scholarly journals FORMING THE STACK OF TEXTURE FEATURES FOR LIVER ULTRASOUND IMAGES CLASSIFICATION

2020 ◽  
Vol 3 (4) ◽  
pp. 240-251
Author(s):  
Dmitro Yuriiovych Hrishko ◽  
Ievgen Arnoldovich Nastenko ◽  
Maksym Oleksandrovych Honcharuk ◽  
Volodymyr Anatoliyovich Pavlov
Keyword(s):  
Random Forest ◽  
Texture Analysis ◽  
Binary Classification ◽  
Texture Features ◽  
Normal Liver ◽  
Group Method ◽  
Ultrasound Images ◽  
Liver Ultrasound ◽  
Random Forest Models ◽  
Occurrence Matrix

This article discusses the use of texture analysis methods to obtain informative features that describe the texture of liver ultrasound images. In total, 317 liver ultrasound images were analyzed, which were provided by the Institute of Nuclear Medicine and Radiation Diagnostics of NAMS of Ukraine. The images were taken by three different sensors (convex, linear, and linear sensor in increased signal level mode). Both images of patients with a normal liver condition and patients with specific liver disease (there were diseases such as: autoimmune hepatitis, Wilson's disease, hepatitis B and C, steatosis, and cirrhosis) were present in the database. Texture analysis was used for “Feature Construction”, which resulted in more than a hundred different informative features that made up a common stack. Among them, there are such features as: three authors’ patented features derived from the grey level co-occurrence matrix; features, obtained with the help of spatial sweep method (working by the principle of group method of data handling), which was applied to ultrasound images; statistical features, calculated on the images, brought to one scale with the help of differential horizontal and vertical matrices, which are proposed by the authors; greyscale pairs ensembles (found using the genetic algorithm), which identify liver pathology on images, transformed with the help of horizontal and vertical differentiations, in the best possible way. The resulting trait stack was used to solve the problem of binary classification (“norma-pathology”) of ultrasound liver images. A Machine Learning method, namely “Random Forest”, was used for this purpose. Before the classification, in order to obtain objective results, the total samples were divided into training (70 %), testing (20 %), and examining (10 %). The result was the best three Random Forest models separately for each sensor, which gave the following recognition rates: 93.4 % for the convex sensor, 92.9 % for the linear sensor, and 92 % for the reinforced linear sensor

Nipple Localization in Automated Whole Breast Ultrasound Coronal Scans Using Ensemble Learning

2020 ◽  
Vol 43 (1) ◽  
pp. 29-45
Author(s):  
Alex Noel Joseph Raj ◽  
Ruban Nersisson ◽  
Vijayalakshmi G. V. Mahesh ◽  
Zhemin Zhuang
Keyword(s):  
Texture Features ◽  
Breast Ultrasound ◽  
Support Vector ◽  
Ultrasound Images ◽  
Shadow Area ◽  
Hu Moments ◽  
Artificial Neural Network Ann ◽  
Cade System ◽  
Occurrence Matrix ◽  
Shape Complexity

Nipple is a vital landmark in the breast lesion diagnosis. Although there are advanced computer-aided detection (CADe) systems for nipple detection in breast mediolateral oblique (MLO) views of mammogram images, few academic works address the coronal views of breast ultrasound (BUS) images. This paper addresses a novel CADe system to locate the Nipple Shadow Area (NSA) in ultrasound images. Here the Hu Moments and Gray-level Co-occurrence Matrix (GLCM) were calculated through an iterative sliding window for the extraction of shape and texture features. These features are then concatenated and fed into an Artificial Neural Network (ANN) to obtain probable NSA’s. Later, contour features, such as shape complexity through fractal dimension, edge distance from the periphery and contour area, were computed and passed into a Support Vector Machine (SVM) to identify the accurate NSA in each case. The coronal plane BUS dataset is built upon our own, which consists of 64 images from 13 patients. The test results show that the proposed CADe system achieves 91.99% accuracy, 97.55% specificity, 82.46% sensitivity and 88% F-score on our dataset.

Relationships of Image Texture Properties with Chewing Activity and Mechanical Properties during Mastication of Bread

2016 ◽  
Vol 12 (4) ◽  
pp. 311-321
Author(s):  
Qian Mao ◽  
Yonghai Sun ◽  
Jumin Hou ◽  
Libo Yu ◽  
Yang Liu ◽  
...  
Keyword(s):  
Mechanical Properties ◽  
Texture Analysis ◽  
Texture Features ◽  
Image Texture ◽  
Emg Activity ◽  
Analysis Method ◽  
Texture Properties ◽  
Property Changes ◽  
Occurrence Matrix ◽  
Chewing Activity

Abstract The objective of this study was to investigate the relationships of image texture properties with chewing behaviors, and mechanical properties during mastication of bread. Gray-level gradient co-occurrence matrix (GGCM) was used to process the images of boluses. The chewing behaviors were recorded by electromyography (EMG), and the mechanical properties were measured by texture analyzer. The results showed that among the texture features, the inverse difference moment (IDMGGCM) was selected as the main parameter to describe the decomposition of boluses. IDMGGCM was positively related to the weight gain (r = 0.865, p < 0.01), negatively correlated with hardness (r = –0.835, p <0.01) and EMG activity per cycle (r = –0.767, p < 0.01). GGCM is an effective texture analysis method that could correctly identify 70.1–80.8 % of food bolus images to the corresponding chewing cycles. This study provided a new clue for texture analysis of bread bolus images and offered data revealing the bolus property changes during the mastication of bread.

scholarly journals Optimal Mass Transport for Robust Texture Analysis

2019 ◽  
Author(s):  
Zehor Belkhatir ◽  
Aditi Iyer ◽  
James C. Mathews ◽  
Maryam Pouryahya ◽  
Saad Nadeem ◽  
...  
Keyword(s):  
Mass Transport ◽  
Texture Analysis ◽  
Transport Theory ◽  
Texture Features ◽  
Standard Of Care ◽  
Wasserstein Distance ◽  
Strongly Correlated ◽  
Optimal Mass Transport ◽  
Feature Processing ◽  
Occurrence Matrix

AbstractThe emerging field of radiomics, which consists of transforming standard-of-care images to quantifiable scalar statistics, endeavors to reveal the information hidden in these macroscopic images. This field of research has found different applications ranging from phenotyping and tumor classification to outcome prediction and treatment planning. Texture analysis, which often consists of reducing spatial texture matrices to summary scalar features, has been shown to be important in many of the latter applications. However, as pointed out in many studies, some of the derived texture statistics are strongly correlated and tend to contribute redundant information; and are also sensitive to the parameters used in their computation, e.g., the number of gray intensity levels. In the present study, we propose first to consider texture matrices, with an emphasis on gray-level co-occurrence matrix (GLCM), as a non-parametric multivariate objects. The proposed modeling approach avoids evaluating redundant and strongly correlated features and also prevents the feature processing steps. Then, via the Wasserstein distance from optimal mass transport theory, we propose to compare these spatial objects to identify computerized tomography slices with dental artifacts in head and neck cancer. We demonstrate the robustness of the proposed classification approach with respect to the GLCM extraction parameters and the size of the training set. Comparisons with the random forest classifier, which is constructed on scalar texture features, demonstrates the efficiency and robustness of the proposed algorithm.

A CAD system for B-mode fatty liver ultrasound images using texture features

2014 ◽  
Vol 39 (2) ◽  
pp. 123-130 ◽  
Author(s):  
M. B. Subramanya ◽  
Vinod Kumar ◽  
Shaktidev Mukherjee ◽  
Manju Saini
Keyword(s):  
Fatty Liver ◽  
Texture Features ◽  
Ultrasound Images ◽  
Cad System ◽  
Liver Ultrasound

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

Animals ◽  
2022 ◽  
Vol 12 (2) ◽  
pp. 195
Author(s):  
Małgorzata Domino ◽  
Marta Borowska ◽  
Anna Trojakowska ◽  
Natalia Kozłowska ◽  
Łukasz Zdrojkowski ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Texture Features ◽  
Image Texture ◽  
Gray Level ◽  
Image Texture Analysis ◽  
Thermal Images ◽  
Thoracolumbar Region ◽  
Thermal Features ◽  
Occurrence Matrix ◽  
The Impact

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.

scholarly journals The Potential Value of Texture Analysis Based on Dynamic Contrast-Enhanced MR Images in the Grading of Breast Phyllode Tumors

2021 ◽  
Vol 11 ◽  
Author(s):  
Xiaoguang Li ◽  
Hong Guo ◽  
Chao Cong ◽  
Huan Liu ◽  
Chunlai Zhang ◽  
...  
Keyword(s):  
Texture Analysis ◽  
Roc Curve ◽  
Breast Imaging ◽  
Statistical Significance ◽  
Texture Features ◽  
Imaging Findings ◽  
Mr Images ◽  
Dynamic Contrast Enhanced ◽  
Contrast Enhanced ◽  
Occurrence Matrix

PurposeTo explore the value of texture analysis (TA) based on dynamic contrast-enhanced MR (DCE-MR) images in the differential diagnosis of benign phyllode tumors (BPTs) and borderline/malignant phyllode tumors (BMPTs).MethodsA total of 47 patients with histologically proven phyllode tumors (PTs) from November 2012 to March 2020, including 26 benign BPTs and 21 BMPTs, were enrolled in this retrospective study. The whole-tumor texture features based on DCE-MR images were calculated, and conventional imaging findings were evaluated according to the Breast Imaging Reporting and Data System (BI-RADS). The differences in the texture features and imaging findings between BPTs and BMPTs were compared; the variates with statistical significance were entered into logistic regression analysis. The receiver operating characteristic (ROC) curve was used to assess the diagnostic performance of models from image-based analysis, TA, and the combination of these two approaches.ResultsRegarding texture features, three features of the histogram, two features of the gray-level co-occurrence matrix (GLCM), and three features of the run-length matrix (RLM) showed significant differences between the two groups (all p &lt; 0.05). Regarding imaging findings, however, only cystic wall morphology showed significant differences between the two groups (p = 0.014). The areas under the ROC curve (AUCs) of image-based analysis, TA, and the combination of these two approaches were 0.687 (95% CI, 0.518–0.825, p = 0.014), 0.886 (95% CI, 0.760–0.960, p &lt; 0.0001), and 0.894 (95% CI, 0.754–0.970, p &lt; 0.0001), respectively.ConclusionTA based on DCE-MR images has potential in differentiating BPTs and BMPTs.

A Novel Texture Analysis Method Based on Reverse Biorthogonal Wavelet and Co-Occurrence Matrix Applied for Classification of Hepatocellular Carcinoma and Hepatic Hemangioma

2018 ◽  
Vol 8 (9) ◽  
pp. 1835-1843 ◽  
Author(s):  
Jia-Jun Qiu ◽  
Yue Wu ◽  
Bei Hui ◽  
Jia Chen ◽  
Lin Ji ◽  
...  
Keyword(s):  
Hepatocellular Carcinoma ◽  
Texture Analysis ◽  
Texture Features ◽  
Ct Images ◽  
Hepatic Hemangioma ◽  
Gray Level ◽  
Biorthogonal Wavelet ◽  
Analysis Method ◽  
Enhanced Ct ◽  
Occurrence Matrix

Purpose: To explore the feasibility of classifying hepatocellular carcinoma (HCC) and hepatic hemangioma (HEM) using texture features of non-enhanced computed tomography (CT) images, especially to investigate the effectiveness of a novel texture analysis method based on the combination of wavelet and co-occurrence matrix. Methods: 269 patients were retrospectively analyzed, including 129 HCCs and 140 HEMs. We cropped tumor regions of interest (ROIs) on non-enhanced CT images, and then used four texture analysis methods to extract quantitative data of the ROIs: gray-level histogram (GLH), gray-level co-occurrence matrix (GLCM), reverse biorthogonal wavelet transform (RBWT), and reverse biorthogonal wavelet co-occurrence matrix (RBCM). The RBCM was a novel method proposed in this study that combined wavelet transform and co-occurrence matrix. It discretized wavelet coefficient matrices based on the statistical characteristics of the training set. Thus, four sets of texture features were obtained. We then conducted classification studies using support vector machine on each set of texture features. 10-fold cross training and testing were used in the classifications, and their results were evaluated and compared. In addition, we tested the significant differences in the texture features of the RBCM method and explored the possible relationships between textures and lesion types. Results: The RBCM method achieved the best classification performance: its average accuracy was 82.14%; its average AUC (area under the receiver operating characteristic curve) was 0.8423. In addition, using the methods of GLH, GLCM, and RBWT, their average accuracies were 75.81%, 78.79%, and 78.8%, respectively. Conclusions: It indicates that the developed texture analysis methods are rewarding for computer-aided diagnosis of HCC and HEM based on non-enhanced CT images. Furthermore, the distinguishing ability of the proposed RBCM method is more pronounced.

scholarly journals Diagnostic Value of Machine Learning-Based Quantitative Texture Analysis in Differentiating Benign and Malignant Thyroid Nodules

2019 ◽  
Vol 2019 ◽  
pp. 1-7
Author(s):  
Bulent Colakoglu ◽  
Deniz Alis ◽  
Mert Yergin
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Texture Analysis ◽  
Thyroid Nodules ◽  
Intraclass Correlation ◽  
Texture Features ◽  
Diagnostic Value ◽  
External Data ◽  
Wrapper Method ◽  
Sensitivity Specificity

Aim. The aim of this study is to evaluate the diagnostic value of machine learning- (ML-) based quantitative texture analysis in the differentiation of benign and malignant thyroid nodules. Materials and methods. A sum of 306 quantitative textural features of 235 thyroid nodules (102 malignant, 43.4%; 133 benign, 56.4%) of a total of 198 patients were investigated using the random forest ML classifier. Feature selection and dimension reduction were conducted using reproducibility testing and a wrapper method. The diagnostic accuracy, sensitivity, specificity, and area under curve (AUC) of the proposed method were compared with the histopathological or cytopathological findings as reference methods. Results. Of the 306 initial texture features, 284 (92.2%) showed good reproducibility (intraclass correlation ≥0.80). The random forest classifier accurately identified 87 out of 102 malignant thyroid nodules and 117 out of 133 benign thyroid nodules, which is a diagnostic sensitivity of 85.2%, specificity of 87.9%, and accuracy of 86.8%. The AUC of the model was 0.92. Conclusions. Quantitative textural analysis of thyroid nodules using ML classification can accurately discriminate benign and malignant thyroid nodules. Our findings should be validated by multicenter prospective studies using completely independent external data.

Sign in / Sign up

Export Citation Format

Share Document