Value of conventional ultrasound and shear wave elastography in the assessment of muscle mass and function in elderly people with type 2 diabetes

Sarcopenia prediction using shear-wave elastography, grayscale ultrasonography, and clinical information with machine learning fusion techniques: feature-level fusion vs. score-level fusion

This study aimed to develop and evaluate a sarcopenia prediction model by fusing numerical features from shear-wave elastography (SWE) and gray-scale ultrasonography (GSU) examinations, using the rectus femoris muscle (RF) and categorical/numerical features related to clinical information. Both cohorts (development, 70 healthy subjects; evaluation, 81 patients) underwent ultrasonography (SWE and GSU) and computed tomography. Sarcopenia was determined using skeletal muscle index calculated from the computed tomography. Clinical and ultrasonography measurements were used to predict sarcopenia based on a linear regression model with the least absolute shrinkage and selection operator (LASSO) regularization. Furthermore, clinical and ultrasonography features were combined at the feature and score levels to improve sarcopenia prediction performance. The accuracies of LASSO were 70.57 ± 5.00-81.54 ± 4.83 (clinical) and 69.00 ± 4.52-69.73 ± 5.47 (ultrasonography). Feature-level fusion of clinical and ultrasonography (accuracy, 70.29 ± 6.63 and 83.55 ± 4.32) showed similar performance with clinical features. Score-level fusion by AdaBoost showed the best performance (accuracy, 73.43 ± 6.57-83.17 ± 5.51) in the development and evaluation cohorts, respectively. This study might suggest the potential of machine learning fusion techniques to enhance the accuracy of sarcopenia prediction models and improve clinical decision-making in patients with sarcopenia.

Imaging of Sarcopenia in Type 2 Diabetes Mellitus

Sarcopenia is an age-related condition characterized by the loss of skeletal muscle mass, muscular strength, and muscle function. In older adults, type 2 diabetes mellitus (T2DM) constitutes a significant health burden. Skeletal muscle damage and deterioration have emerged as novel chronic complications in patients with diabetes, often linked to their increased longevity. Diabetic sarcopenia has been associated with increased rates of hospitalization, cardiovascular events, and mortality. Nevertheless, effectively managing metabolic disorders in patients with T2DM through appropriate therapeutic interventions could potentially mitigate the risk of sarcopenia. Utilizing imaging technologies holds substantial clinical significance in the early detection of skeletal muscle mass alterations associated with sarcopenia. Such detection is pivotal for arresting disease progression and preserving patients' quality of life. These imaging modalities offer reproducible and consistent patterns over time, as they all provide varying degrees of quantitative data. This review primarily delves into the application of dual-energy X-ray absorptiometry, computed tomography, magnetic resonance imaging, and ultrasound for both qualitative and quantitative assessments of muscle mass in patients with T2DM. It also juxtaposes the merits and limitations of these four techniques. By understanding the nuances of each method, clinicians can discern how best to apply them in diverse clinical scenarios.

Deep learning radiomics on shear wave elastography and b-mode ultrasound videos of diaphragm for weaning outcome prediction

PURPOSE

We proposed an automatic method based on deep learning radiomics (DLR) on shear wave elastography (SWE) and B-mode ultrasound videos of diaphragm for two classification tasks, one for differentiation between the control and patient groups, and the other for weaning outcome prediction.

MATERIALS AND METHODS

We included a total of 581 SWE and B-mode ultrasound videos, of which 466 were from the control group of 179 normal subjects, and 115 were from the patient group of 35 mechanically ventilated subjects in the intensive care unit (ICU). Among the patient group, 17 subjects successfully weaned and 18 failed. The deep neural network of U-Net was utilized to automatically segment diaphragm regions in dual-modal videos of SWE and B-mode. High-throughput radiomics features were then extracted, the statistical test and least absolute shrinkage and selection operator (LASSO) were applied for feature dimension reduction. The optimal classification models for the two tasks were established using the support vector machine (SVM).

RESULTS

The automatic segmentation model achieved Dice score of 87.89 %. A total of 4524 radiomics features were extracted, 10 and 20 important features were left after feature dimension reduction for constructing the two classification models. The best areas under receiver operating characteristic curves of the two models reached 84.01 % and 94.37 %, respectively.

CONCLUSIONS

Our proposed DLR methods are innovative for automatic segmentation of diaphragm regions in SWE and B-mode videos and deep mining of high-throughput radiomics features from dual-modal images. The approaches have been proved to be effective for prediction of weaning outcomes.

Ultrasound Assessment of the Gastrocnemius Muscle as a Potential Tool for Identifying Sarcopenia in Patients with Type 2 Diabetes

Objective

This study aims to examine the clinical significance of ultrasound evaluation of the gastrocnemius muscle (GM) in identifying sarcopenia in patients with type 2 diabetes (T2D).

Methods

One hundred and fifty-three patients with T2D were included in this study. We measured the appendicular skeletal muscle mass index (ASMI), handgrip strength, and 6-meter walking speed. The US-derived muscle thickness (MT), cross-sectional area (CSA), and shear wave ultrasound elastography (SWE) of GM were also measured. We assessed the correlations between clinical indicators and US features. The model for screening sarcopenia was established using stepwise logistic regression. Stepwise linear regression was used to identify a set of variables that jointly estimated ASMI. The model's ability to identify sarcopenia and low muscle mass was assessed by receiver operating characteristic (ROC) curve analysis.

Results

The prevalence of sarcopenia in this study was 24.2%. The CSA, MT and SWE values of the patients with sarcopenia were lower than those of patients without sarcopenia (all p < 0.05). ASMI was positively correlated with CSA (r = 0.56, p < 0.001) and MT (r = 0.39, p < 0.001). Handgrip strength was positively correlated with CSA (r = 0.45, p < 0.001), MT (r = 0.25, p < 0.001), and SWE (r = 0.26, p = 0.002). A diagnostic model for sarcopenia was established with a sensitivity of 81.1%, specificity of 75.0%, and an area under the curve (AUC) of 0.800. The estimated ASMI equation was developed and found to have a positive correlation with actual ASMI (r = 0.70, p < 0.001). It was also effective in diagnosing low muscle mass, with an AUC of 0.787 for males and 0.783 for females.

Conclusion

Ultrasonographic assessment of the gastrocnemius muscle was found to be a useful and convenient method for detecting sarcopenia in patients with T2D.