Gray-level Co-occurrence Matrix Texture Features Research Articles

Machine Learning on Ultrasound Texture Analysis Data for Characterizing of Salivary Glandular Tumors: A Feasibility Study.

Objective quantitative texture characteristics may be helpful in salivary glandular tumor differential diagnosis. This study uses machine learning (ML) to explore and validate the performance of ultrasound (US) texture features in diagnosing salivary glandular tumors. 122 patients with salivary glandular tumors, including 71 benign and 51 malignant tumors, are enrolled. Representative brightness mode US pictures are selected for further Gray Level Co-occurrence Matrix (GLCM) texture analysis. We use a t-test to test the significance and use the receiver operating characteristic curve method to find the optimal cut-point for these significant features. After splitting 80% of the data into a training set and 20% data into a testing set, we use five machine learning models, k-nearest Neighbors (kNN), Naïve Bayes, Logistic regression, Artificial Neural Networks (ANNs) and supportive vector machine (SVM), to explore and validate the performance of US GLCM texture features in diagnosing salivary glandular tumors. This study includes 49 female and 73 male patients, with a mean age of 53 years old, ranging from 21 to 93. We find that six GLCM texture features (contrast, inverse difference movement, entropy, dissimilarity, inverse difference and difference entropy) are significantly different between benign and malignant tumors (p < 0.05). In ML, the overall accuracy rates are 74.3% (95%CI: 59.8-88.8%), 94.3% (86.6-100%), 72% (54-89%), 84% (69.5-97.3%) and 73.5% (58.7-88.4%) for kNN, Naïve Bayes, Logistic regression, a one-node ANN and SVM, respectively. US texture analysis with ML has potential as an objective and valuable tool to make a differential diagnosis between benign and malignant salivary gland tumors.

Study on the EC prediction of cracked soda saline-alkali soil based on texture analysis of high-resolution images from ground-based observation and machine learning methods

The rapid and accurate measurement of soil salinity is essential for assessing the level of soil salinization. In natural conditions, the surface of cohesive soda saline-alkali soil experiences shrinkage and cracking phenomena during water evaporation. The propagation and development of these desiccation cracks can be effectively described using texture features due to their statistical randomness. This study aims to establish a relationship between electrical conductivity (EC) values and texture features derived from both gray-level co-occurrence matrix (GLCM) and wavelet decomposition, and to develop a prediction model for EC accordingly. To achieve these objectives, crack images on the surface of 200 soil samples with varying levels of salinity were obtained in the Songnen Plain field. GLCM was computed and wavelet decomposition was performed to extract texture features in different directions and scales. The results demonstrate a significant correlation between texture features and soil EC values. Among the various texture features, 12 GLCM texture features with a grayscale level of 2 and a step size of 1 pixel, and wavelet texture features derived from a 4th level orthogonal decomposition based on the coiflet-1 function were selected as the optimal parameters for establishing and comparing the predictive effects of two machine learning models on soil EC values. In comparison to the testing results of the BP neural network model (R2=0.83, RPD=1.64, RMSE=0.32 dS/m, MAE=0.18 dS/m), the random forest model exhibited higher accuracy and stability (R2=0.95, RPD=3.48, RMSE=0.21 dS/m, MAE=0.07 dS/m), indicating that although both machine learning models demonstrated rapid and nondestructive capabilities, the random forest method was better suited for EC prediction in soda saline-alkali soil due to its superior accuracy.

Assessing Maize Yield Spatiotemporal Variability Using Unmanned Aerial Vehicles and Machine Learning

Optimizing the prediction of maize (Zea mays L.) yields in smallholder farming systems enhances crop management and thus contributes to reducing hunger and achieving one of the Sustainable Development Goals (SDG 2—zero hunger). This research investigated the capability of unmanned aerial vehicle (UAV)-derived data and machine learning algorithms to estimate maize yield and evaluate its spatiotemporal variability through the phenological cycle of the crop in Bronkhorstspruit, South Africa, where UAV data collection took over four dates (pre-flowering, flowering, grain filling, and maturity). The five spectral bands (red, green, blue, near-infrared, and red-edge) of the UAV data, vegetation indices, and grey-level co-occurrence matrix textural features were computed from the bands. Feature selection relied on the correlation between these features and the measured maize yield to estimate maize yield at each growth period. Crop yield prediction was then conducted using our machine learning (ML) regression models, including Random Forest, Gradient Boosting (GradBoost), Categorical Boosting, and Extreme Gradient Boosting. The GradBoost regression showed the best overall model accuracy with R2 ranging from 0.05 to 0.67 and root mean square error from 1.93 to 2.9 t/ha. The yield variability across the growing season indicated that overall higher yield values were predicted in the grain-filling and mature growth stages for both maize fields. An analysis of variance using Welch’s test indicated statistically significant differences in maize yields from the pre-flowering to mature growing stages of the crop (p-value &lt; 0.01). These findings show the utility of UAV data and advanced modelling in detecting yield variations across space and time within smallholder farming environments. Assessing the spatiotemporal variability of maize yields in such environments accurately and timely improves decision-making, essential for ensuring sustainable crop production.

Frequency and Spatial Domain-Based Approaches for Recognition of Indian Sign Language Gestures

Objectives: The objective of this paper is to introduce and demonstrate an innovative approach for the recognition of Indian sign language gestures, with a focus on bridging communication gap between the deaf and hearing communities. The goal is to contribute to the development of effective tools and technologies that facilitate seamless communication between individuals using sign language and the people with no knowledge about sign language. Methods: The methodology consists of three key steps. First, data pre-processing involves resizing and contours extraction. Next, feature extraction employs Fourier descriptors for frequency domain analysis and gray-level-co-occurrence matrix for spatial domain analysis. Finally, various machine learning models including SVM, Random Forest, Logistic Regression, K-Nearest Neighbor and Naive Bayes are trained on a standard dataset. Findings: In our controlled experimental setup, we applied a diverse set of machine learning classifiers to evaluate the proposed approach for gesture recognition. Among the classifiers tested, K-Nearest Neighbors demonstrated the highest accuracy, achieving 99.82%. To validate the robustness of our approach, we employed k-fold cross-validation with 5 folds. Novelty: This study presents an innovative method for sign language recognition by employing a dual-domain fusion strategy that prominently emphasizes the frequency domain. Through the integration of Fourier descriptors, the research conducts a detailed frequency domain analysis to characterize the contour shapes of sign language gestures. The synergy with gray-level co-occurrence matrix texture features in the spatial domain analysis, contributes to the creation of a comprehensive feature vector. The proposed approach ensures a thorough exploration of gesture features, there by advancing the precision and efficacy of sign language recognition. Keywords: Indian Sign Language (ISL), Sign Language Recognition (SLR), Frequency domain, Spatial domain, Fourier descriptors, Gray level co­occurrence matrix (GLCM), K­ Fold

Optimizing window size and directional parameters of GLCM texture features for estimating rice AGB based on UAVs multispectral imagery.

Aboveground biomass (AGB) is a crucial physiological parameter for monitoring crop growth, assessing nutrient status, and predicting yield. Texture features (TFs) derived from remote sensing images have been proven to be crucial for estimating crops AGB, which can effectively address the issue of low accuracy in AGB estimation solely based on spectral information. TFs exhibit sensitivity to the size of the moving window and directional parameters, resulting in a substantial impact on AGB estimation. However, few studies systematically assessed the effects of moving window and directional parameters for TFs extraction on rice AGB estimation. To this end, this study used Unmanned aerial vehicles (UAVs) to acquire multispectral imagery during crucial growth stages of rice and evaluated the performance of TFs derived with different grey level co-occurrence matrix (GLCM) parameters by random forest (RF) regression model. Meanwhile, we analyzed the importance of TFs under the optimal parameter settings. The results indicated that: (1) the appropriate window size for extracting TFs varies with the growth stages of rice plant, wherein a small-scale window demonstrates advantages during the early growth stages, while the opposite holds during the later growth stages; (2) TFs derived from 45° direction represent the optimal choice for estimating rice AGB. During the four crucial growth stages, this selection improved performance in AGB estimation with R2 = 0.76 to 0.83 and rRMSE = 13.62% to 21.33%. Furthermore, the estimation accuracy for the entire growth season is R2 =0.84 and rRMSE =21.07%. However, there is no consensus regarding the selection of the worst TFs computation direction; (3) Correlation (Cor), Mean, and Homogeneity (Hom) from the first principal component image reflecting internal information of rice plant and Contrast (Con), Dissimilarity (Dis), and Second Moment (SM) from the second principal component image expressing edge texture are more important to estimate rice AGB among the whole growth stages; and (4) Considering the optimal parameters, the accuracy of texture-based AGB estimation slightly outperforms the estimation accuracy based on spectral reflectance alone. In summary, the present study can help researchers confident use of GLCM-based TFs to enhance the estimation accuracy of physiological and biochemical parameters of crops.

Identification of EIMD Level Differences Between Long- and Short Head of Biceps Brachii Using Echo Intensity and GLCM Texture Features

ABSTRACT Purpose: This study aimed to compare the time-course changes of exercise-induced muscle damage (EIMD) levels in the long head of biceps brachii (LHB) and short head of the biceps brachii (SHB) using echo intensity (EI) and to determine the efficiency of the gray level co-occurrence matrix (GLCM) texture parameters. Methods: The participants performed 30 maximal eccentric contractions of the elbow flexor. Along with muscle damage indicators, including circumference, range of motion, muscle soreness, and maximal voluntary isometric contraction (MVIC), the EI and GLCM texture features of the LHB and SHB was also assessed using B-mode ultrasonography. All measurements were assessed pre- and immediately post-exercise and after 24, 48, 72, and 96 h. Results: The muscle damage indicators indicated significant changes after the eccentric contractions (p < 0.01 for circumference, range of motion, muscle soreness, and MVIC). The EI of LHB significantly increased following the contractions (p < 0.01), but that of SHB did not (p > 0.05). In contrast, for the GLCM texture parameters, there were significant changes in the SHB (p < 0.01 for homogeneity, energy, and entropy). Conclusion: Thus, this study demonstrated that EIMD severity is different between LHB and SHB even within the same muscle. In the GLCM features, the time course of SHB after eccentric contraction revealed different patterns compared with those of LHB. Therefore, even if there are no changes in EI within a target muscle following muscle contractions, new information on muscle quality can be obtained through GLCM analysis.

Quantitative Study on Salinity Estimation of Salt-Affected Soils by Combining Different Types of Crack Characteristics Using Ground-Based Remote Sensing Observation

Soil salinity is one of the parameters used for determining the extent of soil salinization. During water evaporation, the surface of salt-affected soils in the Songnen Plain, China, exhibits obvious shrinkage and cracking phenomena due to the high salt content. The aim of this current study is to quantify the influence of the salt content on the surface shrinkage–cracking process and to achieve quantitative extraction of soil salinity parameters based on different crack parameter types. In order to achieve the above objectives, a controlled shrinkage–cracking experiment was conducted. Subsequently, three kinds of crack characteristics such as crack length, box-counting dimension, and 12 gray-level co-occurrence matrix (GLCM) texture features were quantitatively extracted from the standard binary crack patterns. In order to predict the soil physical–chemical properties of salt-affected soils in the Songnen Plain, three models such as multiple linear regression (MLR), multiple stepwise regression (MSR), and artificial neural network (ANN) were developed and compared based on the crack length, box-counting dimension, and the first two principal components of GLCM texture features. The results show that the extent of desiccation cracks was determined by soil salinity since the water film caused by exchangeable cations and the thickness of DDL determined by soil salinity can promote desiccation cracking. Although the three methods have high prediction accuracy for Na+, electrical conductivity (EC), and total soil salinity, the ANN-based method showed the best prediction with R2 values for Na+, EC, and soil salinity as high as 0.91, 0.91, and 0.89, and ratio of performance to deviation (RPD) values for Na+, EC, and soil salinity corresponding to 2.96, 3.47, and 2.95.

Exploring the Use of Orthophotos in Google Earth Engine for Very High-Resolution Mapping of Impervious Surfaces: A Data Fusion Approach in Wuppertal, Germany

Germany aims to reduce soil sealing to under 30 hectares per day by 2030 to address negative environmental impacts from the expansion of impervious surfaces. As cities adapt to climate change, spatially explicit very high-resolution information about the distribution of impervious surfaces is becoming increasingly important for urban planning and decision-making. This study proposes a method for mapping impervious surfaces in Google Earth Engine (GEE) using a data fusion approach of 0.9 m colour-infrared true orthophotos, digital elevation models, and vector data. We conducted a pixel-based random forest (RF) classification utilizing spectral indices, Grey-Level Co-occurrence Matrix texture features, and topographic features. Impervious surfaces were mapped with 0.9 m precision resulting in an Overall Accuracy of 92.31% and Kappa-Coefficient of 84.62%. To address challenges posed by high-resolution imagery, we superimposed the RF classification results with land use data from Germany’s Authoritative Real Estate Cadastre Information System (ALKIS). The results show that 25.26% of the city of Wuppertal is covered by impervious surfaces coinciding with a government-funded study from 2020 based on Sentinel-2 Copernicus data that defined a proportion of 25.22% as built-up area. This demonstrates the effectiveness of our method for semi-automated mapping of impervious surfaces in GEE to support urban planning on a local to regional scale.

Detection and diagnosis of melanoma skin cancers in dermoscopic images using pipelined internal module architecture (PIMA) method.

Detection and diagnosis of melanoma skin cancer is important to save the life of humans. The main objective of this article is to perform both detection and diagnosis of the skin cancers in dermoscopy images. Both skin cancer detection and diagnosis system uses deep learning architectures for the effective performance improvement as the main objective. The detection process involves by identifying the cancer affected skin dermoscopy images and the diagnosis process involves by estimating the severity levels of the segmented cancer regions in skin images. This article proposes parallel CNN architecture for the classification of skin images into either melanoma or healthy. Initially, color map histogram equalization (CMHE) method is proposed in this article to enhance the source skin images and then thick and thin edges are detected from the enhanced skin image using the Fuzzy system. The gray-level co-occurrence matrix (GLCM) and Law's texture features are extracted from the edge detected images and these features are optimized using genetic algorithm (GA) approach. Further, the optimized features are classified by the developed pipelined internal module architecture (PIMA) of deep learning structure. The cancer regions in the classified melanoma skin images are segmented using mathematical morphological process and these segmented cancer regions are diagnosed into either mild or severe using the proposed PIMA structure. The proposed PIMA-based skin cancer classification system is applied and tested on ISIC and HAM 10000 skin image datasets. RESEARCH HIGHLIGHTS: The melanoma skin cancer is detected and classified using dermoscopy images. The skin dermoscopy images are enhanced using color map histogram equalization. GLCM and Law's texture features are extracted from the enhanced skin images. To propose pipelined internal module architecture (PIMA) for the classification of skin images.

Quantitative Texture Analysis of Parotid Gland Ultrasound Images Yield Higher Correlation with Scintigraphy than Semiquantitative Scoring in Primary Sjögren's Syndrome Patients.

Ultrasound (US) can detect salivary gland abnormalities in primary Sjögren's syndrome (SS). This study aimed to compare the correlation among the semiquantitative US scores, texture features, and the quantitative salivary gland scintigraphy (SGS) results. This retrospective study included 11 patients who were diagnosed with primary SS and underwent US examinations of the parotid glands and SGS simultaneously. We evaluated SGS quantitatively based on the calculation of maximum accumulation ratio (MAR) and stimulated excretion fraction (EF). The US findings were accessed through the semiquantitative Outcome Measures in Rheumatology scoring system and by gray-level co-occurrence matrix (GLCM) texture analysis. Spearman's rank correlation tests were performed. A significant moderate negative correlation was noted between the semiquantitative US score and MAR (rho = -0.57, P = 0.006), but not with EF (rho = -0.11, P = 0.613). The GLCM texture metrics, including contrast, dissimilarity, and homogeneity, were all determined to be significantly associated with both MAR and EF. The GLCM contrast correlated moderately to MAR (rho = -0.66, P = 0.001). The GLCM homogeneity highly correlated to EF (rho = 0.74, P < 0.001). The contrast and homogeneity can still discriminate the changes in MAR and EF in the subgroups with the same semiquantitative US scores. US findings on parotid gland can correlate with SGS results when analyzed based on GLCM texture features. With the GLCM texture metrics, US appears to be an excellent imaging tool for the assessment of the parotid glands in primary SS patients.

Building Change Detection Based on a Gray-Level Co-Occurrence Matrix and Artificial Neural Networks

The recovery phase following an earthquake event is essential for urban areas with a significant number of damaged buildings. A lot of changes can take place in such a landscape within the buildings’ footprints, such as total or partial collapses, debris removal and reconstruction. Remote sensing data and methodologies can considerably contribute to site monitoring. The main objective of this paper is the change detection of the building stock in the settlement of Vrissa on Lesvos Island during the recovery phase after the catastrophic earthquake of 12 June 2017, through the analysis and processing of UAV (unmanned aerial vehicle) images and the application of Artificial Neural Networks (ANNs). More specifically, change detection of the settlement’s building stock by applying an ANN on Gray-Level Co-occurrence Matrix (GLCM) texture features of orthophotomaps acquired by UAVs was performed. For the training of the ANN, a number of GLCM texture features were defined as the independent variable, while the existence or not of structural changes in the buildings were defined as the dependent variable, assigning, respectively, the values 1 or 0 (binary classification). The ANN was trained based on the Levenberg–Marquardt algorithm, and its ability to detect changes was evaluated on the basis of the buildings’ condition, as derived from the binary classification. In conclusion, the GLCM texture feature changes in conjunction with the ANN can provide satisfactory results in predicting the structural changes of buildings with an accuracy of almost 92%.

Application of Two-Dimensional Entropy Measures to Detect the Radiographic Signs of Tooth Resorption and Hypercementosis in an Equine Model.

Dental disorders are a serious health problem in equine medicine, their early recognition benefits the long-term general health of the horse. Most of the initial signs of Equine Odontoclastic Tooth Resorption and Hypercementosis (EOTRH) syndrome concern the alveolar aspect of the teeth, thus, the need for early recognition radiographic imaging. This study is aimed to evaluate the applicability of entropy measures to quantify the radiological signs of tooth resorption and hypercementosis as well as to enhance radiographic image quality in order to facilitate the identification of the signs of EOTRH syndrome. A detailed examination of the oral cavity was performed in eighty horses. Each evaluated incisor tooth was assigned to one of four grade-related EOTRH groups (0-3). Radiographs of the incisor teeth were taken and digitally processed. For each radiograph, two-dimensional sample (SampEn2D), fuzzy (FuzzEn2D), permutation (PermEn2D), dispersion (DispEn2D), and distribution (DistEn2D) entropies were measured after image filtering was performed using Normalize, Median, and LaplacianSharpening filters. Moreover, the similarities between entropy measures and selected Gray-Level Co-occurrence Matrix (GLCM) texture features were investigated. Among the 15 returned measures, DistEn2D was EOTRH grade-related. Moreover, DistEn2D extracted after Normalize filtering was the most informative. The EOTRH grade-related similarity between DistEn2D and Difference Entropy (GLCM) confirms the higher irregularity and complexity of incisor teeth radiographs in advanced EOTRH syndrome, demonstrating the greatest sensitivity (0.50) and specificity (0.95) of EOTRH 3 group detection. An application of DistEn2D to Normalize filtered incisor teeth radiographs enables the identification of the radiological signs of advanced EOTRH with higher accuracy than the previously used entropy-related GLCM texture features.

Vegetation Mapping with Random Forest Using Sentinel 2 and GLCM Texture Feature—A Case Study for Lousã Region, Portugal

Vegetation mapping requires accurate information to allow its use in applications such as sustainable forest management against the effects of climate change and the threat of wildfires. Remote sensing provides a powerful resource of fundamental data at different spatial resolutions and spectral regions, making it an essential tool for vegetation mapping and biomass management. Due to the ever-increasing availability of free data and software, satellites have been predominantly used to map, analyze, and monitor natural resources for conservation purposes. This study aimed to map vegetation from Sentinel-2 (S2) data in a complex and mixed vegetation cover of the Lousã district in Portugal. We used ten multispectral bands with a spatial resolution of 10 m, and four vegetation indices, including Normalized Difference Vegetation Index (NDVI), Green Normalized Difference Vegetation Index (GNDVI), Enhanced Vegetation Index (EVI), and Soil Adjusted Vegetation Index (SAVI). After applying principal component analysis (PCA) on the 10 S2A bands, four texture features, including mean (ME), homogeneity (HO), correlation (CO), and entropy (EN), were derived for the first three principal components. Textures were obtained using the Gray-Level Co-Occurrence Matrix (GLCM). As a result, 26 independent variables were extracted from S2. After defining the land use classes using an object-based approach, the Random Forest (RF) classifier was applied. The map accuracy was evaluated by the confusion matrix, using the metrics of overall accuracy (OA), producer accuracy (PA), user accuracy (UA), and kappa coefficient (Kappa). The described classification methodology showed a high OA of 90.5% and kappa of 89% for vegetation mapping. Using GLCM texture features and vegetation indices increased the accuracy by up to 2%; however, classification using GLCM texture features and spectral bands achieved the highest OA (92%), indicating the texture features′ capability in detecting the variability of forest species at stand level. The ME and CO showed the highest contribution to the classification accuracy among the GLCM textures. GNDVI outperformed other vegetation indices in variable importance. Moreover, using only S2A spectral bands, especially bands 11, 12, and 2, showed a high potential to classify the map with an OA of 88%. This study showed that adding at least one GLCM texture feature and at least one vegetation index into the S2A spectral bands may effectively increase the accuracy metrics and tree species discrimination.

Cloud Computing-Based Framework for Breast Tumor Image Classification Using Fusion of AlexNet and GLCM Texture Features with Ensemble Multi-Kernel Support Vector Machine (MK-SVM).

Breast cancer is common among women all over the world. Early identification of breast cancer lowers death rates. However, it is difficult to determine whether these are cancerous or noncancerous lesions due to their inconsistencies in image appearance. Machine learning techniques are widely employed in imaging analysis as a diagnostic method for breast cancer classification. However, patients cannot take advantage of remote areas as these systems are unavailable on clouds. Thus, breast cancer detection for remote patients is indispensable, which can only be possible through cloud computing. The user is allowed to feed images into the cloud system, which is further investigated through the computer aided diagnosis (CAD) system. Such systems could also be used to track patients, older adults, especially with disabilities, particularly in remote areas of developing countries that do not have medical facilities and paramedic staff. In the proposed CAD system, a fusion of AlexNet architecture and GLCM (gray-level cooccurrence matrix) features are used to extract distinguishable texture features from breast tissues. Finally, to attain higher precision, an ensemble of MK-SVM is used. For testing purposes, the proposed model is applied to the MIAS dataset, a commonly used breast image database, and achieved 96.26% accuracy.

Application of the Two-Dimensional Entropy Measures in the Infrared Thermography-Based Detection of Rider: Horse Bodyweight Ratio in Horseback Riding.

As obesity is a serious problem in the human population, overloading of the horse’s thoracolumbar region often affects sport and school horses. The advances in using infrared thermography (IRT) to assess the horse’s back overload will shortly integrate the IRT-based rider-horse fit into everyday equine practice. This study aimed to evaluate the applicability of entropy measures to select the most informative measures and color components, and the accuracy of rider:horse bodyweight ratio detection. Twelve horses were ridden by each of the six riders assigned to the light, moderate, and heavy groups. Thermal images were taken pre- and post-exercise. For each thermal image, two-dimensional sample (SampEn), fuzzy (FuzzEn), permutation (PermEn), dispersion (DispEn), and distribution (DistEn) entropies were measured in the withers and the thoracic spine areas. Among 40 returned measures, 30 entropy measures were exercise-dependent, whereas 8 entropy measures were bodyweight ratio-dependent. Moreover, three entropy measures demonstrated similarities to entropy-related gray level co-occurrence matrix (GLCM) texture features, confirming the higher irregularity and complexity of thermal image texture when horses worked under heavy riders. An application of DispEn to red color components enables identification of the light and heavy rider groups with higher accuracy than the previously used entropy-related GLCM texture features.

Multi-region radiomics for artificially intelligent diagnosis of breast cancer using multimodal ultrasound

PurposeThe ultrasound (US) diagnosis of breast cancer is usually based on a single-region of a whole breast tumor from a single ultrasonic modality, which limits the diagnostic performance. Multiple regions on multimodal US images of breast tumors may all have useful information for diagnosis. This study aimed to propose a multi-region radiomics approach with multimodal US for artificially intelligent diagnosis of malignant and benign breast tumors. Materials and methodsFirstly, radiomics features were extracted from five regions of interest (ROIs) on B-mode US and contrast-enhanced ultrasound (CEUS) images, including intensity statistics, gray-level co-occurrence matrix texture features and binary texture features. The multiple ROIs included the whole tumor region, strongest perfusion region, marginal region and surrounding region. Secondly, a deep neural network, composed of the point-wise gated Boltzmann machine and the restricted Boltzmann machine, was adopted to comprehensively learn and select features. Thirdly, the support vector machine was used for classification between benign and malignant breast tumors. Finally, five single-region classification models were generated from five ROIs, and they were fused to form an integrated classification model. ResultsExperimental evaluation was conducted on multimodal US images of breast from 187 patients with breast tumors (68 malignant and 119 benign). Under five-fold cross-validation, the classification accuracy, sensitivity, specificity, Youden's index and area under the receiver operating characteristic curve (AUC) with our model were 87.1% ± 3.3%, 77.4% ± 11.8%, 92.4% ± 7.2%, 69.8% ± 8.6% and 0.849 ± 0.043, respectively. Our model was significantly better than single-region single-modal methods in terms of the AUC and accuracy (p < 0.05). ConclusionIn addition to the whole tumor region, the other regions including the strongest perfusion region, marginal region and surrounding region on US images can assist breast cancer diagnosis. The multi-region multimodal radiomics model achieved the best classification results. Our artificially intelligent model would be potentially useful for clinical diagnosis of breast cancer.

Quantitative Response of Gray-Level Co-Occurrence Matrix Texture Features to the Salinity of Cracked Soda Saline-Alkali Soil.

Desiccation cracking during water evaporation is a common phenomenon in soda saline–alkali soils and is mainly determined by soil salinity. Therefore, quantitative measurement of the surface cracking status of soda saline–alkali soils is highly significant in different applications. Texture features can help to determine the mechanical properties of soda saline–alkali soils, thus improving the understanding of the mechanism of desiccation cracking in saline–alkali soils. This study aims to provide a new standard describing the surface cracking conditions of soda saline–alkali soil on the basis of gray-level co-occurrence matrix (GLCM) texture analysis and to quantitatively study the responses of GLCM texture features to soil salinity. To achieve this, images of 200 field soil samples with different surface cracks were processed and calculated for GLCMs under different parameters, including directions, gray levels, and step sizes. Subsequently, correlation analysis was then conducted between texture features and electrical conductivity (EC) values. The results indicated that direction had little effect on the GLCM texture features, and that four selected texture features, contrast (CON), angular second moment (ASM), entropy (ENT), and homogeneity (HOM), were the most correlated with EC under a gray level of 2 and step size of 1 pixel. The results also showed that logarithmic models can be used to accurately describe the relationships between EC values and GLCM texture features of soda saline–alkali soils in the Songnen Plain of China, with calibration R2 ranging from 0.88 to 0.92, and RMSE from 2.12 × 10−4 to 9.68 × 10−3, respectively. This study can therefore enhance the understanding of desiccation cracking of salt-affected soil to a certain extent and can also help to improve the detection accuracy of soil salinity.

Comparative study on the abilities of different crack parameters to estimate the salinity of soda saline-alkali soil in Songnen Plain, China

Salinity is commonly considered to be the main factor determining the crack extent of clayey soda saline-alkali soil in the Songnen Plain in China. However, there are great variations among different parameters in quantifying the extent of desiccation cracks in salt-affected soil, leading to substantial uncertainty in their abilities to characterize soil salinity. This study aimed to analyze the relationships between different types of crack parameters and the salinity of soil samples to establish optimal prediction models for the electrical conductivity (EC) values. To achieve these objectives, 104 soil samples with different salinity levels were obtained and pre-processed based on a unified standard for binary crack patterns. Thereafter, three common types of crack parameters including the crack intensity factor (CIF); box-counting dimensions under equal-partitions of 2, 3, 5, and 7; and four gray-level co-occurrence matrix (GLCM) texture features were extracted for correlation coefficients with the EC values of the soil samples based on a series of regression analyses. The results indicate that although different types of crack parameters all have a clear correlation with EC, CIF shows a poor relationship with EC values compared to those of the fractal dimensions and the GLCM texture features. The CIF, box-counting fractal dimensions based on 2 equal-partition, and contrast (CON) texture feature were then selected as the most ideal indices to develop exponential regression models for EC estimation. In addition, fitting results from verification work showed that CON was the best predictor of EC (R2 of 0.85), with an accuracy much higher than box-counting dimension based on 2 equal-partition (R2 of 0.68) and CIF (R2 of only 0.56).

A New Texture Segmentation Method with Energy-driven Parametric Active Contour Model Based on Jensen-Tsallis Divergence

Texture image segmentation plays an important role in various computer vision tasks. Active contour models are one of the most efficient and popular methods for identifying the purpose and segmentation of objects in the image. This paper presents a parametric active contour model (PACM) with a robust minimization framework based on image texture energy. First, the texture features of the original image are extracted using gray level co-occurrence matrix (GLCM). Subsequently, based on the GLCM texture features inside and outside the active contour, Jensen-Tsallis divergence of energies is calculated. The Jensen-Tsallis divergence is added to the parametric active contour using the balloon equation. The divergence is maximum at the boundary between the foreground and background of the image, which results in minimizing the active contour equation at the boundary of the target object. This global minimization energy function with texture feature can avoid the existence of local minima in the PACM models. Also, as opposed to previous models, the proposed model only requires the initial contour and is not dependent on the distance of the initial contour from the target object. In terms of segmentation accuracy and efficiency, experiments with synthetic and natural images demonstrate that the proposed approach obtains more satisfactory results than the previous state-of-the-art methods.

Wheat Yellow Rust Disease Infection Type Classification Using Texture Features.

Wheat is a staple crop of Pakistan that covers almost 40% of the cultivated land and contributes almost 3% in the overall Gross Domestic Product (GDP) of Pakistan. However, due to increasing seasonal variation, it was observed that wheat is majorly affected by rust disease, particularly in rain-fed areas. Rust is considered the most harmful fungal disease for wheat, which can cause reductions of 20–30% in wheat yield. Its capability to spread rapidly over time has made its management most challenging, becoming a major threat to food security. In order to counter this threat, precise detection of wheat rust and its infection types is important for minimizing yield losses. For this purpose, we have proposed a framework for classifying wheat yellow rust infection types using machine learning techniques. First, an image dataset of different yellow rust infections was collected using mobile cameras. Six Gray Level Co-occurrence Matrix (GLCM) texture features and four Local Binary Patterns (LBP) texture features were extracted from grayscale images of the collected dataset. In order to classify wheat yellow rust disease into its three classes (healthy, resistant, and susceptible), Decision Tree, Random Forest, Light Gradient Boosting Machine (LightGBM), Extreme Gradient Boosting (XGBoost), and CatBoost were used with (i) GLCM, (ii) LBP, and (iii) combined GLCM-LBP texture features. The results indicate that CatBoost outperformed on GLCM texture features with an accuracy of 92.30%. This accuracy can be further improved by scaling up the dataset and applying deep learning models. The development of the proposed study could be useful for the agricultural community for the early detection of wheat yellow rust infection and assist in taking remedial measures to contain crop yield.