Co-occurrence Matrix Research Articles

A time-dependent explainable radiomic analysis from the multi-omic cohort of CPTAC-Pancreatic Ductal Adenocarcinoma

Background and ObjectiveIn Pancreatic Ductal Adenocarcinoma (PDA), multi-omic models are emerging to answer unmet clinical needs to derive novel quantitative prognostic factors. We realized a pipeline that relies on survival machine-learning (SML) classifiers and explainability based on patients’ follow-up (FU) to stratify prognosis from the public-available multi-omic datasets of the CPTAC-PDA project. Materials and MethodsAnalyzed datasets included tumor-annotated radiologic images, clinical, and mutational data. A feature selection was based on univariate (UV) and multivariate (MV) survival analyses according to Overall Survival (OS) and recurrence (REC). In this study, we considered seven multi-omic datasets and compared four SML classifiers: Cox, survival random forest, generalized boosted, and support vector machines (SVM). For each classifier, we assessed the concordance (C) index on the validation set. The best classifiers for the validation set on both OS and REC underwent explainability analyses using SurvSHAP(t), which extends SHapley Additive exPlanations (SHAP). ResultsAccording to OS, after UV and MV analyses we selected 18/37 and 10/37 multi-omic features, respectively. According to REC, based on UV and MV analyses we selected 10/35 and 5/35 determinants, respectively. Generally, SML classifiers including radiomics outperformed those modelled on clinical or mutational predictors. For OS, the Cox model encompassing radiomic, clinical, and mutational features reached 75 % of C index, outperforming other classifiers. On the other hand, for REC, the SVM model including only radiomics emerged as the best-performing, with 68 % of C index. For OS, SurvSHAP(t) identified the first order Median Gray Level (GL) intensities, the gender, the tumor grade, the Joint Energy GL Co-occurrence Matrix (GLCM), and the GLCM Informational Measures of Correlations of type 1 as the most important features. For REC, the first order Median GL intensities, the GL size zone matrix Small Area Low GL Emphasis, and first order variance of GL intensities emerged as the most discriminative. ConclusionsIn this work, radiomics showed the potential for improving patients’ risk stratification in PDA. Furthermore, a deeper understanding of how radiomics can contribute to prognosis in PDA was achieved with a time-dependent explainability of the top multi-omic predictors.

Image Processing and Support Vector Machine (SVM) for Classifying Environmental Stress Symptoms of Pepper Seedlings Grown in a Plant Factory

Environmental factors such as temperature, humidity, light, and CO2 influence plant growth, and unfavorable environmental conditions cause stress in plants, producing symptoms in their early growth stages. The increasing importance of optimizing crop management strategies has led to a rising demand for the precise evaluation of stress symptoms during early plant growth. Advanced technologies are transforming plant health monitoring through enabling image-based stress analysis. Machine learning (ML) models can effectively identify the important features and morphological changes connected with various stress conditions through the use of large datasets acquired from high-resolution plant images. Therefore, the objective of this study was to develop a method for classifying the early-stage stress symptoms of pepper seedlings and enabling their identification and quantification using image processing and a support vector machine (SVM). Two-week-old pepper seedlings were grown under different temperatures (20, 25, and 30 °C), light intensity levels (50, 250, and 450 µmol m−2s−1), and day–night hours (8/16, 10/14, and 16/8) in five controlled plant growth chambers. Images of the seedling canopies were captured daily using a low-cost red, green, and blue (RGB) camera over a two-week period. Eighteen color features, nine texture features using the gray-level co-occurrence matrix (GLCM), and one morphological feature were extracted from each image. A two-way ANOVA and multiple mean comparison (Duncan) analysis were used to determine the statistical significance of the treatment effects. To reduce feature overlap, sequential feature selection (SFS) was applied, and a support vector machine (SVM) was used for stress classification. The SFS method was used to identify the optimal features for the classification model, leading to substantial increases in stress classification accuracy. The SVM model, using these selected features, achieved a classification accuracy of 82% without the SFS and 86% with the SFS. To address overfitting, 5- and 10-fold cross-validation were used, resulting in MAEs of 0.138 and 0.163 for the polynomial kernel, respectively. The SVM model, evaluated with the ROC curve and confusion matrix, achieved a classification accuracy of 85%. This classification approach enables real-time stress monitoring, allowing growers to optimize environmental conditions and enhance seedling growth. Future directions include integrating this system into automated cultivation environments to enable continuous, efficient stress monitoring and response, further improving crop management and productivity.

Analysis on typical characteristics and causes of coal mine gas explosion accidents in China.

Large-scale coal mine gas explosion (CMGE) accidents have occurred occasionally and exerted a devastating effect on society. Therefore, it is essential to systematically identify the characteristics and association rules of causes of CMGE accidents through analysis on large-scale CMGE accident reports. In this study, 298 large-scale CMGE accidents in China from 2000 to 2021 were taken as the data sample, and mathematical statistical methods were adopted to analyze their general characteristics, coupling cross characteristics, and characteristics of gas accumulation and ignition sources. Moreover, the text mining technology and the Apriori algorithm were used for exploring the formation mechanism of CMGE accidents, during which 46 main causal factors were identified and 59 strong association rules were obtained. Furthermore, an accident causation network was constructed based on the co-occurrence matrix. The key causal items and sets of CMGE accidents were clarified through network centrality analysis. According to the research results, electrical equipment failure, cable short circuit, mine lamp misfire, hot-line work, and blasting spark are the key ignition sources of CMGE. Fan failure, airflow short circuit, and local ventilation fan damage are the main causes of gas accumulation. Besides, the confidence levels of two association rules of "static spark-fan failure" and "blasting spark-airflow short circuit" are higher than 70%, indicating that they are the two dominant risk-coupling paths of gas explosions. In addition, six causes appear frequently in the shortest risk paths of gas explosion and are closely related to other causes, i.e., fan failure, local ventilation fan damage, static sparks, electrical equipment failure, self-heating ignition, and friction impact sparks. This study provides a new perspective on identifying causes of accidents and their complex association mechanisms from accident report data for practical guidance in risk assessment and accident prevention.

Rapid and nondestructive identification of rice storage year using hyperspectral technology

Rice is the main staple food for more than half of the world's population. Consumption of long-stored rice will have adverse effects on the human body. Here, we proposed the near-infrared (NIR) hyperspectral imaging (HSI) technique to distinguish rice from different storage years. Multiplicative Scatter Correction (MSC), Standard Normalize Variate (SNV) and 1st Derivative (1st) were used for the pretreatment of HSI data. In order to reduce dimensional spectral features, Principal Component Analysis (PCA) and t-distributed Stochastic Neighbor Embedding (tSNE) were used for data visualization. Besides, spectral characteristic wavelengths were extracted by competitive adaptive reweighted sampling (CARS) and least absolute shrinkage and selection operator (Lasso). Simultaneously, the textural features of rice were analyzed by Local Binary Pattern (LBP), Gray-Level Co-occurrence Matrix (GLCM) and Tamura algorithms. In order to realize feature fusion of spectra and texture, Support Vector Machine (SVM) model was optimized using the Whale optimization algorithm (WOA) and Extreme Gradient Boosting (XGBoost) model were established based on spectral features and textural features. Compared to other models, feature fusion model showed an excellent result with an accuracy of 98.89%. Experimental results suggested that HSI technology can be served as an effective method for rice detection.

Visualization-based comprehensive feature representation with improved EfficientNet for malicious file and variant recognition

Malicious file attacks seriously affect network and data security, and recognizing malicious files and variants is crucial for preventing network attacks. Faced with the challenge of traditional methods in quickly, effectively, and efficiently recognizing malicious files or variants, visualization-based feature representation methods have shown promising results. However, practical applications encounter issues such as loss of crucial information, high spatiotemporal overhead, and the need for model performance improvement. Therefore, this paper introduces a novel recognition framework focusing on feature representation and model performance. The framework uses the proposed visualization-based comprehensive feature representation method (VCFR) to extract file information into the Gray-Level Co-occurrence Matrix (GLCM), 2-gram frequency matrix, and interval 2-gram frequency matrix, followed by feature fusion to generate the three-channel RGB images. Subsequently, the proposed lightweight model is applied for recognizing those files, which utilizes ideas such as group convolution, channel shuffle, and attention mechanisms to improve model performance while significantly reducing model parameters, size, and FLOPs. In summary, through a series of experiments conducted on manually collected malicious file dataset (MFD) and public dataset MMCC, the proposed framework significantly outperformed other state-of-the-art technologies and has F1-Score as high as 94.10% and 98.58%, respectively, further verifying its outstanding effectiveness and efficiency.

A Hybrid Segmentation Algorithm for Rheumatoid Arthritis Diagnosis Using X-ray Images

Rheumatoid Arthritis (RA) is a chronic autoimmune illness that occurs in the joints, resulting in inflammation, pain, and stiffness. X-ray examination is one of the most common diagnostic procedures for RA, but manual X-ray image analysis has limitations because it is a time-consuming procedure and is prone to errors. A specific algorithm aims to a lay stable and accurate segmenting of carpal bones from hand bone images, which is vitally important for identifying rheumatoid arthritis. The algorithm demonstrates several stages, starting with Carpal bone Region of Interest (CROI) specification, dynamic thresholding, and Gray Level Co-occurrence Matrix (GLCM) application for texture analysis. To get the clear edges of the image, the component is first converted to the greyscale function and thresholding is carried out to separate the hand from the background. The pad region is identified to obtain the contours of it, and the CROI is defined by the bounding box of the largest contour. The threshold value used in the CROI method is given a dynamic feature that can separate the carpal bones from the surrounding tissue. Then the GLCM texture analysis is carried out, calculating the number of pixel neighbors, with the specific intensity and neighbor relations of the pixels. The resulting feature matrix is then employed to extract features such as contrast and energy, which are later used to categorize the images of the affected carpal bone into inflamed and normal. The proposed technique is tested on a rheumatoid arthritis image dataset, and the results show its contribution to diagnosis of the disease. The algorithm efficiently divides carpal bones and extracts the signature parameters that are critical for correct classification of the inflammation in the cartilage images.

Classification method of seabed sonar image substrate based on ELM-AdaBoost

The results of sediment classification are affected by the measurement environment. The water depth has a significant impact on the sound propagation, and the acoustic characteristics will be different under different water depths. In addition, seabed topography, sediment types and their distribution, acoustic frequency, equipment types and settings, and suspended substances in water will all affect the original sonar data. In order to obtain accurate classification results, a seabed sonar image classification method based on Elm AdaBoost is proposed. The original sound intensity data is compensated for gain and the anomaly is eliminated. After preprocessing the multi beam sonar data, the image texture feature is extracted from the gray level co-occurrence matrix as the feature vector for classification, and the elm classifier is constructed. The elm is enhanced by AdaBoost. The calculated feature is input into the elm AdaBoost network for sediment classification, and the result is output. Simulation results show that the proposed method effectively improves the accuracy of sediment classification, and verifies the feasibility of this method.

A hybrid hue saturation lightness, gray level co-occurrence matrix, and k-nearest neighbour for palm-sugar classification

<span lang="EN-US">In recent years, there has been an increasing demand for high-quality raw materials driven by consumers and the food industry. This study aims to build a model to predict the type of </span><span lang="IN">palm</span><span lang="EN-US"> sugar using a hybrid method of hue</span><span lang="IN">-</span><span lang="EN-US">saturation</span><span lang="IN">-l</span><span lang="EN-US">ightness (HSL), gray level co-occurrence matrix (GLCM), and K-nearest neighbor (KNN). The price of palm sugar is determined based on the type and ingredients used. However, due to the lack of public knowledge in distinguishing the types of </span><span lang="IN">palm</span><span lang="EN-US"> sugar, there is the potential for price manipulation that can harm the community. The accuracy rate of 9</span><span lang="IN">7.6</span><span lang="EN-US">% of the palm sugar type prediction results shows that the model that was built has worked very well. The results have practical implications, such as developing automated systems to classify palm species in specific industries to benefit economics and operational efficiency. Future research directions may explore the integration of advanced machine-learning techniques and real-time image processing for further improving classification performance and scalability in industrial applications</span><span lang="IN">.</span>

Classification and identification of pest, diseases and nutrient deficiency in paddy using layer based EMD phase features with decision tree

Pest attack, disease incidence, and nutrient deficiency are the major factors limiting the yield of paddy. Therefore, the paper proposes a classification system for the identification of pest, disease, and nutrient deficiency classes. This approach initially preprocesses leaf images using entropy filtering followed by a leaf segmentation process. Multiple layers are then constructed on the leaf image through which features are extracted. The Gray Level Co-occurrence Matrix (GLCM) algorithm and Principal Component Analysis (PCA) are used to extract the global texture features of the leaf image. A 1D-signal sequence is constructed on each layer, which is decomposed by the Empirical Mode Decomposition algorithm from which the phase features are estimated. The features are trained/classified using the decision tree classifiers that classify the pest attack, disease incidence, and nutrient deficiency categories. The proposed approach provides a precision, accuracy, specificity, sensitivity, and F1-score of 97 %, 97.88 %, 96.52 %, 96.7 %, and 96.7 % respectively.

Reimagining otitis media diagnosis: A fusion of nested U-Net segmentation with graph theory-inspired feature set

Otitis media (OM) is a common infection or inflammation of the middle ear causing conductive hearing loss that primarily affects children and may delay speech, language, and cognitive development. OM can manifest itself in different forms, and can be diagnosed using (video) otoscopy (visualizing the tympanic membrane) or (video) pneumatic otoscopy and tympanometry. Accurate diagnosis of OM is challenging due to subtle differences in otoscopic features. This research aims to develop an automated computer-aided design (CAD) system to assist clinicians in diagnosing OM using otoscopy images. The ground truths, generated manually and validated by otolaryngologists, are utilized to train the proposed nested U-Net++ model. Ten clinically relevant gray level co-occurrence matrix (GLCM) and morphological features were extracted from the segmented Region of Interest (ROI) and validated for OM classification based on a statistical significance test. These features serve as input for a Graph Neural Network (GNN) model, the base model in our research. An optimized GNN model is proposed after ablation study of the base model. Three datasets, one private dataset, and two public ones have been used, where the private dataset is utilized for both training and testing, and the public datasets are used to test the robustness of the proposed GNN model only. The proposed GNN model obtained the highest accuracy in diagnosing OM: 99.38 %, 93.51 %, and 91.38 % for the private dataset, public dataset1, and public dataset2, respectively. The proposed methodology and results of this research might enhance clinicians' effectiveness in diagnosing OM.

Identifying liver cancer cells using cascaded convolutional neural network and gray level co-occurrence matrix techniques

<p>Liver cancer has a high mortality rate, especially in South Asia, East Asia, and Sub-Saharan Africa. Efforts to reduce these rates focus on detecting liver cancer at all stages. Early detection allows more treatment options, though symptoms may not always be apparent. The staging process evaluates tumor size, location, lymph node involvement, and spread to other organs. Our research used the CLD staging system, assessing tumor size (C), lymph nodes (L), and distant invasion (D). We applied a deep learning approach with a cascaded convolutional neural network (CNN) and gray level co-occurrence matrix (GLCM)-based texture features to distinguish benign from malignant tumors. The method validated with the cancer imaging archive (TCIA) dataset, demonstrating superior accuracy compared to existing techniques.</p>

Identification of rice crop diseases using gray level co-occurrence matrix (GLCM) and Neuro-GA classifier

Identification of rice crop diseases using gray level co-occurrence matrix (GLCM) and Neuro-GA classifier

Plant Monitoring System Using Gray Level Co-occurrence Matrix and Weight Based Artificial Neural Network Algorithm over Internet of Things

The potential deployment of the plant monitoring system in cutting-edge technologies is currently generating a great deal of interest. A new IoT-based technology is used to track both the development and wellness of the plant. Setting up cross-device connectivity over the internet is the idea underlying IoT devices. It is a sizable network that links people and various interconnected elements in order to gather and transmit data. This research article aims to generate a manufacturing Internet of Things (IoT) based plant monitoring system that uses IoT sensors to detect environmental conditions. The IoT term is used to link objects to the internet and make it easier for consumers to obtain data. The technology can accurately perceive the surroundings in agriculture and convey the data to users. The system keeps track of several factors like soil moisture, temperature, and light intensity. The method begins with the collection of plant images and noise reduction pre-processing. Once the images have been segmented, they are done so utilizing the Region based K-Means Clustering (RKMC) technique. Following that, Gray Level Co-occurrence Matrix (GLCM) is utilized to extract features, with a focus on extracting the more informative characteristics like color, texture, and shape features. The classifying process is completed by utilizing Weight based Artificial Neural Network (WANN) algorithm for improving the plant monitoring system performance significantly. It offers IoT-based solutions to categorize plant illnesses and observe variables including soil moisture, air temperature, and pH values. Te findings of the suggested GLCM-WANN algorithm show better performers than existing methods for obtained values of computation complexity, accuracy, Mean Absolute Error (MAE), and Root Mean Square Error (RMSE).

Enhancing medical image classification via federated learning and pre-trained model

The precise classification of medical images is crucial in various healthcare applications, especially in fields like disease diagnosis and treatment planning. In recent times, machine-intelligent models are desired to work in remote settings. However, the potential privacy concerns that arise from sharing confidential patient information to train traditional centralized machine learning models cannot be ignored. Federated learning (FL) offers a promising method for collaborative training on distributed data held by various entities, ensuring the privacy of patient information. This study evaluated the efficiency of the pre-trained models in the FL environment for medical image classification. The Convolutional Neural Network (CNN) model with Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP), along with the EfficientNet model, are being used as the local models. The trainable parameters from the local models are fed as input for building the global model. Pre-trained models trained on extensive datasets, possess valuable characteristics that can be utilized by FL models trained on proprietary datasets. Implementing this method can improve the efficacy and precision of FL models while also ensuring data confidentiality. The proposed model is evaluated using two distinct medical imaging datasets: Magnetic Resonance Image(MRI) and Computed Tomography (CT) scan images. The research highlights the advantages of utilizing pre-trained models in federated learning for medical image classification (MIC). The model’s performance is assessed acrossseveral assessment criteria, demonstrating the model exhibited a satisfactory accuracy rate of 97.4% and 98.8% for MRI and CT scan images, respectively. The model is evaluated concerning to Diagnostic Odds Ratio (DOR), where the proposed global model has exhibited 1164.54 for the MRI images and 6825.17 for CT scan images, and the values have outperformed the pretrained model.

Background adaptive PosMarker based on online generation and detection for locating watermarked regions in photographs

Robust watermarking technology can embed invisible messages in screens to trace the source of unauthorized screen photographs. Locating the four vertices of the embedded region in the photograph is necessary, as existing watermarking methods require geometric correction of the embedded region before revealing the message. Existing localization methods suffer from a performance trade-off: either causing unaesthetic visual quality by embedding visible markers or achieving poor localization precision, leading to message extraction failure. To address this issue, we propose a background adaptive position marker, PosMarker, based on the gray level co-occurrence matrix and the noise visibility function. Besides, we propose an online generation scheme that employs a learnable generator to cooperate with the detector, allowing joint optimization between the two. This simultaneously improves both visual quality and detection precision. Extensive experiments demonstrate the superior localization precision of our PosMarker-based method compared to others.

Exploring the Influence of Object, Subject, and Context on Aesthetic Evaluation through Computational Aesthetics and Neuroaesthetics

Background: In recent years, computational aesthetics and neuroaesthetics have provided novel insights into understanding beauty. Building upon the findings of traditional aesthetics, this study aims to combine these two research methods to explore an interdisciplinary approach to studying aesthetics. Method: Abstract artworks were used as experimental materials. Based on traditional aesthetics and in combination, features of composition, tone, and texture were selected. Computational aesthetic methods were then employed to correspond these features to physical quantities: blank space, gray histogram, Gray Level Co-occurrence Matrix (GLCM), Local Binary Pattern (LBP), and Gabor filters. An electroencephalogram (EEG) experiment was carried out, in which participants conducted aesthetic evaluations of the experimental materials in different contexts (genuine, fake), and their EEG data were recorded to analyze the impact of various feature classes in the aesthetic evaluation process. Finally, a Support Vector Machines (SVMs) was utilized to model the feature data, Event-Related Potentials (ERPs), context data, and subjective aesthetic evaluation data. Result: Behavioral data revealed higher aesthetic ratings in the genuine context. ERP data indicated that genuine contexts elicited more negative deflections in the prefrontal lobes between 200 and 1000 ms. Class II compositions demonstrated more positive deflections in the parietal lobes at 50–120 ms, while Class I tones evoked more positive amplitudes in the occipital lobes at 200–300 ms. Gabor features showed significant variations in the parieto-occipital area at an early stage. Class II LBP elicited a prefrontal negative wave with a larger amplitude. The results of the SVM models indicated that the model incorporating aesthetic subject and context data (ACC = 0.76866) outperforms the model using only parameters of the aesthetic object (ACC = 0.68657). Conclusion: A positive context tends to provide participants with a more positive aesthetic experience, but abstract artworks may not respond to this positivity. During aesthetic evaluation, the ERP data activated by different features show a trend from global to local. The SVM model based on multimodal data fusion effectively predicts aesthetics, further demonstrating the feasibility of the combined research approach of computational aesthetics and neuroaesthetics.

Texture feature-aware consistency for semi-supervised honeycomb lung lesion segmentation

Accurate segmentation of honeycomb lung lesions from lung CT images is crucial for the clinical diagnosis of a wide range of lung diseases. Existing semi-supervised segmentation methods ignore the rich texture feature information in honeycomb lung CT images, resulting in inaccurate predictions in the lesion region. Therefore, this paper proposes a semi-supervised honeycomb lung lesion segmentation framework using texture feature-aware consistency. The framework consists of a shared encoder, a main decoder, and three auxiliary decoders. The different outputs produced by the decoders are used to compute the Grey Level Co-occurrence Matrix and extract texture features, respectively, and further to compute the loss of texture feature-aware consistency. In pseudo-labeling supervision, the uncertainty of each output is computed to bootstrap the pseudo-labeling supervision loss. For the small lesion recognition omission problem, a pseudo-label refinement module is constructed to reuse the multi-scale features of the encoder, focusing on small-scale lesions, and refining the pseudo-labels. Experimental results show that the proposed method outperforms other methods in the honeycomb lung segmentation task, achieving a Dice coefficient of 77.62 using 20% labeled data. Additionally, experiments on publicly available datasets further demonstrate the generalizability of the proposed method. The code is available at https://github.com/Oran9er/TFC-Net-main.

Diagnosing the MRI brain tumour images through RNN-LSTM

According to the World Health Organization, cancer is the second most common cause of death worldwide (WHO). Death from cancer may sometimes be avoided through early diagnosis, although this is not always practicable. A tumour, unlike cancer, may be benign, pre-cancerous, or malignant. Contrary to malignant tumours, benign tumours may frequently be surgically removed and seldom metastasize to other organs or tissues. The method most often used to differentiate between various types of tumours is magnetic resonance imaging (MRI) (MRI). But because it depends on human subjectivity, it could be challenging for one person to see a lot of data. The radiologist's ability to identify brain tumours early mostly depends on their level of training. Before determining whether the tumour is benign or malignant, the diagnostic process for it could not be finished. A biopsy is often carried out to determine if the tissue is benign or cancerous. The biopsy of a brain tumour is often delayed until the last brain operation, in contrast to tumours discovered elsewhere in the body. An efficient diagnostics tool for tumour segmentation and classification from MRI images is crucial to obtaining accurate diagnoses, avoiding surgery, and eliminating subjectivity. The classification and segmentation of the tumour part of the MRI brain picture is the goal of this study. Prior to feature extraction in the first study, pre-processing is done using the Gray Level Co-occurrence Matrix (GLCM). Based on these features, the data is then separated into normal, glioma, meningioma, and pituitary groups. In prior studies, classification was handled by traditional Deep Neural Networks (DNN), with the best weights selected using optimization methods. Accordingly, a recent study recommends including Long Short-Term Memory based on Recurrent Neural Networks (RNN) (LSTM). The Local Direction Ternary Pattern (LDTP), the Gray Level Co-occurrence Matrix (GLCM), and the Le-Net features are all combined in the proposed Hybrid GLCM-LDTP-Le-Net Feature extraction approach. The hybrid parameters produced by the feature extraction process and the brain MRI data are used by the RNN-LSTM model to categorise the data as benign or malignant. By removing mixed features from the input data, the suggested hybrid feature extraction improves the learnt models' accuracy. The accuracy of 98.99 % of the suggested hybrid feature extraction approach was higher than the current CNN-based model methodologies.

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.

Age-related changes in ultrasound-assessed muscle composition and postural stability

While the simultaneous degradation of muscle composition and postural stability in aging are independently highly investigated due to their association with fall risk, the interplay between the two has received little attention. Thus, the purpose of this study is to explore how age-related changes in muscle composition relate to postural stability. To that aim, we collected posturography measures and ultrasound images of the dominant Vastus Lateralis and Biceps Brachii from 32 young (18–35 year old) and 34 older (65–85 year old) participants. Muscle properties were quantified with echo-intensity and texture-based metrics derived from gray-level co-occurrence matrix analysis, and postural stability with the variability of the center of pressure during bipedal stance tasks. Ultrasound parameters revealed that young muscle possessed lower echo-intensity and higher homogeneity compared to the elderly. Echo-intensity and muscle thickness, and several texture-based parameters possessed outstanding young versus older classification performance. A canonical correlation analysis demonstrated a significant relationship between ultrasound and postural measures only within the young group (r = 0.53, p < 0.002), where those with ‘better’ muscle composition displayed larger postural sways. Our results indicate that, in older individuals, postural stability and muscle composition, two common fall risk factors, are unrelated. In view of this decoupling, both may contribute independently to fall risk. Furthermore, our data support the view that texture-based parameters provide a robust alternative to echo-intensity in providing markers of muscle composition.