We pursue two different approaches for modeling. (1) Supervised machine-learning methods are used to generate linear and nonlinear models from the experimental data automatically. The quality of these models is discussed, mainly focusing on interpretability and accuracy. (2) We apply a psychological-based approach that models the processing pathways in human perception of naturalness, introducing judgement dimensions (principal components) mediating the relationship between texture features and naturalness judgements. This multiple mediator model serves as a verification of the machine-learning approach. We conclude with a comparison of these two approaches, highlighting the similarities and discrepancies in terms of identified relationships between computational texture features and aesthetic properties of visual textures.

Texture Segmentation by Genetic Programming

This paper describes a texture segmentation method using genetic programming (GP), which is one of the most powerful evolutionary computation algorithms. By choosing an appropriate representation texture, classifiers can be evolved without computing texture features. Due to the absence of time-consuming feature extraction, the evolved classifiers enable the development of the proposed texture segmentation algorithm. This GP based method can achieve a segmentation speed that is significantly higher than that of conventional methods. This method does not require a human expert to manually construct models for texture feature extraction. In an analysis of the evolved classifiers, it can be seen that these GP classifiers are not arbitrary. Certain textural regularities are captured by these classifiers to discriminate different textures. GP has been shown in this study as a feasible and a powerful approach for texture classification and segmentation, which are generally considered as complex vision tasks.

Differential diagnosis of CT focal liver lesions using texture features, feature selection and ensemble driven classifiers

The aim of the present study is to define an optimally performing computer-aided diagnosis (CAD) architecture for the classification of liver tissue from non-enhanced computed tomography (CT) images into normal liver (C1), hepatic cyst (C2), hemangioma (C3), and hepatocellular carcinoma (C4). To this end, various CAD architectures, based on texture features and ensembles of classifiers (ECs), are comparatively assessed. Number of regions of interests (ROIs) corresponding to C1-C4 have been defined by experienced radiologists in non-enhanced liver CT images. For each ROI, five distinct sets of texture features were extracted using first order statistics, spatial gray level dependence matrix, gray level difference method, Laws' texture energy measures, and fractal dimension measurements. Two different ECs were constructed and compared. The first one consists of five multilayer perceptron neural networks (NNs), each using as input one of the computed texture feature sets or its reduced version after genetic algorithm-based feature selection. The second EC comprised five different primary classifiers, namely one multilayer perceptron NN, one probabilistic NN, and three k-nearest neighbor classifiers, each fed with the combination of the five texture feature sets or their reduced versions. The final decision of each EC was extracted by using appropriate voting schemes, while bootstrap re-sampling was utilized in order to estimate the generalization ability of the CAD architectures based on the available relatively small-sized data set. The best mean classification accuracy (84.96%) is achieved by the second EC using a fused feature set, and the weighted voting scheme. The fused feature set was obtained after appropriate feature selection applied to specific subsets of the original feature set. The comparative assessment of the various CAD architectures shows that combining three types of classifiers with a voting scheme, fed with identical feature sets obtained after appropriate feature selection and fusion, may result in an accurate system able to assist differential diagnosis of focal liver lesions from non-enhanced CT images.

Computerized Texture Analysis of Mammographic Parenchymal Patterns of Digitized Mammograms 1

Mammographic density and parenchymal patterns have been shown to be related to the risk of developing breast cancer. Thus, computerized texture analysis of breast parenchymal patterns on mammograms may be useful in assessing breast cancer risk. A comparative evaluation was conducted of various computer-extracted texture features of mammographic parenchymal patterns of women with BRCA1/BRCA2 gene mutations and those of women at low risk of developing breast cancer. Mammograms from 172 subjects (30 women with either the BRCA1 or BRCA2 gene mutation and 142 low-risk women) were analyzed. Computerized texture features were extracted from regions-of-interest to assess the mammographic parenchymal patterns in the images. Receiver operating characteristic analysis was used to assess the performance of these features in the task of distinguishing between the two groups of women. Quantitative texture analysis on digitized mammograms demonstrated that gene-mutation carriers and low-risk women have different mammographic parenchymal patterns. Gene-mutation carriers presented with parenchymal patterns that were denser, coarser, and lower in contrast than those of the low-risk group. For the gene-mutation carriers, their mammographic patterns appear to contain less high-frequency component as indicated by higher coarseness values, lower fractal dimensions, and smaller edge gradients, which yielded corresponding A(z) values of 0.79, 0.84, and 0.78, respectively, in the task of distinguishing between gene-mutation carriers and the low-risk group with the entire dataset. The contrast measure calculated from co-occurrence matrix method, which describes local image variation, yielded an A(z) value of 0.86 in distinguishing between the two groups of women. Computerized texture analysis of mammograms provides radiographic descriptors of mammographic parenchymal patterns. The computer-extracted features may be useful for identifying women at high risk for breast cancer and for monitoring the treatment of breast cancer patients.

Computerized texture analysis of mammographic parenchymal patterns of digitized mammograms

This study involved a comparative evaluation of various computer-extracted texture features of mammographic parenchymal patterns of women with BRCA1/BRCA2 gene mutations and those of women at low risk of developing breast cancer. With our method, computerized texture analysis is performed on a region of interest (ROI) within the mammographic image. We analyzed mammograms from 172 subjects: 30 women with the BRCA1 or BRCA2 gene mutation and 142 low-risk women. A series of texture features were automatically extracted from each ROI to assess the mammographic parenchymal patterns in the images. Receiver Operating Characteristic (ROC) analysis was used to assess the performance of the computerized texture features in the task of distinguishing between gene mutation carriers and low-risk subjects. Results show that gene mutation carriers and low-risk women have different mammographic patterns. For the gene carriers, their mammographic images have coarse texture, which is indicated by high coarseness values, low fractal dimension, and low entropy. It is expected that women identified as high risk by such radiographic markers of risk might potentially be more aggressively screened for breast cancer.

Computerized analysis of mammographic parenchymal patterns for assessing breast cancer risk: effect of ROI size and location.

The long-term goal of our research is to develop computerized radiographic markers for assessing breast density and parenchymal patterns that may be used together with clinical measures for determining the risk of breast cancer and assessing the response to preventive treatment. In our earlier studies, we found that women at high risk tended to have dense breasts with mammographic patterns that were coarse and low in contrast. With our method, computerized texture analysis is performed on a region of interest (ROI) within the mammographic image. In our current study, we investigate the effect of ROI size and ROI location on the computerized texture features obtained from 90 subjects (30 BRCA1/BRCA2 gene-mutation carriers and 60 age-matched women deemed to be at low risk for breast cancer). Mammograms were digitized at 0.1 mm pixel size and various ROI sizes were extracted from different breast regions in the craniocaudal (CC) view. Seventeen features, which characterize the density and texture of the parenchymal patterns, were extracted from the ROIs on these digitized mammograms. Stepwise feature selection and linear discriminant analysis were applied to identify features that differentiate between the low-risk women and the BRCA1/BRCA2 gene-mutation carriers. ROC analysis was used to assess the performance of the features in the task of distinguishing between these two groups. Our results show that there was a statistically significant decrease in the performance of the computerized texture features, as the ROI location was varied from the central region behind the nipple. However, we failed to show a statistically significant decrease in the performance of the computerized texture features with decreasing ROI size for the range studied.

Frequency and orientation sensitive texture measures using linear symmetry

Abstract An efficient method for computing texture features based on dominant local orientation is introduced. The features are computed as a Laplacian pyramid is built. At each level of the Laplacian pyramid, the linear symmetry feature is computed. This feature is anisotropic and estimates the optimal local orientation in the Least Square Error (LSE) sense. It is complex valued and hence consists of two components, the local orientation estimate and its confidence measure based on the error. The algorithm is based on convolutions with simple separable filters and pixel-wise non-linear arithmetic operations. These properties allow highly parallel implementation, for example on a pyramid machine, yielding real time applications. Comparative experimental results are presented using the feature for unsupervised segmentation on test images of natural aerial image textures.