Muscle Composition Analysis of Ultrasound Images: A Narrative Review of Texture Analysis

Remote and In-person Supervised Exercise in Patients with Knee Osteoarthritis (RISE-KOA): study protocol for a non-inferiority randomized controlled trial

BACKGROUND

Knee osteoarthritis (OA) is a prevalent joint condition resulting in years lived with disability. A first-line treatment recommended by clinical guidelines is the therapeutic exercise to control pain and improve physical function. One possible approach for exercise supervision is telehealth using video calls, as it can be an effective alternative to in-person physical therapy for treating musculoskeletal conditions, expanding community access to physical rehabilitation. In this scenario, this study aims to investigate whether a muscle-strengthening exercise program for the lower limbs supervised remotely via video calls is as effective as the same exercise applied in person for improving pain, physical function, condition-specific patient-reported outcomes (PROMs), psychological well-being, sleep quality, functional performance, and quadriceps muscle architecture.

METHODS

A Remote and In-person Supervised Exercise in Patients with Knee Osteoarthritis (RISE-KOA) study is a parallel, two-armed, single-blinded protocol for a non-inferiority randomized controlled trial. Forty-eight participants aged 45 years or more, with a symptomatic and radiographic diagnosis of unilateral or bilateral knee OA (grade II or III according to Kellgren and Lawerence) will be randomly assigned to a remote exercise group supervised by video calls or in-person exercise group supervised at a physiotherapy clinic. Both groups will receive the same muscle-strengthening exercises for the lower extremities for 12 weeks. Follow-ups will be conducted during treatment (6 weeks), after treatment (12 weeks), and 18 weeks after randomization. The primary outcomes will be pain intensity and physical function during (6 weeks) and after treatment (12 weeks). Secondary outcomes will be condition-specific PROMs, psychological well-being, sleep quality, functional performance, and quadriceps muscle architecture.

DISCUSSION

We hypothesize that muscle strengthening exercise supervised remotely via video calls will not be inferior to in-person exercise at a physiotherapy clinic in terms of primary and secondary outcomes in patients with knee OA.

TRIAL REGISTRATION

The study was prospectively registered at ClinicalTrials.gov (NCT06101797). Registered on Oct 26, 2023.

Diagnosis of Sarcopenia Using Convolutional Neural Network Models Based on Muscle Ultrasound Images: Prospective Multicenter Study

BACKGROUND

Early detection is clinically crucial for the strategic handling of sarcopenia, yet the screening process, which includes assessments of muscle mass, strength, and function, remains complex and difficult to access.

OBJECTIVE

This study aims to develop a convolutional neural network model based on ultrasound images to simplify the diagnostic process and promote its accessibility.

METHODS

This study prospectively evaluated 357 participants (101 with sarcopenia and 256 without sarcopenia) for training, encompassing three types of data: muscle ultrasound images, clinical information, and laboratory information. Three monomodal models based on each data type were developed in the training cohort. The data type with the best diagnostic performance was selected to develop the bimodal and multimodal model by adding another one or two data types. Subsequently, the diagnostic performance of the above models was compared. The contribution ratios of different data types were further analyzed for the multimodal model. A sensitivity analysis was performed by excluding 86 cases with missing values and retaining 271 complete cases for robustness validation. By comprehensive comparison, we finally identified the optimal model (SARCO model) as the convenient solution. Moreover, the SARCO model underwent an external validation with 145 participants (68 with sarcopenia and 77 without sarcopenia) and a proof-of-concept validation with 82 participants (19 with sarcopenia and 63 without sarcopenia) from two other hospitals.

RESULTS

The monomodal model based on ultrasound images achieved the highest area under the receiver operator characteristic curve (AUC) of 0.827 and F1-score of 0.738 among the three monomodal models. Sensitivity analysis on complete data further confirmed the superiority of the ultrasound images model (AUC: 0.851; F1-score: 0.698). The performance of the multimodal model demonstrated statistical differences compared to the best monomodal model (AUC: 0.845 vs 0.827; P=.02) as well as the two bimodal models based on ultrasound images+clinical information (AUC: 0.845 vs 0.826; P=.03) and ultrasound images+laboratory information (AUC: 0.845 vs 0.832, P=0.035). On the other hand, ultrasound images contributed the most evidence for diagnosing sarcopenia (0.787) and nonsarcopenia (0.823) in the multimodal models. Sensitivity analysis showed consistent performance trends, with ultrasound images remaining the dominant contributor (Shapley additive explanation values: 0.810 for sarcopenia and 0.795 for nonsarcopenia). After comprehensive clinical analysis, the monomodal model based on ultrasound images was identified as the SARCO model. Subsequently, the SARCO model achieved satisfactory prediction performance in the external validation and proof-of-concept validation, with AUCs of 0.801 and 0.757 and F1-scores of 0.727 and 0.666, respectively.

CONCLUSIONS

All three types of data contributed to sarcopenia diagnosis, while ultrasound images played a dominant role in model decision-making. The SARCO model based on ultrasound images is potentially the most convenient solution for diagnosing sarcopenia.

TRIAL REGISTRATION

Chinese Clinical Trial Registry ChiCTR2300073651; https://www.chictr.org.cn/showproj.html?proj=199199.

Improving the Reliability of Muscle Tissue Characterization Post-Stroke: A Secondary Statistical Analysis of Echotexture Features

Background/Objectives: Ultrasound (US) imaging and echotexture analysis are emerging techniques for assessing muscle tissue quality in the post-stroke population. Clinical studies suggest that echovariation (EV) and echointensity (EI) serve as objective indicators of muscle impairment, although methodological limitations hinder their clinical translation. This secondary analysis aimed to refine the assessment of echotexture by using robust statistical techniques. Methods: A total of 130 regions of interest (ROIs) extracted from the gastrocnemius medialis of 22 post-stroke individuals were analyzed. First, inter-examiner reliability between two physiotherapists was assessed by using Cohen's kappa for muscle impairment classification (low/high) for each echotexture feature. For each examiner, the correlation between the classification of the degree of impairment and the modified Heckmatt scale for each feature was analyzed. The dataset was then reduced to 44 ROIs (one image per leg per patient) and assessed by three physiotherapists to analyze inter-examiner reliability by using Light´s kappa and correlation between both assessment methods globally. Statistical differences in 21 echotexture features were evaluated according to the degree of muscle impairment. A binary logistic regression model was developed by using features with a Cohen's kappa value greater than 0.9 as predictors. Results: A strong and significant degree of agreement was observed among the three examiners regarding the degree of muscle impairment (Kappalight = 0.85, p < 0.001), with nine of the 21 features showing excellent inter-examiner reliability. The correlation between muscle impairment classification with the modified Heckmatt scale was very high and significant both globally and for each echotexture feature. Significant differences (<0.05) were found for EV, EI, dissimilarity, energy, contrast, maximum likelihood, skewness, and the modified Heckmatt scale. Logistic regression highlighted dissimilarity, entropy, EV, Gray-Level Uniformity (GLU), and EI as the main predictors of muscle tissue impairment. The EV and EI models showed high explanatory power (Nagelkerke's pseudo-R2 = 0.74 and 0.76) and robust classification performance (AUC = 94.20% and 95.45%). Conclusions: This secondary analysis confirms echotexture analysis as a reliable tool for post-stroke muscle assessment, validating EV and EI as key indicators while identifying dissimilarity, entropy, and GLU as additional relevant features.

Sonographic image texture features in muscle tissue-mimicking material reduce variability introduced by probe angle and gain settings compared to traditional echogenicity

Cost-effective and portable ultrasonography offers a promising approach for monitoring skeletal muscle damage and quality in many contexts. However, echogenicity analysis relies on precise transducer orientations and machine parameters, posing challenges for data pooling across different raters and settings. Muscle texture analysis offers a potential means of reducing inter-rater and machine-setting variability. Scans were assessed at nine angles, controlled using a custom transducer shell and software. Scans were performed three times, and different gains were applied. All scans were performed on a muscle tissue-mimicking phantom to eliminate biological variability. Intra-angle and intra-gain variability and internal consistency were assessed via coefficient of variation (CV%) and Cronbach's alpha (αc). Spearman's (ρ) correlations were employed to determine the relationship between echogenicity and each texture feature. Entropy (angle: CV=2.7-7.6%; gain: CV=10.5%; αc=0.86), and inverse difference moment (angle: CV=3.7-9.8%; gain: CV=16.5%; αc=0.87) were less variable than echogenicity (angle: CV=6.4-19.4%; gain: CV=39.0%; αc=0.82). Angular second moment (angle: CV=17.9-116.6%; gain: CV=71.6%; αc=0.68), contrast (angle: CV=7.8-14.7%; gain: CV=41.8%;αc=0.75), and correlation (angle: CV=9.0-13.5%; gain: CV=28.6%; αc=0.49) features were generally more variable. Entropy (ρ=0.82-0.98, p≤0.011) and inverse difference moment (ρ=-0.98--0.83, p≤0.008), were more strongly correlated with echogenicity than angular second moment (ρ=-0.98--0.77, p≤0.016), contrast (ρ=0.53-0.98, p≤0.15), and correlation (ρ=-0.25--0.19, p=0.520-0.631). Entropy and inverse difference moment features may allow data sharing between laboratory and clinical settings with ultrasound machine parameters and raters of varying skill levels. Clinical and mechanistic studies are required to determine if texture features can replace echogenicity assessments.

Changes in Muscle Quality Following Short-Term Resistance Training in Older Adults: A Comparison of Echo Intensity and Texture Analysis

BACKGROUND

Skeletal muscle echo intensity (EI) is associated with functional outcomes in older adults, but resistance training interventions have shown mixed results. Texture analysis has been proposed as a novel approach for assessing muscle quality, as it captures spatial relationships between pixels. It is unclear whether texture analysis is able to track changes following resistance training.

OBJECTIVE

To examine changes in first-order (EI) and second-order (texture) features of muscle quality following lower-body resistance training in older adults.

METHODS

Twelve older adults (2 males, 10 females; mean ± SD age = 70 ± 5 years) completed 6 weeks of resistance training, consisting of twice-weekly sessions at 85% of estimated 1RM. Testing included ultrasound imaging of the rectus femoris (RF) and vastus lateralis (VL), 5-repetition maximum (5RM) leg extension strength, and maximal voluntary isometric contraction (MVIC) force. Ultrasound images were analyzed for EI and texture features using gray-level co-occurrence matrix (GLCM) analysis.

RESULTS

Large improvements were observed in 5RM leg extension strength (p < 0.001, effect size [ES] = 2.09), MVIC force (p = 0.006, ES = 0.969), and RF EI (uncorrected: p = 0.003, ES = 0.727; corrected: p = 0.012, ES = 0.864). No significant changes were observed in muscle size, VL EI, or texture features for either muscle.

CONCLUSION

Short-term resistance training improved strength and RF EI. However, texture analysis features were not sensitive to changes following training. These findings suggest that traditional EI measures may be more appropriate than texture analysis for tracking changes in muscle quality following resistance training in older adults.

Machine learning-driven Heckmatt grading in facioscapulohumeral muscular dystrophy: A novel pathway for musculoskeletal ultrasound analysis

OBJECTIVE

This study introduces a machine learning approach to automate muscle ultrasound analysis, aiming to improve objectivity and efficiency in segmentation, classification, and Heckmatt grading.

METHODS

We analyzed a dataset of 25,005 B-mode images from 290 participants (110 FSHD patients) acquired using a single Esaote ultrasound scanner with a standardized protocol. Manual segmentation and Heckmatt grading by experienced observers served as ground truth. K-Net was utilized for simultaneous muscle segmentation and classification. Heckmatt scoring was approached with texture analysis, using a modified scale with three classes (Normal, Uncertain, Abnormal). Radiomics features were extracted using PyRadiomics and automatic scoring was performed using XGBoost, incorporating explainability through SHAP analysis.

RESULTS

K-Net demonstrated high accuracy in skeletal muscle classification and segmentation, with Intersection over Union ranging from 73.40 to 74.03 across folds. Heckmatt's grading achieved an Area Under Curve of 0.95, 0.87, and 0.97 for classes Normal, Uncertain, and Abnormal. SHAP analysis highlighted histogram-based features as critical for visual scoring.

CONCLUSION

This study proposes and validates an automatic pipeline for muscle ultrasound analysis, leveraging machine learning for segmentation, classification, and quantitative Heckmatt grading.

SIGNIFICANCE

Automating the visual assessment of muscle ultrasound images improves the objectivity and efficiency of muscle ultrasound, supporting clinical decision-making.

Radiomics with Ultrasound Radiofrequency Data for Improving Evaluation of Duchenne Muscular Dystrophy

Duchenne muscular dystrophy (DMD) is a rare and severe genetic neuromuscular disease, characterized by rapid progression and high mortality, highlighting the need for accurate ambulatory function assessment tools. Ultrasound imaging methods have been widely used for quantitative analysis. Radiomics, which converts medical images into data, combined with machine learning (ML), offers a promising solution. This study is aimed at utilizing radiomics to analyze different stages of data generated during B-mode image processing to evaluate the ambulatory function of DMD patients. The study included 85 participants, categorized into ambulatory and non-ambulatory groups based on their functional status. Ultrasound scans were utilized to capture backscattered radiofrequency data, which were then processed to generate envelope, normalized, and B-mode images. Radiomics analysis involved the manual segmentation of grayscale images and automatic feature extraction using specialized software, followed by feature selection using the maximal relevance and minimal redundancy method. The selected features were input into five ML algorithms, with model evaluation conducted via area under the receiver operating characteristic curve (AUROC). To ensure robustness, both leave-one-out cross-validation and repeated data splitting methods were employed. Additionally, multiple ML models were constructed and tested to assess their performance. The intensity values across all image types increased as walking ability declined, with significant differences observed between the ambulatory and non-ambulatory groups (p < 0.001). These groups exhibited similar diagnostic performance levels, with AUROC values below 0.8. However, radiofrequency (RF) images outperformed other types when radiomics was applied, notably achieving an AUROC value of 0.906. Additionally, combining multiple ML algorithms yielded a higher AUROC value of 0.912 using RF images as input. Radiomics analysis of RF data surpasses conventional B-mode imaging and other ultrasound-derived images in evaluating ambulatory function in DMD. Moreover, integrating multiple machine learning models further enhances classification performance. The proposed method in this study offers a promising framework for improving the accuracy and reliability of clinical follow-up evaluations, supporting more effective management of DMD. The code is available at https://github.com/Goldenyan/radiomicsUS .

Lung cancer detection with machine learning classifiers with multi-attribute decision-making system and deep learning model

Diseases of the airways and the other parts of the lung cause chronic respiratory diseases. The major cause of lung disease is tobacco smoke, along with risk factors such as dust, air pollution, chemicals, and frequent lower respiratory infections during childhood. Early detection of these diseases requires the analysis of medical images, which would aid doctors in providing effective treatment.This paper aims to classify lung X-ray images as benign or malignant and to identify the type of disease, such as Atelectasis, Infiltration, Nodule, and Pneumonia, if the disease is malignant. Machine learning (ML) approaches, combined with a multi-attribute decision-making method called Technique for Order Preference by Similarity to Ideal Solution (TOPSIS), are used to rank different classifiers. Additionally, the deep learning (DL) model Inception v3 is proposed. This method ranks the SVM with RBF as the best classifier among the others used in this approach. Furthermore, the results show that the deep learning model achieves the best accuracy of 97.05%, which is 11.8% higher than the machine learning approach using the same dataset.

Texture Analysis in Musculoskeletal Ultrasonography: A Systematic Review

Background: The objective of this systematic review was to summarize the findings of texture analyses of musculoskeletal ultrasound images and synthesize the information to facilitate the use of texture analysis on assessing skeletal muscle quality in various pathophysiological conditions. Methods: Medline, PubMed, Scopus, Web of Science, and Cochrane databases were searched from their inception until January 2025 using the PRISMA Diagnostic Test Accuracy and was registered at PROSPERO CRD42025636613. Information related to patients, interventions, ultrasound settings, texture analyses, muscles, and findings were extracted. The quality of evidence was evaluated using QUADAS-2. Results: A total of 38 studies using second-order and higher-order texture analysis met the criteria. The results indicated that no studies used an established reference standard (histopathology) to evaluate the accuracy of ultrasound texture analysis in diagnosing muscle quality. Alternative reference standards were compared, including various physiological, pathological, and pre-post intervention comparisons using over 200+ texture features of various muscles on diverse pathophysiological conditions. Conclusions: The findings of these included studies demonstrating that ultrasound texture analysis was able to discriminate changes in muscle quality using texture analysis between patients with pathological conditions and healthy conditions, including popular gray-level co-occurrence matrix (GLCM)-based contrast, correlation, energy, entropy, and homogeneity. Studies also demonstrated that texture analysis can discriminate muscle quality in various muscles under pathophysiological conditions although evidence is low because of bias in subject recruitment and lack of comparison with the established reference standard. This is the first systematic review of the use of texture analysis of musculoskeletal ultrasonography in assessing muscle quality in various muscles under diverse pathophysiological conditions.

Ultrasonographic examination of the maturational effect of maternal vitamin D use on fetal clavicle bone development

AIM

This study aimed to evaluate the effect of maternal vitamin D use during intrauterine life on fetal bone development using ultrasonographic image processing techniques.

MATERIALS AND METHODS

We evaluated 52 pregnant women receiving vitamin D supplementation and 50 who refused vitamin D supplementation. Ultrasonographic imaging was performed on the fetal clavicle at 37-40 weeks of gestation. The fetal clavicle images were compared with adult male clavicle images. The texture features obtained from these images were used for analysis.

RESULTS

No difference was observed in bone formation and destruction markers between the two groups. However, the texture analysis of ultrasonographic images revealed similarities in the characteristics of fetal clavicles in pregnant women receiving vitamin D supplementation and those of adult male clavicles.

CONCLUSIONS

Vitamin D supplementation in pregnancy has significant positive effects on fetal bone maturation besides contributing to maternal bone health. Texture feature analyses using ultrasonographic images successfully demonstrated fetal bone maturation.

Sex differences in quantitative ultrasonographic measurements of the rectus femoris in children

The distribution and amount of intramuscular fat and fibrous tissue can be influenced by biological sex and impact muscle quality in both the functional (force-generating capacity) and morphological (muscle composition) domains. While ultrasonography (US) has proven effective in assessing age- or sex-related differences in muscle quality, limited information is available on sex differences in children. Quantitative ultrasonographic measurements, such as echo intensity (EI), EI bands (number of pixels across 50-unit intervals) and texture, may offer a comprehensive framework for identifying sex differences in muscle composition. The aim of our study was to examine the effect of sex on the rectus femoris (RF) muscle quality in children. We used EI (mean and bands) and texture as muscle quality estimates derived from B-mode US. We hypothesised that RF muscle quality differs significantly between girls and boys. Additionally, we also hypothesised that there is a significant correlation between EI bands and texture. Forty-four non-active healthy children were recruited (n = 22 girls, 12.8 ± 1.5 years; and n = 22 boys, 13.5 ± 1.2 years). RF was assessed using EI mean, EI bands, and texture analysis (homogeneity and correlation) using the Gray-Level Co-Occurrence Matrix. The results revealed significant (p < 0.05) sex differences in RF EI bands and texture. Boys displayed higher values in the 0-50 EI band and had more homogeneous muscle texture than girls. Conversely, girls displayed greater values in the 51-100 EI band and had less homogenous texture compared to boys (p < 0.05). A positive correlation was observed between the 0-50 EI band and muscle homogeneity. However, the 51-100 EI band correlated negatively with homogeneity (p < 0.05), particularly for girls. In conclusion, our study revealed sex-specific differences in mean EI, EI bands, and texture of the RF muscle in children. The variations in the correlations between the first and second EI bands and texture reveal different levels of homogeneity in each band. This indicates that distinct muscle tissue constituents, such as intramuscular fat and/or connective tissue, may be reflected in EI bands. Overall, the methods used in this study may be useful for examining muscle quality in healthy children and those with medical conditions.

Characterizing Muscle Tissue Quality Post-Stroke: Echovariation as a Clinical Indicator

Background/Objectives: Strokes remain a major global health concern, contributing significantly to disability and healthcare costs. Currently, there are no established indicators to accurately assess the degree of muscle tissue impairment in stroke-affected individuals. However, ultrasound imaging with an echotexture analysis shows potential as a quantitative tool to assess muscle tissue quality. This study aimed to identify specific echotexture features in the gastrocnemius medialis that effectively characterize muscle impairment in post-stroke individuals. Methods: An observational study was conducted with 22 post-stroke individuals. A total of 21 echotexture features were extracted and analyzed, including first-order metrics, a grey-level co-occurrence matrix, and a grey-level run length matrix. The modified Heckmatt scale was also applied to correlate with the most informative echotexture features. Results: Among the features analyzed, echovariation (EV), echointensity, and kurtosis emerged as the most informative indicators of muscle tissue quality. The EV was highlighted as the primary feature due to its strong and significant correlation with the modified Heckmatt scale (r = -0.81, p < 0.001) and its clinical and technical robustness. Lower EV values were associated with poorer muscle tissue quality, while higher values indicated better quality. Conclusions: The EV may be used as a quantitative indicator for characterizing the gastrocnemius medialis muscle tissue quality in post-stroke individuals, offering a more nuanced assessment than traditional qualitative scales. Future studies should investigate the correlation between the EV and other clinical outcomes and explore its potential to monitor the treatment efficacy, enhancing its applicability in clinical practice.

Texture differences of microchambers and macrochambers in heel pads between the elderly with and without diabetes

OBJECTIVE

This study aims to use the texture analysis of ultrasound images to distinguish the features of microchambers (a superficial thinner layer) and macrochambers (a deep thicker layer) in heel pads between the elderly with and without diabetes, so as to preliminarily explore whether texture analysis can identify the potential injury characteristics of deep tissue under the influence of diabetes before the obvious injury signs can be detected in clinical management.

METHODS

Ultrasound images were obtained from the right heel (dominant leg) of eleven elderly people with diabetes (DM group) and eleven elderly people without diabetes (Non-DM group). The TekScan system was used to measure the peak plantar pressure (PPP) of each participant. Six gray-level co-occurrence matrix (GLCM) features including contrast, correlation, dissimilarity, energy, entropy, homogeneity were used to quantify texture changes in microchambers and macrochambers of heel pads.

RESULTS

Significant differences in GLCM features (correlation, energy and entropy) of macrochambers were found between the two groups, while no significant differences in all GLCM features of microchambers were found between the two groups. No significant differences in PPP and tissue thickness in the heel region were observed between the two groups.

CONCLUSIONS

In the elderly with diabetes who showed no significant differences in PPP and plantar tissue thickness compared to those without diabetes, several texture features of ultrasound images were found to be significantly different. Our finding indicates that texture features (correlation, energy and entropy) of macrochambers could be used for early detection of soft tissue damage associated with diabetes.

Exploring the associations between skeletal muscle echogenicity and physical function in aging adults: A systematic review with meta-analyses

BACKGROUND

Assessment and quantification of skeletal muscle within the aging population is vital for diagnosis, treatment, and injury/disease prevention. The clinical availability of assessing muscle quality through diagnostic ultrasound presents an opportunity to be utilized as a screening tool for function-limiting diseases. However, relationships between muscle echogenicity and clinical functional assessments require authoritative analysis. Thus, we aimed to (a) synthesize the literature to assess the relationships between skeletal muscle echogenicity and physical function in older adults (≥60 years), (b) perform pooled analyses of relationships between skeletal muscle echogenicity and physical function, and (c) perform sub-analyses to determine between-muscle relationships.

METHODS

CINAHL, Embase, MEDLINE, PubMed, and Web of Science databases were systematically searched to identify articles relating skeletal muscle echogenicity to physical function in older adults. Risk-of-bias assessments were conducted along with funnel plot examination. Meta-analyses with and without sub-analyses for individual muscles were performed utilizing Fisher's Z transformation for the most common measures of physical function. Fisher's Z was back-transformed to Pearson's r for interpretation.

RESULTS

Fifty-one articles (n = 5095, female = ∼2759, male = ∼2301, 72.5 ± 5.8 years, mean ± SD (1 study did not provide sex descriptors)) were extracted for review, with previously unpublished data obtained from the authors of 13 studies. The rectus femoris (n = 34) and isometric knee extension strength (n = 22) were the most accessed muscle and physical qualities, respectively. The relationship between quadriceps echogenicity and knee extensor strength was moderate (n = 2924, r = -0.36 (95% confidence interval: -0.38 to -0.32), p < 0.001), with all other meta-analyses (grip strength, walking speed, sit-to-stand, timed up-and-go) resulting in slightly weaker correlations (r:  -0.34 to -0.23, all p < 0.001). Sub-analyses determined minimal differences in predictive ability between muscle groups, although combining muscles (e.g., rectus femoris + vastus lateralis) often resulted in stronger correlations with maximal strength.

CONCLUSION

While correlations are modest, the affordable, portable, and noninvasive ultrasonic assessment of muscle quality is a consistent predictor of physical function in older adults. Minimal between-muscle differences suggest that echogenicity estimates of muscle quality are systemic. Therefore, practitioners may be able to scan a single muscle to estimate full-body skeletal muscle quality/composition, while researchers should consider combining multiple muscles to strengthen the model.

Brain tumor classification utilizing pixel distribution and spatial dependencies higher-order statistical measurements through explainable ML models

Brain tumors are among the most fatal and devastating diseases, and they often result in a significant reduction in life expectancy. The devising of treatment plans that can extend the lives of affected individuals hinges on an accurate diagnosis of these tumors. Identifying and analyzing large volumes of magnetic resonance imaging (MRI) data manually proves to be both challenging and time-consuming. As a result, there exists a pressing need for a reliable machine-learning approach to accurately diagnose brain tumors, and numerous methods have already been proposed over the last decade. In this paper, a novel, comprehensive approach is proposed for identifying and classifying a given MR brain image as abnormal. Three common brain diseases, namely glioma, meningioma, and pituitary tumor, are chosen as abnormal brains, and the Figshare MRI brain image dataset was collected from the Kaggle and IEEE websites. The proposed method is initiated by employing 1st-order statistics, 2nd-order statistics, and higher-order transformed (DWT) feature extraction to extract features from images. Then missing data is addressed and handled using KNNImputer, followed by the application of the ExtratreesClassifier and PCA feature selection methods to identify the most relevant features and reduce the dimensions of these features. Subsequently, the reduced features are submitted to seven machine learning models, namely RF, GB, CB, SVM, LGBM, DT, and LR. The strategy of k-fold cross-validation is utilized to enhance the performance of those models. Finally, the models are evaluated using XAI approaches, which ensure transparent decision-making processes and provide insights into the model's predictions. Remarkably, our approach achieves the highest accuracy, precision, recall, F1 score, MCC, Kappa, AUC-ROC, and R2, as well as the lowest loss, among the seven models evaluated, proving its effectiveness and applicability in multiple analytic applications relying on publicly available datasets.

Real-time artificial intelligence-based texture analysis of muscle ultrasound data for neuromuscular disorder assessment

Objective

Many artificial intelligence approaches to muscle ultrasound image analysis have not been implemented on usable devices in clinical neuromuscular medicine practice, owing to high computational demands and lack of standardised testing protocols. This study evaluated the feasibility of using real-time texture analysis to differentiate between various pathological conditions.

Methods

We analysed 17,021 cross-sectional ultrasound images of the biceps brachii of 75 participants, including 25 each with neurogenic disorders, myogenic disorders, and healthy controls. The size and location of the regions of interest were randomly selected to minimise bias. A random forest classifier utilising texture features such as Dissimilarity and Homogeneity was developed and deployed on a mobile PC, enabling real-time analysis.

Results

The classifier distinguished patients with an accuracy of 81 %. Echogenicity and Contrast from the Co-Occurrence Matrix were significant predictive features. Validation on 15 patients achieved accuracies of 78 %/93 % per image/patient over 15-second videos, respectively. The use of a mobile PC facilitated real-time estimation of the underlying pathology during ultrasound examination, without influencing procedures.

Conclusions

Real-time automatic texture analysis is feasible as an adjunct for the diagnosis of neuromuscular disorders.

Significance

Artificial intelligence using texture analysis with a light computational load supports the semi-quantitative evaluation of neuromuscular ultrasound.

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.

Non invasive techniques for direct muscle quality assessment after exercise intervention in older adults: a systematic review

BACKGROUND

The aging process induces neural and morphological changes in the human musculoskeletal system, leading to a decline in muscle mass, strength and quality. These alterations, coupled with shifts in muscle metabolism, underscore the essential role of physical exercise in maintaining and improving muscle quality in older adults. Muscle quality's morphological domain encompasses direct assessments of muscle microscopic and macroscopic aspects of muscle architecture and composition. Various tools exist to estimate muscle quality, each with specific technical requirements. However, due to the heterogeneity in both the studied population and study methodologies, there is a gap in the establishment of reference standards to determine which are the non-invasive and direct tools to assess muscle quality after exercise interventions. Therefore, the purpose of this review is to obtain an overview of the non-invasive tools used to measure muscle quality directly after exercise interventions in healthy older adults, as well as to assess the effects of exercise on muscle quality.

MAIN TEXT

To address the imperative of understanding and optimizing muscle quality in aging individuals, this review provides an overview of non-invasive tools employed to measure muscle quality directly after exercise interventions in healthy older adults, along with an assessment of the effects of exercise on muscle quality.

RESULTS

Thirty four studies were included. Several methods of direct muscle quality assessment were identified. Notably, 2 studies harnessed CT, 20 utilized US, 9 employed MRI, 2 opted for TMG, 2 adopted myotonometry, and 1 incorporated BIA, with several studies employing multiple tests. Exploring interventions, 26 studies focus on resistance exercise, 4 on aerobic training, and 5 on concurrent training.

CONCLUSIONS

There is significant diversity in the methods of direct assessment of muscle quality, mainly using ultrasound and magnetic resonance imaging; and a consistent positive trend in exercise interventions, indicating their efficacy in improving or preserving muscle quality. However, the lack of standardized assessment criteria poses a challenge given the diversity within the studied population and variations in methodologies.. These data emphasize the need to standardize assessment criteria and underscore the potential benefits of exercise interventions aimed at optimizing muscle quality.

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

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.

Association between physical fitness tests and neuromuscular properties

PURPOSE

While various fitness tests have been developed to assess physical performances, it is unclear how these tests are affected by differences, such as, in morphological and neural factors. This study was aimed to investigate associations between individual differences in physical fitness tests and neuromuscular properties.

METHODS

One hundred and thirty-three young adults participated in various general physical fitness tests and neuromuscular measurements. The appendicular skeletal muscle mass (ASM) was estimated by bioelectrical impedance analysis. Echo intensity (EI) was evaluated from the vastus lateralis. During submaximal knee extension force, high-density surface electromyography of the vastus lateralis was recorded and individual motor unit firings were detected. Y-intercept (i-MU) and slope (s-MU) from the regression line between the recruitment threshold and motor unit firing rate were calculated.

RESULTS

Stepwise multiple regression analyses revealed that knee extension strength could be explained (adjusted R2 = 0.712) by ASM (β = 0.723), i-MU (0.317), EI (- 0.177), and s-MU (0.210). Five-sec stepping could be explained by ASM (adjusted R2 = 0.212). Grip strength, side-stepping, and standing broad jump could be explained by ASM and echo intensity (adjusted R2 = 0.686, 0.354, and 0.627, respectively). Squat jump could be explained by EI (adjusted R2 = 0.640). Counter-movement jump could be explained by EI and s-MU (adjusted R2 = 0.631). On the other hand, i-MU and s-MU could be explained by five-sec stepping and counter-movement jump, respectively, but the coefficients of determination were low (adjusted R2 = 0.100 and 0.045).

CONCLUSION

Generally developed physical fitness tests were mainly explained by morphological factors, but were weakly affected by neural factors involved in performance.

Ultrasound-based assessment of the expression of inflammatory markers in the rectus femoris muscle of rats

Ultrasonographic characteristics of skeletal muscles are related to their health status and functional capacity, but they still provide limited information on muscle composition during the inflammatory process. It has been demonstrated that an alteration in muscle composition or structure can have disparate effects on different ranges of ultrasonogram pixel intensities. Therefore, monitoring specific clusters or bands of pixel intensity values could help detect echotextural changes in skeletal muscles associated with neurogenic inflammation. Here we compare two methods of ultrasonographic image analysis, namely, the echointensity (EI) segmentation approach (EI banding method) and detection of selective pixel intensity ranges correlated with the expression of inflammatory regulators using an in-house developed computer algorithm (r-Algo). This study utilized an experimental model of neurogenic inflammation in segmentally linked myotomes (i.e., rectus femoris (RF) muscle) of rats subjected to lumbar facet injury. Our results show that there were no significant differences in RF echotextural variables for different EI bands (with 50- or 25-pixel intervals) between surgery and sham-operated rats, and no significant correlations among individual EI band pixel characteristics and protein expression of inflammatory regulators studied. However, mean numerical pixel values for the pixel intensity ranges identified with the proprietary r-Algo computer program correlated with protein expression of ERK1/2 and substance P (both 86-101-pixel ranges) and CaMKII (86-103-pixel range) in RF, and were greater (p < 0.05) in surgery rats compared with their sham-operated counterparts. Our findings indicate that computer-aided identification of specific pixel intensity ranges was critical for ultrasonographic detection of changes in the expression of inflammatory mediators in neurosegmentally-linked skeletal muscles of rats after facet injury.

Development of Continuous Assessment of Muscle Quality and Frailty in Older Patients Using Multiparametric Combinations of Ultrasound and Blood Biomarkers: Protocol for the ECOFRAIL Study

BACKGROUND

Frailty resulting from the loss of muscle quality can potentially be delayed through early detection and physical exercise interventions. There is a demand for cost-effective tools for the objective evaluation of muscle quality, in both cross-sectional and longitudinal assessments. Literature suggests that quantitative analysis of ultrasound data captures morphometric, compositional, and microstructural muscle properties, while biological assays derived from blood samples are associated with functional information.

OBJECTIVE

This study aims to assess multiparametric combinations of ultrasound and blood-based biomarkers to offer a cross-sectional evaluation of the patient frailty phenotype and to track changes in muscle quality associated with supervised exercise programs.

METHODS

This prospective observational multicenter study will include patients aged 70 years and older who are capable of providing informed consent. We aim to recruit 100 patients from hospital environments and 100 from primary care facilities. Each patient will undergo at least two examinations (baseline and follow-up), totaling a minimum of 400 examinations. In hospital environments, 50 patients will be measured before/after a 16-week individualized and supervised exercise program, while another 50 patients will be followed up after the same period without intervention. Primary care patients will undergo a 1-year follow-up evaluation. The primary objective is to compare cross-sectional evaluations of physical performance, functional capacity, body composition, and derived scales of sarcopenia and frailty with biomarker combinations obtained from muscle ultrasound and blood-based assays. We will analyze ultrasound raw data obtained with a point-of-care device, along with a set of biomarkers previously associated with frailty, using quantitative real-time polymerase chain reaction and enzyme-linked immunosorbent assay. Additionally, we will examine the sensitivity of these biomarkers to detect short-term muscle quality changes and functional improvement after a supervised exercise intervention compared with usual care.

RESULTS

At the time of manuscript submission, the enrollment of volunteers is ongoing. Recruitment started on March 1, 2022, and ends on June 30, 2024.

CONCLUSIONS

The outlined study protocol will integrate portable technologies, using quantitative muscle ultrasound and blood biomarkers, to facilitate an objective cross-sectional assessment of muscle quality in both hospital and primary care settings. The primary objective is to generate data that can be used to explore associations between biomarker combinations and the cross-sectional clinical assessment of frailty and sarcopenia. Additionally, the study aims to investigate musculoskeletal changes following multicomponent physical exercise programs.

TRIAL REGISTRATION

ClinicalTrials.gov NCT05294757; https://clinicaltrials.gov/ct2/show/NCT05294757.

INTERNATIONAL REGISTERED REPORT IDENTIFIER (IRRID)

DERR1-10.2196/50325.

Non-invasive prediction of the chronic degree of lupus nephropathy based on ultrasound radiomics

OBJECTIVE

Through machine learning (ML) analysis of the radiomics features of ultrasound extracted from patients with lupus nephritis (LN), this attempt was made to non-invasively predict the chronicity index (CI)of LN.

METHODS

A retrospective collection of 136 patients with LN who had renal biopsy was retrospectively collected, and the patients were randomly divided into training set and validation set according to 7:3. Radiomics features are extracted from ultrasound images, independent factors are obtained by using LASSO dimensionality reduction, and then seven ML models were used to establish predictive models. At the same time, a clinical model and an US model were established. The diagnostic efficacy of the model is evaluated by analysis of the receiver operating characteristics (ROC) curve, accuracy, specificity, and sensitivity. The performance of the seven machine learning models was compared with each other and with clinical and US models.

RESULTS

A total of 1314 radiomics features are extracted from ultrasound images, and 5 features are finally screened out by LASSO for model construction, and the average ROC of the seven ML is 0.683, among which the Xgboost model performed the best, and the AUC in the test set is 0.826 (95% CI: 0.681-0.936). For the same test set, the AUC of clinical model constructed based on eGFR is 0.560 (95% CI: 0.357-0.761), and the AUC of US model constructed based on Ultrasound parameters is 0.679 (95% CI: 0.489-0.853). The Xgboost model is significantly more efficient than the clinical and US models.

CONCLUSION

ML model based on ultrasound radiomics features can accurately predict the chronic degree of LN, which can provide a valuable reference for clinicians in the treatment strategy of LN patients.

Identification of Myofascial Trigger Point Using the Combination of Texture Analysis in B-Mode Ultrasound with Machine Learning Classifiers

Myofascial pain syndrome is a chronic pain disorder characterized by myofascial trigger points (MTrPs). Quantitative ultrasound (US) techniques can be used to discriminate MTrPs from healthy muscle. In this study, 90 B-mode US images of upper trapezius muscles were collected from 63 participants (left and/or right side(s)). Four texture feature approaches (individually and a combination of them) were employed that focused on identifying spots, and edges were used to explore the discrimination between the three groups: active MTrPs (n = 30), latent MTrPs (n = 30), and healthy muscle (n = 30). Machine learning (ML) and one-way analysis of variance were used to investigate the discrimination ability of the different approaches. Statistically significant results were seen in almost all examined features for each texture feature approach, but, in contrast, ML techniques struggled to produce robust discrimination. The ML techniques showed that two texture features (i.e., correlation and mean) within the combination of texture features were most important in classifying the three groups. This discrepancy between traditional statistical analysis and ML techniques prompts the need for further investigation of texture-based approaches in US for the discrimination of MTrPs.

Assessment of short-term effect of platelet-rich plasma treatment of tendinosis using texture analysis of ultrasound images

BACKGROUND

Computer-aided diagnosis (i.e., texture analyses) tools are becoming increasingly beneficial methods to monitor subtle tissue changes. The aim of this pilot study was to investigate short-term effect of platelet rich plasma (PRP) treatment in supraspinatus and common extensor of the forearm tendinosis by using texture analysis of ultrasound (US) images as well as by clinical questionnaires.

PATIENTS AND METHODS

Thirteen patients (7 male and 6 female, age 36-60 years, mean age 51.2 ± 5.2) were followed after US guided PRP treatment for tendinosis of two tendons (9 patients with lateral epicondylitis and 4 with supraspinatus tendinosis). Clinical and US assessment was performed prior to as well as 3 months after PRP treatment with validated clinical questionnaires. Tissue response in tendons was assessed by using gray level run length matrix method (GLRLM) of US images.

RESULTS

All patients improved of tendinosis symptoms after PRP treatment according to clinical questionnaires. Almost all GLRLM features were statistically improved 3 months after PRP treatment. GLRLM-long run high gray level emphasis (LRLGLE) revealed the best moderate positive and statistically significant correlation after PRP (r = 0.4373, p = 0.0255), followed by GLRLM-low gray level run emphasis (LGLRE) (r = 0.3877, p = 0.05).

CONCLUSIONS

Texture analysis of tendinosis US images was a useful quantitative method for the assessment of tendon remodeling after minimally invasive PRP treatment. GLRLM features have the potential to become useful imaging biomarkers to monitor spatial and time limited tissue response after PRP, however larger studies with similar protocols are needed.

Gender differences in lateral pterygoid muscle in patients with anterior disk displacement

OBJECTIVE

To use quantitative MRI to assess gender differences in lateral pterygoid muscle (LPM) characteristics in patients with anterior disk displacement (ADD).

METHODS

Lateral pterygoid muscle of 51 patients diagnosed with temporomandibular joint disorders (TMD) who underwent T1-weighted Dixon and T1-mapping sequences were retrospectively analyzed. There were 34 female patients (10 with bilateral normal position disk [NP]; 24 with bilateral ADD) and 17 male patients (eight with bilateral NP; nine with bilateral ADD) among them. After controlling for age, differences in fat fraction, T1 value, volume and histogram features related to gender and disk status were tested with 2-way ANCOVA or Quade ANCOVA with Bonferroni correction.

RESULTS

Volume of LPM in NP was significantly smaller than that of ADD (p < 0.001). Fat fraction of LPM in females with NP was significantly higher than males with NP (p < 0.05). Females with ADD showed a significantly higher T1 value (p < 0.05), and higher intramuscular heterogeneity than males with ADD.

CONCLUSIONS

Lateral pterygoid muscle in female TMD patients presented more fatty infiltration in the NP stage and might present more fibrosis in the ADD stage compared with males. Together, this leads to more serious intramuscular heterogeneity during the pathogenesis of ADD in females.

Myofascial Trigger Point Identification in B-Mode Ultrasound: Texture Analysis Versus a Convolutional Neural Network Approach

OBJECTIVE

Myofascial pain syndrome (MPS) is one of the most common causes of chronic pain and affects a large portion of patients seen in specialty pain centers as well as primary care clinics. Diagnosis of MPS relies heavily on a clinician's ability to identify the presence of a myofascial trigger point (MTrP). Ultrasound can help, but requires the user to be experienced in ultrasound. Thus, this study investigates the use of texture features and deep learning strategies for the automatic identification of muscle with MTrPs (i.e., active and latent MTrPs) from normal (i.e., no MTrP) muscle.

METHODS

Participants (n = 201) were recruited from Toronto Rehabilitation Institute, and ultrasound videos of their trapezius muscles were acquired. This new data set consists of 1344 images (248 active, 120 latent, 976 normal) collected from these videos. For texture analysis, several features were investigated with varying parameters (i.e., region of interest size, feature type and pixel pair relationships). Convolutional neural networks (CNN) were also applied to observe the performance of deep learning approaches. Performance was evaluated based on the classification accuracy, micro F1-score, sensitivity, specificity, positive predictive value and negative predictive value.

RESULTS

The best CNN approach was able to differentiate between muscles with and without MTrPs better than the best texture feature approach, with F1-scores of 0.7299 and 0.7135, respectively.

CONCLUSION

The results of this study reveal the challenges associated with MTrP identification and the potential and shortcomings of CNN and radiomics approaches in detail.

A survey of testicular texture in canine ultrasound images

Introduction

Computer-based texture analysis provides objective data that can be extracted from medical images, including ultrasound images. One popular methodology involves the generation of a gray-level co-occurrence matrix (GLCM) from the image, and from that matrix, texture fractures can be extracted.

Methods

We performed texture analysis on 280 ultrasound testicular images obtained from 70 dogs and explored the resulting texture data, by means of principal component analysis (PCA).

Results

Various abnormal lesions were identified subjectively in 35 of the 280 cropped images. In 16 images, pinpoint-to-small, well-defined, hyperechoic foci were identified without acoustic shadowing. These latter images were classified as having "microliths." The remaining 19 images with other lesions and areas of non-homogeneous testicular parenchyma were classified as "other." In the PCA scores plot, most of the images with lesions were clustered. These clustered images represented by those scores had higher values for the texture features entropy, dissimilarity, and contrast, and lower values for the angular second moment and energy in the first principal component. Other data relating to the dogs, including age and history of treatment for prostatomegaly or chemical castration, did not show clustering on the PCA.

Discussion

This study illustrates that objective texture analysis in testicular ultrasound correlates to some of the visual features used in subjective interpretation and provides quantitative data for parameters that are highly subjective by human observer analysis. The study demonstrated a potential for texture analysis in prediction models in dogs with testicular abnormalities.

Hamstring Muscle Quality Properties Using Texture Analysis of Ultrasound Images

The aim of this study was to examine the intra- and inter-muscular differences of the hamstring muscles using textural analysis of ultrasound (US) images, and the relationship between textural indicators with hamstring torque. Transverse US scans were obtained from 10 young males from four different measurement sites along the thigh of each individual hamstring muscle at rest. Maximum-knee-flexion isometric torque measurements were also obtained. Texture analysis was applied to US images, and five gray-level co-occurrence matrix (GLCM) features were quantified: entropy (ENT), angular second moment (ASM), inverse difference moment (IDM), contrast (CON) and correlation (COR). The intraclass correlation coefficients ranged from 0.77 to 0.99, and the standard error of measurement ranged from 0.06 to 10.05%, indicating high test-retest reliability. Analysis of the variance indicated significant differences between measurement sites and individual muscles, with the proximal measurement sites having greater values for ASM, IDM and COR and lower values for ENT and CON compared with the distal sites. Additionally, only the COR at the proximal measurement site exhibited a significant relationship (r = -0.66) with strength. The present study indicated significant differences among hamstrings and measurement locations with respect to the textural analysis and may provide a novel indicator of hamstring functional properties.

Ultrasound Radiomics for the Detection of Early-Stage Liver Fibrosis

Objective: The study evaluates quantitative ultrasound (QUS) texture features with machine learning (ML) to enhance the sensitivity of B-mode ultrasound (US) for the detection of fibrosis at an early stage and distinguish it from advanced fibrosis. Different ML methods were evaluated to determine the best diagnostic model. Methods: 233 B-mode images of liver lobes with early and advanced-stage fibrosis induced in a rat model were analyzed. Sixteen features describing liver texture were measured from regions of interest (ROIs) drawn on B-mode images. The texture features included a first-order statistics run length (RL) and gray-level co-occurrence matrix (GLCM). The features discriminating between early and advanced fibrosis were used to build diagnostic models with logistic regression (LR), naïve Bayes (nB), and multi-class perceptron (MLP). The diagnostic performances of the models were compared by ROC analysis using different train-test sampling approaches, including leave-one-out, 10-fold cross-validation, and varying percentage splits. METAVIR scoring was used for histological fibrosis staging of the liver. Results: 15 features showed a significant difference between the advanced and early liver fibrosis groups, p < 0.05. Among the individual features, first-order statics features led to the best classification with a sensitivity of 82.1−90.5% and a specificity of 87.1−89.8%. For the features combined, the diagnostic performances of nB and MLP were high, with the area under the ROC curve (AUC) approaching 0.95−0.96. LR also yielded high diagnostic performance (AUC = 0.91−0.92) but was lower than nB and MLP. The diagnostic variability between test-train trials, measured by the coefficient-of-variation (CV), was higher for LR (3−5%) than nB and MLP (1−2%). Conclusion: Quantitative ultrasound with machine learning differentiated early and advanced fibrosis. Ultrasound B-mode images contain a high level of information to enable accurate diagnosis with relatively straightforward machine learning methods like naïve Bayes and logistic regression. Implementing simple ML approaches with QUS features in clinical settings could reduce the user-dependent limitation of ultrasound in detecting early-stage liver fibrosis.

A Radiomics Approach on Chest CT Distinguishes Primary Lung Cancer from Solitary Lung Metastasis in Colorectal Cancer Patients

PURPOSE

This study utilized a radiomics approach combined with a machine learning algorithm to distinguish primary lung cancer (LC) from solitary lung metastasis (LM) in colorectal cancer (CRC) patients with a solitary pulmonary nodule (SPN).

MATERIALS AND METHODS

In a retrospective study, 239 patients who underwent chest computerized tomography (CT) at three different institutions between 2011 and 2019 and were diagnosed as primary LC or solitary LM were included. The data from the first institution were divided into training and internal testing datasets. The data from the second and third institutions were used as an external testing dataset. Radiomic features were extracted from the intra and perinodular regions of interest (ROI). After a feature selection process, Support vector machine (SVM) was used to train models for classifying between LC and LM. The performances of the SVM classifiers were evaluated with both the internal and external testing datasets. The performances of the model were compared to those of two radiologists who reviewed the CT images of the testing datasets for the binary prediction of LC versus LM.

RESULTS

The SVM classifier trained with the radiomic features from the intranodular ROI and achieved the sensitivity/specificity of 0.545/0.828 in the internal test dataset, and 0.833/0.964 in the external test dataset, respectively. The SVM classifier trained with the combined radiomic features from the intra- and perinodular ROIs achieved the sensitivity/specificity of 0.545/0.966 in the internal test dataset, and 0.833/1.000 in the external test data set, respectively. Two radiologists demonstrated the sensitivity/specificity of 0.545/0.966 and 0.636/0.828 in the internal test dataset, and 0.917/0.929 and 0.833/0.929 in the external test dataset, which were comparable to the performance of the model trained with the combined radiomics features.

CONCLUSION

Our results suggested that the machine learning classifiers trained using radiomics features of SPN in CRC patients can be used to distinguish the primary LC and the solitary LM with a similar level of performance to radiologists.

Ultrasonographic assessment of skeletal muscles after experimentally induced neurogenic inflammation (facet injury) in rats

This study set out to examine ultrasonographic attributes of non-neurosegmentally (pectoral-forelimb) and neurosegmentally linked (hindlimb) myotomes in an experimental model that leads to neurogenic inflammation in segmentally linked myotomes, and to evaluate quantitative correlations among ultrasonographic attributes of the muscles, relative content of various inflammatory mediators, and nociceptive thresholds (hot and mechanical) in rats. Twelve male Wistar Kyoto rats were randomly divided into two equinumerous groups: surgery group, in which the left lumbar (L4-L6) facet joints were compressed for 3 min with modified Kelly forceps under general anesthesia, and sham-operated rats. All ultrasonograms were obtained with the Vevo 2100 Visual Sonic scanner connected to a 24-MHz transducer at four different time points: pre-surgery and 7, 14, and 21 days after surgical procedures. Digital ultrasonographic images of quadriceps femoris, hamstring, and pectoral-brachial muscle groups were analyzed using a polygonal meter region of interest placed on the largest cross-sectional area of the muscles displayed in Image ProPlus^® analytical software to compute numerical pixel values and pixel heterogeneity (standard deviation of mean pixel values). On day 21, pain behavior tests (hot plate and von Frey) were performed and then all animals were euthanized. Protein expression of inflammatory mediators in biceps brachii and rectus femoris muscles was measured by Western blot. The most prominent differences in muscle echotextural attributes between the two subsets of rats occurred 14 days post-surgery in pectoral-brachial and quadriceps femoris muscles. The expression of calcitonin-gene-related peptide was directly related to both echotextural variables only in biceps brachii (pixel intensity: r = 0.65, P = 0.02; and heterogeneity: r = 0.66, P = 0.02, respectively). Our findings have revealed the occurrence of echotextural changes in skeletal muscles of rats during myositis; however, the accumulation of inflammatory mediators and the outcomes of sensory tests did not relate to the changes in first-order echotextural characteristics of affected hindlimb muscles.

Current Approach to the Diagnosis of Sarcopenia in Heart Failure: A Narrative Review on the Role of Clinical and Imaging Assessments

Sarcopenia has been established as a predictor of poor outcomes in various clinical settings. It is particularly prevalent in heart failure, a clinical syndrome that poses significant challenges to health care worldwide. Despite this, sarcopenia remains overlooked and undertreated in cardiology practice. Understanding the currently proposed diagnostic process is paramount for the early detection and treatment of sarcopenia to mitigate downstream adverse health outcomes.

The Short-Term Impact of Botulinum Neurotoxin-A on Muscle Morphology and Gait in Children with Spastic Cerebral Palsy

Children with spastic cerebral palsy (SCP) are often treated with intramuscular Botulinum Neurotoxin type-A (BoNT-A). Recent studies demonstrated BoNT-A-induced muscle atrophy and variable effects on gait pathology. This group-matched controlled study in children with SCP compared changes in muscle morphology 8-10 weeks post-BoNT-A treatment (n = 25, median age 6.4 years, GMFCS level I/II/III (14/9/2)) to morphological changes of an untreated control group (n = 20, median age 7.6 years, GMFCS level I/II/III (14/5/1)). Additionally, the effects on gait and spasticity were assessed in all treated children and a subgroup (n = 14), respectively. BoNT-A treatment was applied following an established integrated approach. Gastrocnemius and semitendinosus volume and echogenicity intensity were assessed by 3D-freehand ultrasound, spasticity was quantified through electromyography during passive muscle stretches at different velocities. Ankle and knee kinematics were evaluated by 3D-gait analysis. Medial gastrocnemius (p = 0.018, -5.2%) and semitendinosus muscle volume (p = 0.030, -16.2%) reduced post-BoNT-A, but not in the untreated control group, while echogenicity intensity did not change. Spasticity reduced and ankle gait kinematics significantly improved, combined with limited effects on knee kinematics. This study demonstrated that BoNT-A reduces spasticity and partly improves pathological gait but reduces muscle volume 8-10 weeks post-injections. Close post-BoNT-A follow-up and well-considered treatment selection is advised before BoNT-A application in SCP.

Hypothesis generation: Quantitative research to levator ani muscle injury based on MRI texture analysis

AIM

Patients with pelvic organ prolapse (POP) mostly have injury to the levator ani muscle (LAM). We aimed to assess LAM injury in POP patients by quantifying texture feature (TF) ratios between the LAM and the obturator internus muscle (OIM) using texture analysis.

METHODS

This study retrospectively enrolled 32 participants, including 24 patients with POP and eight people with normal pelvic floor muscles. TFs of the LAM and the OIM were extracted using LIFEx version 6.30, and an independent samples t-test was performed to determine TF ratios characterizing LAM injury. After dimension reduction and binary logic analysis, the optimal TF ratio was obtained and the LAM injury quantitative evaluation was proposed. Spearman's correlation was performed to explore the correlations between TF ratios and clinical characteristics. We compared the diagnostic performance of quantitative evaluation and visual evaluation.

RESULTS

There were significant differences in 13 TF ratios between the POP and control groups. The area under the receiver operating characteristic curve of the integrated TF ratio was 0.948. Integrated TF ratio was significantly correlated with body mass index, pregnancies, and vaginal deliveries but had no correlation with LAM volume, hiatal area or abortions. Compared with the visual evaluation, the diagnostic accuracy of the quantitative evaluation had improved by 63.2% and 14.3% in the "minor defect" and "major defect" categories, respectively.

CONCLUSION

The integrated TF ratio can be used as a new quantifiable index to characterize LAM injury. The TF evaluation provides a potential role in LAM injury noninvasive diagnostic.

[Assessment and technical monitoring of nutritional status of patients in intensive and intermediate care units : Position paper of the Section Metabolism and Nutrition of the German Interdisciplinary Association for Intensive and Emergency Medicine (DIVI)]

At the time of admission to an intensive or intermediate care unit, assessment of the patients' nutritional status may have both prognostic and therapeutic relevance with regard to the planning of individualized medical nutrition therapy (MNT). MNT has definitely no priority in the initial treatment of a critically ill patient, but is often also neglected during the course of the disease. Especially with prolonged length of stay, there is an increasing risk of malnutrition with considerable prognostic macro- and/or micronutrient deficit. So far, there are no structured, evidence-based recommendations for assessing nutritional status in intensive or intermediate care patients. This position paper of the Section Metabolism and Nutrition of the German Interdisciplinary Association for Intensive and Emergency Medicine (DIVI) presents consensus-based recommendations for the assessment and technical monitoring of nutritional status of patients in intensive and intermediate care units. These recommendations supplement the current S2k guideline "Clinical Nutrition in Intensive Care Medicine" of the German Society for Nutritional Medicine (DGEM) and the DIVI.

Influence of Subcutaneous Adipose Tissue and Skeletal Muscle Thickness on Rectus Femoris Echo Intensity in Younger and Older Males and Females

OBJECTIVES

Ultrasound measurements of muscle echo intensity are commonly used surrogates of muscle composition (eg, intramuscular adipose tissue). However, given that soundwaves are increasingly attenuated with tissue depth, the interpretation of echo intensity may be confounded by adipose and skeletal muscle thickness. Our objectives are to compare the associations between adipose or muscle tissue thickness and rectus femoris echo intensity in younger and older males and females.

METHODS

Participants included in this analysis were derived from 3 previously published cohorts of younger (<45 years) and older (≥60 years) males and females. Ultrasound images of the rectus femoris were evaluated for muscle thickness, echo intensity, and subcutaneous adipose tissue thickness.

RESULTS

Older adults (n: 49 males, 19 females) had a higher body mass index (P = .001) compared with younger adults (n: 37 males, 49 females). Muscle thickness was negatively associated with echo intensity in older males (r = -0.59) and females (r = -0.53), whereas no associations were observed in younger males (r = 0.00) or females (r = -0.11). Subcutaneous adipose tissue thickness displayed no associations with echo intensity in any group.

CONCLUSIONS

Despite the known influence of subcutaneous adipose tissue thickness on beam attenuation, we observed no association with muscle echo intensity, indicating that adipose tissue correction may be required to better understand muscle echo intensity across differences in adiposity. The negative associations between muscle thickness and echo intensity in older, but not younger adults, suggests these associations may be related to the co-occurrence of skeletal muscle atrophy and intramuscular adipose tissue infiltration with advancing age.

Altered features of body composition in older adults with type 2 diabetes and prediabetes compared with matched controls

BACKGROUND

Ageing is accompanied by muscle loss and fat gain, which may elevate the risk of type 2 diabetes (T2D). However, there is a paucity of data on the distribution of regional lean and fat tissue in older adults with T2D or prediabetes compared with healthy controls. The objective of this study was to compare regional body composition [by dual-energy x-ray absorptiometry (DXA)], muscle and subcutaneous adipose tissue (SAT) thicknesses (by ultrasound), and ultrasound-based muscle texture features in older adults with T2D or prediabetes compared with normoglycaemic controls.

METHODS

Eighteen adults > 60 years with T2D or prediabetes (T2D group) were individually matched to normoglycaemic participants [healthy matched (HM) group] for age (±5 years), sex, and body fat (±2.5%). In a single study visit, all participants received a whole-body DXA scan and ultrasound assessment of the abdomen and anterior thigh. At these two landmarks, we used ultrasound to measure muscle and SAT thickness, as well as texture features of the rectus femoris and rectus abdominis. We also conducted an exploratory subanalysis on a subset of participants (n = 14/18 in the T2D group and n = 10/18 in the HM group) who underwent additional assessments including strength testing of the knee extensors (using a Biodex dynamometer), and a fasting blood sample for the measurement of circulating markers of glucose metabolism [glucose, insulin, c-peptide, and the homoeostatic model assessment of insulin resistance (HOMA-IR)].

RESULTS

The T2D group was 72 ± 8 years old (mean ± SD), predominantly male (n = 15/18; 83%), and overweight (BMI: 27.8 ± 4.2 kg/m² , 33.2 ± 5.3% body fat). DXA-derived upper arm lean mass was 0.4 kg greater (P = 0.034), and leg fat mass was 1.4 kg lower (P = 0.048), in the T2D vs. HM group. Ultrasound-based texture features were distinct between the groups [rectus abdominis blob size: 0.07 ± 0.06 vs. 0.30 ± 0.43 cm² , P = 0.045; rectus femoris local binary pattern (LBP) entropy: 4.65 ± 0.05 vs. 4.59 ± 0.08 A.U., P = 0.007]. When all participants who underwent additional assessments were pooled (n = 24), we observed that certain ultrasound-based muscle texture features correlated significantly with muscle strength (rectus abdominis histogram skew vs. power during an isokinetic contraction at 60°/s: r = 0.601, P = 0.003) and insulin resistance (rectus femoris LBP entropy vs. HOMA-IR: r = 0.419, P = 0.042).

CONCLUSIONS

Our findings suggest a novel body composition phenotype specific to older adults with T2D or prediabetes. We are also the first to report that ultrasound-based texture features correspond with functional outcomes. Future larger scale studies are needed to uncover the mechanisms underpinning these regional body composition differences.

Evaluation of lateral pterygoid muscle in patients with temporomandibular joint anterior disk displacement using T1-weighted Dixon sequence: a retrospective study

Background

Pathological alterations of lateral pterygoid muscle (LPM) are implicated in temporomandibular joint anterior disk displacement (ADD). However, quantification of the fatty infiltration of LPM and its correlation with ADD have rarely been reported. The aim of this study was to evaluate the fatty infiltration, morphological features and texture features of LPM in patients with ADD using T1-weighted Dixon sequence.

Methods

This retrospective study included patients who underwent temporomandibular joint MRI with T1-weighted Dixon sequence between December 2018 and August 2020. The temporomandibular joints of the included patients were divided into three groups according to the position of disk: Normal position disk (NP) group, Anterior disk displacement with reduction (ADDWR) group and Anterior disk displacement without reduction (ADDWOR) group. Fat fraction, morphological features (Length; Width; Thickness), and texture features (Angular second moment; Contrast; Correlation; Inverse different moment; Entropy) extracted from in-phase image of LPM were evaluated. One-way ANOVA, Welch’s ANOVA, Kruskal–Wallis test, Spearman and Pearson correlation analysis were performed. Intra-class correlation coefficient was used to evaluate the reproducibility.

Results

A total of 53 patients with 106 temporomandibular joints were evaluated. Anterior disk displacement without reduction group showed higher fat fraction than normal position disk group (P = 0.024). Length of LPM was negatively correlated with fat fraction (r = -0.22, P = 0.026). Angular second moment (ρ = -0.32, P < 0.001), correlation (ρ = -0.28, P = 0.003) and inverse different moment (ρ = -0.27, P = 0.005) were negatively correlated with fat fraction, while positive correlation was found between entropy and fat fraction (ρ = 0.31, P = 0.001). The intra-class correlation coefficients for all values were ranged from 0.80 to 0.97.

Conclusions

Patients with ADDWOR present more fatty infiltration in the LPM compared to NP or ADDWR patients. Fatty infiltration of LPM was associated with more atrophic and higher intramuscular heterogeneity in patients with ADD. Fat fraction of LPM quantitatively and noninvasively evaluated by Dixon sequence may has utility as an imaging-based marker of the structural severity of ADD disease process, which could be clinical helpful for the early diagnose of ADD and predication of disease progression.

From subjective to objective: A pilot study on testicular radiomics analysis as a measure of gonadal function

BACKGROUND

The connection between testicular ultrasound (US) parameters and testicular function, including both spermato- and steroidogenesis has been largely suggested, but their predictive properties are not routinely applied. Radiomics, a new engineering approach to radiological imaging, could overcome the visual limit of the sonographer.

OBJECTIVES

This study is aimed at extracting objective testicular US features, correlating with testicular function, including both spermato- and steroidogenesis, using an engineering approach, in order to overcome the operator-dependent subjectivity.

MATERIALS AND METHODS

Prospective observational pilot study from December 2019 to December 2020 on normozoospermic subjects and patients with semen variables alterations, excluding azoospermia. All patients underwent conventional semen analysis, pituitary-gonadal hormones assessment, and testicular US, performed by the same operator. US images were analyzed by Biolab (Turin) throughout image segmentation, image pre-processing, and texture features extraction.

RESULTS

One hundred seventy US testicular images were collected from 85 patients (age 38.6 ± 9.1 years). A total of 44 first-order and advanced features were extracted. US inhomogeneity defined by radiomics significantly correlates with the andrologist definition, showing for the first time a mathematical quantification of a subjective US evaluation. Thirteen US texture features correlated with semen parameters, predicting sperm concentration, total sperm number, progressive motility, total motility and morphology, and with gonadotropins serum levels, but not with total testosterone serum levels. Classification analyses confirmed that US textural features predicted patients' classification according to semen parameters alterations.

CONCLUSIONS

Radiomics texture features qualitatively describe the testicular parenchyma with objective and reliable quantitative parameters, reflecting both the testicular spermatogenic capability and the action of pituitary gonadotropins. This is an innovative model in which US texture features represent a mirror of the pituitary-gonadal homeostasis in terms of reproductive function.

Associations between skeletal muscle echo intensity and thickness in relation to glucose homeostasis in healthy and glucose impaired older males

BACKGROUND

Aging-related changes in muscle composition and mass may predispose older adults to developing insulin resistance. Ultrasound echo intensity and thickness are surrogates of muscle composition and mass, however, their associations with glucose homeostasis are not well established. We examined how muscle echo intensity and thickness correlate with markers of glucose homeostasis in older (≥65 years) males with normal (n = 22) or impaired (n = 10) glucose control.

METHODS

Echo intensity was measured for the biceps brachii, rectus abdominis, and rectus femoris. Muscle thickness was evaluated for the biceps brachii + brachioradialis, rectus abdominis, and rectus femoris + vastus intermedius. Glucose homeostasis was evaluated using a 2-h oral glucose tolerance test.

RESULTS

In older males with normal glucose homeostasis, higher echo intensity of the rectus abdominis and rectus femoris was moderately (r = 0.36 to 0.59) associated with 2-h glucose. On the contrary, higher muscle echo intensity of the rectus abdominis, biceps brachii, and rectus femoris was moderately-to-strongly (r = -0.36 to -0.79) associated with indices of better glucose homeostasis in the impaired group. Rectus abdominis muscle thickness was moderately associated (r = 0.36) with better glucose tolerance in the normal glucose homeostasis; however, in the glucose impaired group, muscle thickness was associated with (r = 0.37 to 0.73) with poorer glucose homeostasis.

CONCLUSIONS

Muscle echo intensity displays divergent associations with glucose homeostasis in older males with normal compared to impaired glucose control. Larger muscle thickness was associated with poorer glucose homeostasis in the glucose impaired group, but rectus abdominis muscle thickness was correlated with better homeostasis in healthy older males.