Assessing the Performance of Morphologic and Echogenic Features in Median Nerve Ultrasound for Carpal Tunnel Syndrome Diagnosis

Peripheral nerve ultrasound: a survival guide for the practicing radiologist with updates

Peripheral nerve injuries negatively impact patients' quality of life and healthcare resources. This review discusses using high-resolution neurosonography (HRNUS) for mapping peripheral nerves and detecting pathologic lesions. It emphasizes the importance of HRNUS in diagnosing nerve disorders and briefs the widely accepted schemes for peripheral nerve injury classification. It also highlights the non-intrusive, flexible, patient-friendly, and cost-effective nature of HRNUS, making it a valuable tool in managing nerve disorders. The authors recommend the use of HRNUS to enable precise diagnoses, prevent permanent disabilities, and contribute to the efficient utilization of healthcare resources.

Effectiveness of Comprehensive Video Datasets: Toward the Development of an Artificial Intelligence Model for Ultrasonography-Based Severity Diagnosis of Carpal Tunnel Syndrome

OBJECTIVES

Advances in diagnosing carpal tunnel syndrome (CTS) using ultrasonography (US) and artificial intelligence (AI) aim to replace nerve conduction studies. However, a method for accurate severity diagnosis remains unachieved. We explored the potential of comprehensive video data formats for constructing an effective model for diagnosing CTS severity.

METHODS

We studied 75 individuals (52 with CTS) from 2019 to 2022, categorizing them into 3 groups based on disease severity. We recorded 132 US videos of carpal tunnel during finger movement. Features of the median nerve (MN) were extracted from automatically segmented US video frames, from which 3 datasets were created: a comprehensive video dataset with full information, a key metrics dataset, and an initial frame dataset with the least information. We compared the accuracy of machine learning algorithms for classifying CTS severity into 3 groups across these datasets using 63-fold cross-validation.

RESULTS

The cross-sectional area of the MN correlated with severity (P < .05) but MN displacement did not. The algorithm using the comprehensive video dataset exhibited the highest sensitivity (1.00) and accuracy (0.75).

CONCLUSIONS

Our study demonstrated that utilizing comprehensive video data enables a more accurate US-based diagnosis of CTS severity. This underscores the value of capturing the patterns of MN deformation and movement, which cannot be captured by representative metrics such as medians or maximums. By further developing an AI model based on our findings, a simpler and painless method for assessing CTS severity can be achieved.

Influences of Variability in Attenuation Compensation on the Estimation of Backscatter Coefficient of Median Nerves in Vivo

OBJECTIVE

Peripheral nerves remain a challenging target for medical imaging, given their size, anatomical complexity, and structural heterogeneity. Quantitative ultrasound (QUS) applies a set of techniques to estimate tissue acoustic parameters independent of the imaging platform. Many useful medical and laboratory applications for QUS have been reported, but challenges remain for deployment in vivo, especially for heterogeneous tissues. Several phenomena introduce variability in attenuation estimates, which may influence the estimation of other QUS parameters. For example, estimating the backscatter coefficient (BSC) requires compensation for the attenuation of overlying tissues between the transducer and the underlying tissue of interest. The purpose of this study is to extend prior studies by investigating the efficacy of several analytical methods of estimating attenuation compensation on QUS outcomes in the human median nerve.

METHODS

Median nerves were imaged at the volar wrist in vivo and beam-formed radiofrequency (RF) data were acquired. Six analytical approaches for attenuation compensation were compared: 1-2) attenuation estimated by applying spectral difference method (SDM) and spectral log difference method (SLDM) independently to regions of interest (ROIs) overlying the nerve and to the nerve ROI itself; 3-4) attenuation estimation by applying SDM and SLDM to ROIs overlying the nerve, and transferring these properties to the nerve ROI; and 5-6) methods that apply previously published values of tissue attenuation to the measured thickness of each overlying tissue. Mean between-subject estimates of BSC-related outcomes as well as within-subject variability of these outcomes were compared among the 6 methods.

RESULTS

Compensating for attenuation using SLDM and values from the literature reduced variability in BSC-based outcomes, compared to SDM. Variability in attenuation coefficients contributes substantially to variability in backscatter measurements.

CONCLUSION

This work has implications for the application of QUS to in vivo diagnostic assessments in peripheral nerves and possibly other heterogeneous tissues.

The Impact of Reference Standard on Diagnostic Testing Characteristics for Carpal Tunnel Syndrome: A Systematic Review

Lack of a reliable reference standard for carpal tunnel syndrome (CTS) diagnosis could impact the diagnostic test characteristics. This systematic review sought to evaluate differences in the accuracy of CTS diagnostic modalities based on the reference standard used.

Methods

A systematic review was performed following PRISMA guidelines to investigate diagnostic modalities used in CTS. A literature search of Embase, PubMed, and Cochrane Reviews was conducted for the years of 2010-2021 for primary data, and 113 studies met final inclusion criteria. Studies were stratified based on the reference standard utilized and diagnostic modality assessed, and the weighted means of the sensitivities and specificities were calculated.

Results

Thirty-five studies used clinical diagnosis alone as a reference standard, and 78 studies used electrodiagnostic study (EDS). The specificity for MRI and ultrasound (US) were substantially lower when EDS was used as the reference standard. MRI was the test most affected by the reference standard used, showing increased sensitivity when using EDS as the reference compared to clinical diagnosis (77.1% versus 60.9%) and decreased specificity (87.6% versus 99.2%). Regardless of the reference standard used, all tests had anticipated false-positive and/or false-negative rates of at least 10%.

Conclusions

Testing characteristics vary greatly based on the choice of reference standard, with the sensitivity of MRI most affected. Regardless of reference standard used, EDS, US, and MRI each had false-positive and/or false-negative rates too great to be appropriate for use as a screening examination.

Image analysis can reliably quantify median nerve echogenicity and texture changes in patients with carpal tunnel syndrome

OBJECTIVE

To study the ability of image analysis measures to quantify echotexture changes of median nerve in order to provide a complementary diagnostic tool in CTS.

METHODS

Image analysis measures (gray level co-occurrence matrix (GLCM), brightness, hypoechoic area percentage using max entropy and mean threshold) were calculated in normalized images of 39 (19 younger and 20 older than 65y) healthy controls and 95 CTS patients (37 younger and 58 older than 65y).

RESULTS

Image analysis measures were equivalent or superior (older patients) to subjective visual analysis. In younger patients, GLCM measures showed equivalent diagnostic accuracy with cross sectional area (CSA) (Area Under Curve (AUC for inverse different moment = 0.97). In older patients all image analysis measures showed similar diagnostic accuracy to CSA (AUC for brightness = 0.88). Moreover, they had abnormal values in many older patients with normal CSA values.

CONCLUSIONS

Image analysis reliably quantifies median nerve echotexture alterations in CTS and offers similar diagnostic accuracy to CSA measurement.

SIGNIFICANCE

Image analysis may offer added value to existing measures in the evaluation of CTS, especially in older patients. Its clinical implementation would require incorporation of mathematically simple software code for online nerve image analysis in ultrasound machines.

Quantitative Ultrasound Techniques Used for Peripheral Nerve Assessment

AIM

This review article describes quantitative ultrasound (QUS) techniques and summarizes their strengths and limitations when applied to peripheral nerves.

METHODS

A systematic review was conducted on publications after 1990 in Google Scholar, Scopus, and PubMed databases. The search terms "peripheral nerve", "quantitative ultrasound", and "elastography ultrasound" were used to identify studies related to this investigation.

RESULTS

Based on this literature review, QUS investigations performed on peripheral nerves can be categorized into three main groups: (1) B-mode echogenicity measurements, which are affected by a variety of post-processing algorithms applied during image formation and in subsequent B-mode images; (2) ultrasound (US) elastography, which examines tissue stiffness or elasticity through modalities such as strain ultrasonography or shear wave elastography (SWE). With strain ultrasonography, induced tissue strain, caused by internal or external compression stimuli that distort the tissue, is measured by tracking detectable speckles in the B-mode images. In SWE, the propagation speed of shear waves, generated by externally applied mechanical vibrations or internal US "push pulse" stimuli, is measured to estimate tissue elasticity; (3) the characterization of raw backscattered ultrasound radiofrequency (RF) signals, which provide fundamental ultrasonic tissue parameters, such as the acoustic attenuation and backscattered coefficients, that reflect tissue composition and microstructural properties.

CONCLUSIONS

QUS techniques allow the objective evaluation of peripheral nerves and reduce operator- or system-associated biases that can influence qualitative B-mode imaging. The application of QUS techniques to peripheral nerves, including their strengths and limitations, were described and discussed in this review to enhance clinical translation.

Ultrasound-based radiomics in the diagnosis of carpal tunnel syndrome: The influence of regions of interest delineation method on mode

BACKGROUND

In the recent years, artificial intelligence (AI) algorithms have been used to accurately diagnose musculoskeletal diseases. However, it is not known whether the particular regions of interest (ROI) delineation method would affect the performance of the AI algorithm.

PURPOSE

The purpose of this study was to investigate the influence of ROI delineation methods on model performance and observer consistency.

METHODS

In this retrospective analysis, ultrasound (US) measures of median nerves affected with carpal tunnel syndrome (CTS) were compared to median nerves in a control group without CTS. Two methods were used for delineation of the ROI: (1) the ROI along the hyperechoic medial edge of the median nerve but not including the epineurium (MN) (ROI1); and (2) the ROI including the hyperechoic epineurium (ROI2), respectively. The intra group correlation coefficient (ICC) was used to compare the observer consistency of ROI features (i.e. the corresponding radiomics parameters). Parameters α₁ and α₂ were obtained based on the ICC of ROI₁ features and ROI₂ features. The ROC analysis was used to determine the area under the curve (AUC) and evaluate the performance of the radiologists and network. In addition, four indices, namely sensitivity, specificity, positive prediction and negative prediction were analyzed too.

RESULTS

A total of 136 wrists of 77 CTS group and 136 wrists of 74 control group were included in the study. Control group was matched to CTS group according to the age and sex. The observer consistency of ROI features delineated by the two schemes was different, and the consistency of ROI₁ features was higher (α1 ˃ α2). The intra-observer consistency was higher than the inter-observer consistency regardless of the scheme, and the intra-observer consistency was higher when chose scheme one. The performances of models based on the two ROI features were different, although the AUC of each model was greater than 0.8.The model performed better when the MN epineurium was included in the ROI. Among five artificial intelligence algorithms, the Forest models (model₁ achieved an AUC of 0.921 in training datasets and 0.830 in testing datasets; model₂ achieved an AUC of 0.967 in training datasets and 0.872 in testing datasets.) obtained the highest performance, followed by the support vector machine (SVM) models and the Logistic models. The performances of the models were significantly better than the inexperienced radiologist (Dr. B. Z. achieved an AUC of 0.702).

CONCLUSION

Different ROI delineation methods may affect the performance of the model and the consistency of observers. Model performance was better when the ROI contained the MN epineurium, and observer consistency was higher when the ROI was delineated along the hyperechoic medial border of the MN.

Ultrasound and elastography role in pre- and post-operative evaluation of median neuropathy in patients with carpal tunnel syndrome

Introduction

Carpal tunnel syndrome (CTS) is a common compression neuropathy of the median nerve in the wrist. Early diagnosis of CTS is essential for selecting treatment options and assessing prognosis. The current diagnosis of CTS is based on the patient's clinical symptoms, signs, and an electromyography (EMG) test. However, they have some limitations. Recently, ultrasound has been adopted as an adjunct diagnostic tool for electromyography (EMG). Ultrasound is a non-invasive and cost-effective technique. It provides a dynamic display of morphological changes in the median nerve and an assessment of CTS etiology such as tenosynovitis, mass compression, and tendon disease. This study aimed to investigate the value of conventional ultrasound and real-time shear wave elastography (SWE) in evaluation of median neuropathy in patients with carpal tunnel syndrome (CTS) before and after surgery.

Methods

First, the Boston Carpal Tunnel Questionnaire (BCTQ) was administered to patients with CTS. All subjects were measured at three levels: the distal 1/3 of the forearm, the carpal tunnel inlet, and the distal carpal tunnel using conventional ultrasound and SWE. Median nerve parameters were examined in patients with CTS 1 week after surgery.

Results

The cross-sectional area (CSA) and stiffness of the median nerve at the carpal tunnel inlet and distal carpal tunnel were significantly higher in patients with CTS than in healthy controls (p < 0.001). The CSA and stiffness of the median nerve at the carpal tunnel inlet were statistically significantly significantly between pre- and postoperative patients with CTS (p < 0.001). The CSA and stiffness of the nerve in patients with CTS had a positive correlation with electrophysiology severity.

Conclusions and discussion

Conventional ultrasound and elastography are valuable in the diagnosis of CTS and are useful in the clinical assessment of patient's nerve recovery after operation.

Clinical Relevance of Ultrasonographic and Electrophysiological Findings of the Median Nerve in Unilateral Carpal Tunnel Syndrome Patients

Few studies have compared the unaffected and affected sides in the same carpal tunnel syndrome (CTS) patients using ultrasonography and electrophysiological tests. We focused on unilateral idiopathic CTS patients to investigate whether clinical test results differ between the unaffected and affected sides. The bilateral wrist joints of 61 unilateral idiopathic CTS patients were evaluated. The median nerve cross-sectional area of ultrasound image, and latencies of the compound muscle action potential (CMAP) and sensory nerve action potential (SNAP) were measured. The values obtained were compared between the affected and unaffected sides. The diagnostic accuracies of each parameter were assessed, and cut-off values were defined. Significant differences were observed in all parameters between the affected and unaffected sides (p < 0.01). Area under the curve (AUC) values were 0.74, 0.88, and 0.73 for the cross-sectional area, CMAP distal latency, and SNAP distal latency, respectively. Cut-off values were 11.9 mm2, 5.1 ms, and 3.1 ms for the cross-sectional area, CMAP distal latency, and SNAP distal latency, respectively. The most reliable parameter that reflected clinical symptoms was the distal latency of CMAP. Cut-off values for each parameter are considered to be an index for the onset of the clinical symptoms of CTS.