Application of ultrasound images‐based radiomics in carpal tunnel syndrome: Without measuring the median nerve cross‐sectional area

Abstract

PurposeBy constructing a prediction model of carpal tunnel syndrome (CTS) based on ultrasound images, it can automatically and accurately diagnose CTS without measuring the median nerve cross‐sectional area (CSA).MethodsA total of 268 wrists ultrasound images of 101 patients diagnosed with CTS and 76 controls in Ningbo NO.2 Hospital from December 2021 to August 2022 were retrospectively analyzed. The radiomics method was used to construct the Logistic model through the steps of feature extraction, feature screening, reduction, and modeling. The area under the receiver operating characteristic curve was calculated to evaluate the performance of the model, and the diagnostic efficiency of the radiomics model was compared with two radiologists with different experience.ResultsThe 134 wrists in the CTS group included 65 mild CTS, 42 moderate CTS, and 17 severe CTS. In the CTS group, 28 wrists median nerve CSA were less than the cut‐off value, 17 wrists were missed by Dr. A, 26 wrists by Dr. B, and only 6 wrists were missed by radiomics model. A total of 335 radiomics features were extracted from each MN, of which 10 features were significantly different between compressed and normal nerves, and were used to construct the model. The area under curve (AUC) value, sensitivity, specificity, and accuracy of the radiomics model in the training set and testing set were 0.939, 86.17%, 87.10%, 86.63%, and 0.891, 87.50%, 80.49%, and 83.95%, respectively. The AUC value, sensitivity, specificity, and accuracy of the two doctors in the diagnosis of CTS were 0.746, 75.37%, 73.88%, 74.63% and 0.679, 68.66%, 67.16%, and 67.91%, respectively. The radiomics model was superior to the two‐radiologist diagnosis, especially when there was no significant change in CSA.ConclusionRadiomics based on ultrasound images can quantitatively analyze the subtle changes in the median nerve, and can automatically and accurately diagnose CTS without measuring CSA, especially when there was no significant change in CSA, which was better than radiologists.

The Potential of Ultrasound Radiomics in Carpal Tunnel Syndrome Diagnosis: A Systematic Review and Meta-Analysis

“…In their subsequent study [22], they explored the potential application of ultrasound radiomics in diagnosing mild CTS. Finally, their third study [20] focused on emphasizing the importance of utilizing specific characteristics of ultrasonic images for diagnosing CTS, without the need to measure their cross-sectional area.…”

“…Concerning the seven criteria in the QUADAS-2 tool, two studies [21,24] did not meet the criteria for assessing the risk of bias related to flow and timing. Only three studies [20,22,23] clearly defined a specific time interval between the electrodiagnostic test and the ultrasound examination. In three studies conducted by Lyu et al [21,23,24], there was a lack of specification regarding exclusion criteria, which raised concerns about the applicability of their patient selection process.…”

“…In three studies conducted by Lyu et al [21,23,24], there was a lack of specification regarding exclusion criteria, which raised concerns about the applicability of their patient selection process. Furthermore, three [19,20,23] of these studies provided specific protocols for radiologists to evaluate the quality of median nerves, e.g., assessing nerve honeycomb pattern and echogenicity. In the context of these studies, radiomics features were extracted using MATLAB software (version R2019a, MathWorks Inc., Natick, MA, USA), Python, and Novo Ultrasound Kit (GE Institute of Precision Medicine, IPM) software, v. 3.12.0.…”