Deep CTS: a Deep Neural Network for Identification MRI of Carpal Tunnel Syndrome

Zhou, Haiying; Bai, Qi; Hu, Xianliang; Alhaskawi, Ahmad; Dong, Yanzhao; Wang, Zewei; Qi, Binjie; Fang, Jianyong; Kota, Vishnu Goutham; Abdulla, Mohamed Hasan Abdulla Hasa; Ezzi, Sohaib Hasan Abdullah; Lü, Hui

doi:10.1007/s10278-022-00661-4

Cited by 8 publications

(10 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Zhou et al designed an end‐to‐end CNN termed DeepCTS, which achieved an accuracy of 74.59% and intersection over union (number of shared pixels between predicted pixels and ground truth pixels) of 63.10% in median nerve segmentation. These values are of significant importance as they achieved in complete cross‐sections of the wrist, of which the carpal tunnel only occupies a small percentage 28 . Furthermore, these studies are significant as the availability of robust and reliable automatic segmentation algorithms facilitates further experimentation with AI techniques, including both supervised and unsupervised 9,29 …”

Section: Discussionmentioning

confidence: 99%

“…These values are of significant importance as they achieved in complete cross-sections of the wrist, of which the carpal tunnel only occupies a small percentage. 28 Furthermore, these studies are significant as the availability of robust and reliable automatic segmentation algorithms facilitates further experimentation with AI techniques, including both supervised and unsupervised. 9,29 There have also been initiatives to use DL algorithms to differentiate CTS from normal wrists.…”

Section: Discussionmentioning

confidence: 99%

See 1 more Smart Citation

Deep Radiomics Features of Median Nerves for Automated Diagnosis of Carpal Tunnel Syndrome With Ultrasound Images: A Multi‐Center Study

Mohammadi

Torres-Cuenca

Mirza‐Aghazadeh‐Attari

et al. 2023

J of Ultrasound Medicine

View full text Add to dashboard Cite

ObjectivesUltrasound is widely used in diagnosing carpal tunnel syndrome (CTS). However, the limitations of ultrasound in CTS detection are the lack of objective measures in the detection of nerve abnormality and the operator‐dependent nature of ultrasound imaging. Therefore, in this study, we developed and proposed externally validated artificial intelligence (AI) models based on deep‐radiomics features.MethodsWe have used 416 median nerves from 2 countries (Iran and Colombia) for the development (112 entrapped and 112 normal nerves from Iran) and validation (26 entrapped and 26 normal nerves from Iran, and 70 entrapped and 70 normal nerves from Columbia) of our models. Ultrasound images were fed to the SqueezNet architecture to extract deep‐radiomics features. Then a ReliefF method was used to select the clinically significant features. The selected deep‐radiomics features were fed to 9 common machine‐learning algorithms to choose the best‐performing classifier. The 2 best‐performing AI models were then externally validated.ResultsOur developed model achieved an area under the receiver operating characteristic (ROC) curve (AUC) of 0.910 (88.46% sensitivity, 88.46% specificity) and 0.908 (84.62% sensitivity, 88.46% specificity) with support vector machine and stochastic gradient descent (SGD), respectively using the internal validation dataset. Furthermore, both models consistently performed well in the external validation dataset, and achieved an AUC of 0.890 (85.71% sensitivity, 82.86% specificity) and 0.890 (84.29% sensitivity and 82.86% specificity), with SVM and SGD models, respectively.ConclusionOur proposed AI models fed with deep‐radiomics features performed consistently with internal and external datasets. This justifies that our proposed system can be employed for clinical use in hospitals and polyclinics.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Discussionmentioning

confidence: 99%

Deep Radiomics Features of Median Nerves for Automated Diagnosis of Carpal Tunnel Syndrome With Ultrasound Images: A Multi‐Center Study

Mohammadi

Torres-Cuenca

Mirza‐Aghazadeh‐Attari

et al. 2023

J of Ultrasound Medicine

View full text Add to dashboard Cite

show abstract

“…Peripheral nerve injury of the upper limb is a common and extremely inconvenient clinical disease. The main mechanisms of its occurrence are compression, trauma, peripheral nerve tumor, inflammation, neuronal degeneration, and radiation exposure (14)(15)(16). The brachial plexus is not only the most complicated structure in the peripheral nervous system, but highly susceptible to trauma, or may be damaged secondary to lesions of adjacent structures (17).…”

Section: Discussionmentioning

confidence: 99%

The effects of melatonin in the treatment of acute brachial plexus compression injury in rats

Fu²,

Zhou³

et al. 2023

Front. Neurol.

Self Cite

View full text Add to dashboard Cite

IntroductionBrachial plexus injury (BPI) is one of the most destructive peripheral nerve injuries and there is still a lack of effective treatment.MethodsThis study was conducted to evaluate the effects of melatonin in the treatment of acute brachial plexus compression injury in rats using histopathological, histomorphometric, immunohistochemical and electrophysiological methods. Forty-eight adult male Sprague Dawley rats were randomly allocated into three groups: sham, melatonin and vehicle groups. The brachial plexus compression injury model was performed by a vascular clamp. Melatonin group received intraperitoneal injection of melatonin at doses of 10 mg/kg for 21 days after crush injury. The conduction velocity and amplitude of compound muscle action potential (CAMP) in the regenerated nerve, and nerve histomorphometry, as well as levels of myelin protein zero (P0) protein of the crush region were assessed.ResultsCompared with the vehicle group, the melatonin group which reported significant increased CMAP conduction velocity and amplitude also showed thicker myelin sheath and lower levels of P0 protein.DiscussionOur results suggest that melatonin effectively promotes nerve regeneration and improves the function of damaged nerves. Melatonin treatment is a promising strategy for the treatment of acute brachial plexus compression injury.

show abstract

“…The developed model was validated using CT images aggregated from 53 patients and achieved an accuracy of 0.94%. The same model was used in [20][21][22][23], showing promising results. However, these studies have several limitations, including the following: (1) They depended on MRI and CT scan images, which are considered costly and may not be available for diagnosis.…”

Section: Problem Statementmentioning

confidence: 99%

“…An SVM classifier was used, and an optimum accuracy of 90.1% was achieved. Haiying Zhou et al [21] proposed a deep learning framework for carpal tunnel segmentation using MR images, known as Deep CTS. Deep CTS can effectively segment the CTS area and correct the intersection when combining the results.…”

Section: Related Workmentioning

confidence: 99%

Predicting CTS Diagnosis and Prognosis Based on Machine Learning Techniques

et al. 2023

View full text Add to dashboard Cite

Carpal tunnel syndrome (CTS) is a clinical disease that occurs due to compression of the median nerve in the carpal tunnel. The determination of the severity of carpal tunnel syndrome is essential to provide appropriate therapeutic interventions. Machine learning (ML)-based modeling can be used to classify diseases, make decisions, and create new therapeutic interventions. It is also used in medical research to implement predictive models. However, despite the growth in medical research based on ML and Deep Learning (DL), CTS research is still relatively scarce. While a few studies have developed models to predict diagnosis of CTS, no ML model has been presented to classify the severity of CTS based on comprehensive clinical data. Therefore, this study developed new classification models for determining CTS severity using ML algorithms. This study included 80 patients with other diseases that have an overlap in symptoms with CTS, such as cervical radiculopathysasas, de quervian tendinopathy, and peripheral neuropathy, and 80 CTS patients who underwent ultrasonography (US)-guided median nerve hydrodissection. CTS severity was classified into mild, moderate, and severe grades. In our study, we aggregated the data from CTS patients and patients with other diseases that have an overlap in symptoms with CTS, such as cervical radiculopathysasas, de quervian tendinopathy, and peripheral neuropathy. The dataset was randomly split into training and test data, at 70% and 30%, respectively. The proposed model achieved promising results of 0.955%, 0.963%, and 0.919% in terms of classification accuracy, precision, and recall, respectively. In addition, we developed a machine learning model that predicts the probability of a patient improving after the hydro-dissection injection process based on the aggregated data after three different months (one, three, and six). The proposed model achieved accuracy after six months of 0.912%, after three months of 0.901%, and after one month 0.877%. The overall performance for predicting the prognosis after six months outperforms the prediction after one and three months. We utilized statistics tests (significance test, Spearman’s correlation test, and two-way ANOVA test) to determine the effect of injection process in CTS treatment. Our data-driven decision support tools can be used to help determine which patients to operate on in order to avoid the associated risks and expenses of surgery.

show abstract

Deep CTS: a Deep Neural Network for Identification MRI of Carpal Tunnel Syndrome

Cited by 8 publications

References 60 publications

Deep Radiomics Features of Median Nerves for Automated Diagnosis of Carpal Tunnel Syndrome With Ultrasound Images: A Multi‐Center Study

Deep Radiomics Features of Median Nerves for Automated Diagnosis of Carpal Tunnel Syndrome With Ultrasound Images: A Multi‐Center Study

The effects of melatonin in the treatment of acute brachial plexus compression injury in rats

Predicting CTS Diagnosis and Prognosis Based on Machine Learning Techniques

Contact Info

Product

Resources

About