Spatial Gray Level Dependence Matrices Research Articles

Using structural equation modeling and intima-media complex texture features to assess cardiovascular disease risk in the common carotid artery

The potential for stroke risk in humans due to clinical cardiovascular disease (CVD), which leads to the hardening of the artery walls (atherosclerosis), can be assessed by examining the common carotid artery (CCA) in ultrasound images. Specifically, this can be done by measuring the intima media thickness (IMT), which represents the thickness of the arteries wall, and by analyzing texture features (TFs) of the CCA's intima-media complex (IMC) of the artery wall. In this paper, a sample of 612 longitudinal-section ultrasound images of the left and the right CCA from 158 men and 148 women, out of which 42 demonstrated clinical CVD, is studied. All images are intensity normalized and despeckled, with the IMC segmented through an in-house system of semi-automated segmentation, where the IMT is measured, and 40 different TFs are extracted. Then, employing structural equation modeling (SEM), these TFs, which are put in 6 groups (constructs), are collectively tested on how they are related to CVD. The influence of the IMT is also studied through a moderation analysis, while gender and age of the sub-jects of the study are tested with regard to their control effect. The main conclusions of the study are as follows. The 6 TFs groups and the IMT fit the measurement model very well. Also, 6 hypothesized paths for the impact of each TFs group on CVD are tested in a structural model, with 5 of them, namely Statistical Features (SF), Spatial Gray Level Dependence Matrices (SGLDM), Gray Level Difference Statistics (GLDS), Statistical Feature Matrix (SFM) and Laws Texture Energy Measures (LTEM), impacting CVD in a moderate manner (p-values between .04 and .07). The IMT is shown to play a strong moderating role (p-values of Δχ2 < .01), enhancing the level of impact of the TFs on CVD. Gender and age have a strong controlling effect on CVD (p-values of < .01). The precision of the findings of this study is considerably improved compared to those previously reported, because of the very good model fit (e.g., normed fit index (NFI) = 0.94) for both measurement and structural models. However, due to the moderate nature of the impact, supplementary work is required for testing either additional combinations of TFs, as well as testing other samples through the proposed model, for further evaluation of the CVD risk on symptomatic subjects at risk of atherosclerosis.

Retinal OCT speckle as a biomarker for glaucoma diagnosis and staging.

This paper presents a novel image analysis strategy that increases the potential of macular Optical Coherence Tomography (OCT) by using speckle features as biomarkers in different stages of glaucoma. A large pool of features (480) were computed for a subset of macular OCT volumes of the Leuven eye study cohort. The dataset contained 258 subjects that were divided into four groups based on their glaucoma severity: Healthy (56), Mild (94), Moderate (48), and Severe (60). The OCT speckle features were categorized as statistical properties, statistical distributions, contrast, spatial gray-level dependence matrices, and frequency domain features. The averaged thicknesses of ten retinal layers were also collected. Kruskal-Wallis H test and multivariable regression models were used to infer the most significant features related to glaucoma severity classification and to the correlation with visual field mean deviation. Four features were selected as being the most relevant: the ganglion cell layer (GCL) and the inner plexiform layer (IPL) thicknesses, and two OCT speckle features, the data skewness computed on the retinal nerve fiber layer (RNFL) and the scale parameter (a) of the generalized gamma distribution fitted to the GCL data. Based on a significance level of 0.05, the regression models revealed that RNFL skewness exhibited the highest significance among the features considered for glaucoma severity staging (p-values of 8.6×10-6 for the logistic model and 2.8×10-7 for the linear model). Furthermore, it demonstrated a strong negative correlation with the visual field mean deviation (ρ=-0.64). The post hoc analysis revealed that, when distinguishing healthy controls from glaucoma subjects, GCL thickness is the most relevant feature (p-value of 8.7×10-5). Conversely, when comparing the Mild versus Moderate stages of glaucoma, RNFL skewness emerged as the only feature exhibiting statistical significance (p-value = 0.001). This work shows that macular OCT speckle contains information that is currently not used in clinical practice, and not only complements structural measurements (thickness) but also has a potential for glaucoma staging.

Abstract P351: Grayscale Texture Feature Angular Second Moment Correlates With Collagen Alignment in Carotid Artery Plaques

Introduction: Grayscale (GS) texture features that examine homogeneity and echogenicity have been used to identify vulnerable plaques with in vivo ultrasound imaging have been shown to correlate with plaque tissue composition. However, the relationship of collagen fiber organization to GS texture features extracted from in vivo images is a novel idea to provide additional information about plaque structure. We hypothesize that collagen fiber alignment is clinically relevant to identify vulnerable plaques. The objective of this feasibility study was to use multiscale imaging (in vivo ultrasound and high resolution optical microscopy) to determine how GS texture features are related to plaque collagen structure. Methods: Participants (n=6) scheduled for clinically indicated carotid endarterectomy underwent in vivo carotid ultrasound imaging with texture feature extraction (spatial gray level dependence matrices method for calculating angular second moment [SGLDM-ASM] and grayscale median value [GSM]). Plaque specimens were sent to histopathology and stained with H&amp;E. The collagen fibers in the fibrous cap of the plaque histopathology slides were imaged with liquid crystal based polarization microscopy and quantified using an established software tool (CurveAlign). Correlations between collagen alignment coefficient (range 0-1, 1 represents perfectly aligned fibers) and the texture feature SGLDM-ASM (a measure of homogeneity, higher values are more homogenous) and GSM (a measure of echogenicity higher values are more echogenic) were examined. Results: Participants were mean (SD) 72.5 (6.1) years of age, had 71.67 (8.16) percent stenosis. The mean SGLDM-ASM was 0.0017 (0.0023), the mean SD GSM was 73.13 (30.98). SGLDM-ASM was significantly correlated to collagen alignment (r=0.83; p=0.028). There was no significant correlation detected between GSM and collagen alignment (r=-0.43;p=0.38). Conclusion: Results of this study indicate the potential role for using high resolution optical microscopy with ultrasound to characterize collagen fiber alignment in plaques with measures of homogeneity. Future studies are needed to see how multiscale imaging can be used to inform in vivo imaging for identification of vulnerable plaque features.

Upgraded Spatial Gray Level Dependence Matrices for Textural Analysis in Colon Cancer Tissues

Colon or Bowel or Colorectal Cancer (CRC) is commonly determined by diagnosing a sample of colon tissue and further analysed by medical imaging. The colon tissue classification method count on specific changes between texture features extracted from benign and malignant regions. The variations in the image acquisition methods effects the colon tissue analysis. In this paper, an Upgraded Spatial Gray Level Dependence Matrices (U-SGLDM) is emphasized to extract textural features. The licensed image set of all applicable types of tissues within colon cancer are used for experimentation. Several texture feature sets are extracted to show the significant differences among the eight colon cancer biopsy images in the image data set. The fractal dimension-Hurst Coefficient is added to U-SGLDM for long range assessment. The Prominence of the analysis evoked in the representation of histopathological image structure over longer periods.

Grape Leaf Disease Detection, Classification and Analysis by using Spatial Gray-level Dependence Matrices

Grape Leaf Disease Detection, Classification and Analysis by using Spatial Gray-level Dependence Matrices

Computer-aided diagnosis in hysteroscopic imaging.

The paper presents the development of a computer-aided diagnostic (CAD) system for the early detection of endometrial cancer. The proposed CAD system supports reproducibility through texture feature standardization, standardized multifeature selection, and provides physicians with comparative distributions of the extracted texture features. The CAD system was validated using 516 regions of interest (ROIs) extracted from 52 subjects. The ROIs were equally distributed among normal and abnormal cases. To support reproducibility, the RGB images were first gamma corrected and then converted into HSV and YCrCb. From each channel of the gamma-corrected YCrCb, HSV, and RGB color systems, we extracted the following texture features: 1) statistical features (SFs), 2) spatial gray-level dependence matrices (SGLDM), and 3) gray-level difference statistics (GLDS). The texture features were then used as inputs with support vector machines (SVMs) and the probabilistic neural network (PNN) classifiers. After accounting for multiple comparisons, texture features extracted from abnormal ROIs were found to be significantly different than texture features extracted from normal ROIs. Compared to texture features extracted from normal ROIs, abnormal ROIs were characterized by lower image intensity, while variance, entropy, and contrast gave higher values. In terms of ROI classification, the best results were achieved by using SF and GLDS features with an SVM classifier. For this combination, the proposed CAD system achieved an 81% correct classification rate.

Disturbance Frequency Determines Morphology and Community Development in Multi-Species Biofilm at the Landscape Scale

Many natural and engineered biofilm systems periodically face disturbances. Here we present how the recovery time of a biofilm between disturbances (expressed as disturbance frequency) shapes the development of morphology and community structure in a multi-species biofilm at the landscape scale. It was hypothesized that a high disturbance frequency favors the development of a stable adapted biofilm system while a low disturbance frequency promotes a dynamic biofilm response. Biofilms were grown in laboratory-scale reactors over a period of 55-70 days and exposed to the biocide monochloramine at two frequencies: daily or weekly pulse injections. One untreated reactor served as control. Biofilm morphology and community structure were followed on comparably large biofilm areas at the landscape scale using automated image analysis (spatial gray level dependence matrices) and community fingerprinting (single-strand conformation polymorphisms). We demonstrated that a weekly disturbed biofilm developed a resilient morphology and community structure. Immediately after the disturbance, the biofilm simplified but recovered its initial complex morphology and community structure between two biocide pulses. In the daily treated reactor, one organism largely dominated a morphologically simple and stable biofilm. Disturbances primarily affected the abundance distribution of already present bacterial taxa but did not promote growth of previously undetected organisms. Our work indicates that disturbances can be used as lever to engineer biofilms by maintaining a biofilm between two developmental states.

Evolution-based hierarchical feature fusion for ultrasonic liver tissue characterization.

This paper presents an evolution-based hierarchical feature fusion system that selects the dominant features among multiple feature vectors for ultrasonic liver tissue characterization. After extracting the spatial gray-level dependence matrices, multiresolution fractal feature vectors and multiresolution energy feature vectors, the system utilizes evolution-based algorithms to select features. In each feature space, features are selected independently to compile a feature subset. As the features of different feature vectors contain complementary information, a feature fusion process is used to combine the subsets generated from different vectors. Features are then selected from the fused feature vector to form a fused feature subset. The selected features are used to classify ultrasonic images of liver tissue into three classes: hepatoma, cirrhosis, and normal liver. Experiment results show that the classification accuracy of the fused feature subset is superior to that derived by using individual feature subsets. Moreover, the findings demonstrate that the proposed algorithm is capable of selecting discriminative features among multiple feature vectors to facilitate the early detection of hepatoma and cirrhosis via ultrasonic liver imaging.

Improved Spatial Gray Level Dependence Matrices for Texture Analysis

In this paper, we will focus on the Spatial Gray Level Dependence MatricesSGLDM to extract the Haralick’s texture features of the ultrasound breast lesions. This method relies on the manual selection of the region of interest, which results in the dependence of parameters values on the extracted region. For that reason, an improvedSpatial Gray Level Dependence Matrices based on the segmented masses using active contour was applied. This method outperform s the existing SGLDM method because it allows establishing a well determined threshold for the classification of lesions.

Prediction of High-Risk Asymptomatic Carotid Plaques Based on Ultrasonic Image Features

Carotid plaques have been associated with ipsilateral neurological symptoms. High-resolution ultrasound can provide information not only on the degree of carotid artery stenosis but also on the characteristics of the arterial wall including the size and consistency of atherosclerotic plaques. The aim of this study is to determine whether the addition of ultrasonic plaque texture features to clinical features in patients with asymptomatic internal carotid artery stenosis (ACS) improves the ability to identify plaques that will produce stroke. 1121 patients with ACS have been scanned with ultrasound and followed for a mean of 4 years. It is shown that the combination of texture features based on second-order statistics spatial gray level dependence matrices (SGLDM) and clinical factors improves stroke prediction (by correctly predicting 89 out of the 108 cases that were symptomatic). Here, the best classification results of 77 ±1.8% were obtained from the use of the SGLDM texture features with support vector machine classifiers. The combination of morphological features with clinical features gave slightly worse classification results of 76 ±2.6% . These findings need to be further validated in additional prospective studies.

Ultrasonic liver tissue characterization by feature fusion

This paper describes a two-stage feature fusion method for ultrasonic liver tissue characterization. The proposed method hierarchically incorporates a genetic-algorithm-based feature selection to automatically select more efficient feature subset to discriminate among ultrasonic images of liver tissue in three states: normal liver, cirrhosis, and hepatoma. Multiple feature spaces are adopted in this paper, including the spatial gray-level dependence matrices (SGLDMs), multiresolution fractal feature vector and multiresolution energy feature vector. Features extracted from different feature spaces may contain complementary information. The feature subsets of different feature spaces are fused and the genetic-algorithm-based feature selection is applied onto the fused feature space to facilitate the two-stage feature fusion. The classification accuracy of the fused feature subset is up to 96.62%. Experimental results demonstrate that the proposed method is capable to select discriminative features among multiple feature vectors to achieve the early detection of hepatoma and cirrhosis based on ultrasonic liver imaging.

488 Ultrasonographic features of plaque texture are associated with histological features of Carotid plaque instability

488 Ultrasonographic features of plaque texture are associated with histological features of Carotid plaque instability

Computer-aided analysis of transrectal ultrasound images of the prostate

IntroductionProstate cancer is usually diagnosed by transrectal ultrasound (TRUS) biopsy. Nevertheless, suspicious images are frequently not found. Imaging analysis studies aim to identify ultrasound patterns characteristic of apparently hidden conditions. Material and methodsWe digitally recorded 288 TRUS ultrasound guided transrectal biopsies and extracted 3 static images from the puncture-biopsy area. The extraction of the texture characteristics were obtained by “simple mapping” on a gray scale and spatial gray level dependence matrices (SGLDM), also known as Haralick's co-occurrence matrices, which study the relationship of each pixel and its neighbors. A pattern recognition software system was developed with two different classification methods: nearest neighbor (k-NN) and Markov's hidden models. Finally, a virtual experiment was carried out in which four urologists compared their diagnostic accuracy for prostate cancer with our system in 408 TRUS images, not in real time. ResultsThe diagnostic capacity (ROC curve) with the simple gray map study was 59.7% with nearest-neighbor classification and 61.6% with Markov's hidden models classification. The co-occurrence matrices showed an area under ROC curve of 60.1% and 60.0% with k-NN and Markov's hidden models classification, respectively. The virtual experiment was conducted with a simple gray map study and k-NN classification. The images processed by our system showed the following diagnostic accuracy: 63.3, 67, 64.3 and 63.7% compared to 61.7, 60.5, 66.2 and 60.7% with the original image. ConclusionsOur pattern recognition system for prostate cancer TRUS images has a limited, yet stable, accuracy.

Análisis de imagen asistido por ordenador en ecografía transrectal de próstata

Introduction Prostate cancer is usually diagnosed by transrectal ultrasound (TRUS) biopsy. Nevertheless, suspicious images are frequently not found. Imaging analysis studies aim to identify ultrasound patterns characteristic of apparently hidden conditions. Material and methods We digitally recorded 288 TRUS ultrasound guided transrectal biopsies and extracted 3 static images from the puncture-biopsy area. The extraction of the texture characteristics were obtained by “simple mapping” on a gray scale and spatial gray level dependence matrices (SGLDM), also known as Haralick‘s co-occurrence matrices, which study the relationship of each pixel and its neighbors. A pattern recognition software system was developed with two different classification methods: nearest neighbor (k-NN) and Markov's hidden models. Finally, a virtual experiment was carried out in which four urologists compared their diagnostic accuracy for prostate cancer with our system in 408 TRUS images, not in real time. Results The diagnostic capacity (R.O.C. curve) with the simple gray map study was 59.7% with nearest-neighbor classification and 61.6% with Markov's hidden models classification. The co-occurrence matrices showed an area under R.O.C. curve of 60.1% and 60.0% with k-NN and Markov's hidden models classification, respectively. The virtual experiment was conducted with a simple gray map study and k-NN classification. The images processed by our system showed the following diagnostic accuracy: 63.3, 67, 64.3 and 63.7% compared to 61.7, 60.5, 66.2 and 60.7% with the original image. Conclusions Our pattern recognition system for prostate cancer TRUS images has a limited, yet stable, accuracy.

Computerized Texture Analysis of Carotid Plaque Ultrasonic Images Can Identify Unstable Plaques Associated With Ipsilateral Neurological Symptoms

We estimated the value of objective, computerized texture analysis of ultrasonic images in distinguishing carotid plaques associated with neurological ipsilateral symptoms (amaurosis fugax [AmF; n = 30], transient ischemic attack [TIA; n = 52], and stroke [n = 55]) from asymptomatic plaques (n = 51). We performed 3 case-control studies (1/symptom with asymptomatic plaques as control). On logistic regression, AmF was independently associated with severity of stenosis, percentage of pixels with gray levels 0 to 10 (PPCS1; measure of echolucency), and spatial gray level dependence matrices (SGLDM) information measure of correlation (IMC-1; texture); TIAs with PPCS1 (echolucency), SGLDM correlation, and skewness (both texture); and stroke with PPCS1, SGLDM correlation, and percentage of pixels with gray levels 11 to 20 (PPCS2; echolucency). The area under the curve of the regression-derived predicted probability for AmF, TIA, and stroke was 0.92, 0.82, and 0.85, respectively (all P < .001). Texture analysis can identify carotid plaques associated with a neurological event, improving the diagnostic value of echolucency measures. Texture analyses could be applied to natural history studies.

Evaluation of placental maturity by the sonographic textures

Routine ultrasound screening to predict gestational age is important for risk assessment of pregnancy complications among pregnant women. We explored a quantitative method for sonographic analysis of placental texture, with the objective of reproducible measurement. We studied 151 pregnant women; the gestational ages of their fetuses ranged from 10 to 38 weeks. Three experienced sonographers delineated the placental contour to define the region of interest (ROI). From these sonograms, 72 texture features were derived from the spatial gray-level dependence matrices and gray-level difference matrices. We used these as input variables in a multiple linear regression analysis. A significant positive correlation (P < 0.01) was found between the multiple linear regression results and the corresponding gestation ages by the three assessors (r (A) = 0.755, r (B) = 0.851, and r (C) = 0.832). We also found good agreement between multiple linear regression results for the three observers. Their κ statistic values were 0.685 between assessors A and B, 0.679 between A and C, and 0.804 between B and C. Quantitative sonography using texture analysis of the placenta was useful in practice to determine gestational age.

Coregistered FDG PET/CT-Based Textural Characterization of Head and Neck Cancer for Radiation Treatment Planning

Coregistered fluoro-deoxy-glucose (FDG) positron emission tomography/computed tomography (PET/CT) has shown potential to improve the accuracy of radiation targeting of head and neck cancer (HNC) when compared to the use of CT simulation alone. The objective of this study was to identify textural features useful in distinguishing tumor from normal tissue in head and neck via quantitative texture analysis of coregistered 18F-FDG PET and CT images. Abnormal and typical normal tissues were manually segmented from PET/CT images of 20 patients with HNC and 20 patients with lung cancer. Texture features including some derived from spatial grey-level dependence matrices (SGLDM) and neighborhood gray-tone-difference matrices (NGTDM) were selected for characterization of these segmented regions of interest (ROIs). Both K nearest neighbors (KNNs) and decision tree (DT)-based KNN classifiers were employed to discriminate images of abnormal and normal tissues. The area under the curve (AZ) of receiver operating characteristics (ROC) was used to evaluate the discrimination performance of features in comparison to an expert observer. The leave-one-out and bootstrap techniques were used to validate the results. The AZ of DT-based KNN classifier was 0.95. Sensitivity and specificity for normal and abnormal tissue classification were 89% and 99%, respectively. In summary, NGTDM features such as PET Coarseness, PET Contrast, and CT Coarseness extracted from FDG PET/CT images provided good discrimination performance. The clinical use of such features may lead to improvement in the accuracy of radiation targeting of HNC.

Textural fingerprints: A comprehensive descriptor for biofilm structure development

Automated tools to determine biofilm structure are necessary to interpret large time series of biofilm images. Image analysis based on the evaluation of Spatial Gray Level Dependence Matrices (SGLDM) enabled us to monitor biofilm structure development in response to external disturbances (i.e., periodic increases of wall shear stress) at a large scale (i.e., >1 mm). We applied our method to an experiment conducted in an annular reactor over a 10-week period. Six states of biofilm development were differentiated by their unique structure. Previous exposure to rapidly increased shear influenced the resulting biofilm structure after additional shear increases. In addition, on the scale of the biofilm images, the biofilm structure after a shear increase was spatially heterogeneous and resulted in spatially differentiated regrowth after detachment at different locations in the biofilm. SGLDM was developed further as an alternative to approaches based on image binarization as binarization leads to information loss for low-magnification and low-resolution images. During post-processing of image data, structural states of biofilm development were identified by K-means clustering and data display in Principal Component plots. Quantitatively selected representative images were used to illustrate the meaning of the clusters. Post-treatment of image data was essential for managing several thousands of raw biofilm images and therefore improved the usefulness of the image analysis.

Bilateral analysis based false positive reduction for computer‐aided mass detection

We have developed a false positive (FP) reduction method based on analysis of bilateral mammograms for computerized mass detection systems. The mass candidates on each view were first detected by our unilateral computer-aided detection (CAD) system. For each detected object, a regional registration technique was used to define a region of interest (ROI) that is "symmetrical" to the object location on the contralateral mammogram. Texture features derived from the spatial gray level dependence matrices and morphological features were extracted from the ROI containing the detected object on a mammogram and its corresponding ROI on the contralateral mammogram. Bilateral features were then generated from corresponding pairs of unilateral features for each object. Two linear discriminant analysis (LDA) classifiers were trained from the unilateral and the bilateral feature spaces, respectively. Finally, the scores from the unilateral LDA classifier and the bilateral LDA asymmetry classifier were fused with a third LDA whose output score was used to distinguish true mass from FPs. A data set of 341 cases of bilateral two-view mammograms was used in this study, of which 276 cases with 552 bilateral pairs contained 110 malignant and 166 benign biopsy-proven masses and 65 cases with 130 bilateral pairs were normal. The mass data set was divided into two subsets for twofold cross-validation training and testing. The normal data set was used for estimation of FP rates. It was found that our bilateral CAD system achieved a case-based sensitivity of 70%, 80%, and 85% at average FP rates of 0.35, 0.75, and 0.95 FPs/image, respectively, on the test data sets with malignant masses. In comparison to the average FP rates for the unilateral CAD system of 0.58, 1.33, and 1.63, respectively, at the corresponding sensitivities, the FP rates were reduced by 40%, 44%, and 42% with the bilateral symmetry information. The improvement was statistically significance (p < 0.05) as estimated by JAFROC analysis.

Texture analysis of spatial biofilm development

The quantitative evaluation of images taken during biofilm experiments is an important step in determining the relation between biofilm performance and biofilm architecture. Whereas areal descriptors are used by some researchers, descriptors of biofilm texture have received limited attention. In our research, the texture of images documenting long-term biofilm experiments was evaluated using a spatial grey level dependence matrices (SGLDM) approach. By calculating SGLDM for a wide range of position operators (angle-distance combinations), the discriminatory power of this approach was extended. For some descriptors, surface plots allowed the direct spatial interpretation of texture. Using principal component analysis (PCA) a subset of independent textural descriptors was identified. It is suggested to determine textural fingerprints of stages during biofilm development by making use of PCA and biplots.