Diagnosis of Cubital Tunnel Syndrome Using Deep Learning on Ultrasonographic Images

Issei Shinohara, Atsuyuki Inui, Yutaka Mifune, Hanako Nishimoto, Kohei Yamaura, Shintaro Mukohara, Tomoya Yoshikawa, Tatsuo Kato, Takahiro Furukawa, Yuichi Hoshino, Takehiko Matsushita, Ryosuke Kuroda, Issei Shinohara, Atsuyuki Inui, Yutaka Mifune, Hanako Nishimoto, Kohei Yamaura, Shintaro Mukohara, Tomoya Yoshikawa, Tatsuo Kato, Takahiro Furukawa, Yuichi Hoshino, Takehiko Matsushita, Ryosuke Kuroda

Abstract

Although electromyography is the routine diagnostic method for cubital tunnel syndrome (CuTS), imaging diagnosis by measuring cross-sectional area (CSA) with ultrasonography (US) has also been attempted in recent years. In this study, deep learning (DL), an artificial intelligence (AI) method, was used on US images, and its diagnostic performance for detecting CuTS was investigated. Elbow images of 30 healthy volunteers and 30 patients diagnosed with CuTS were used. Three thousand US images were prepared per each group to visualize the short axis of the ulnar nerve. Transfer learning was performed on 5000 randomly selected training images using three pre-trained models, and the remaining images were used for testing. The model was evaluated by analyzing a confusion matrix and the area under the receiver operating characteristic curve. Occlusion sensitivity and locally interpretable model-agnostic explanations were used to visualize the features deemed important by the AI. The highest score had an accuracy of 0.90, a precision of 0.86, a recall of 1.00, and an F-measure of 0.92. Visualization results show that the DL models focused on the epineurium of the ulnar nerve and the surrounding soft tissue. The proposed technique enables the accurate prediction of CuTS without the need to measure CSA.

Keywords: artificial intelligence; cubital tunnel syndrome; deep learning; ulnar nerve; ultrasonography.

Conflict of interest statement

The authors declare no conflict of interest.

Figures

Figure 1
Figure 1
(a) US probe placed on the medial epicondyle to visualize the ulnar nerve; (b) short-axis image of the ulnar nerve (red arrows) at the level of the medial epicondyle.
Figure 2
Figure 2
Flowchart of the proposed framework.
Figure 3
Figure 3
Images were randomly extracted by AI to be used as training data (light blue for control, orange for CuTS patients).
Figure 4
Figure 4
Block diagram of ResNet-50.
Figure 5
Figure 5
Block diagram of MobileNet_v2.
Figure 6
Figure 6
Block diagram of EfficientNet.
Figure 7
Figure 7
(a) A confusion matrix is a table of four combinations based on predicted and actual values and the presence or absence of disease; (b) diagnostic accuracy from the learning model is calculated from the confusion matrix created using testing data.
Figure 8
Figure 8
Area under the curve (AUC), based on the receiver operating characteristic (ROC) curve, was high for all learning models.
Figure 9
Figure 9
Confusion matrix of each learning model.
Figure 10
Figure 10
Visualization of the region of interest using occlusion sensitivity and image LIMEs. Learning models focus on neural interior and perineural tissues. The red circle is a cross section of the ulnar nerve in the original image. AI focused on hyperechoic changes in the ulnar nerve epithelium and hypoechoic changes in the ulnar nerve interior and surrounding tissue.

References

    1. Staples J.R., Calfee R. Cubital tunnel syndrome: Current concepts. J. Am. Acad. Orthop. Surg. 2017;25:e215–e224. doi: 10.5435/JAAOS-D-15-00261.
    1. Latinovic R., Gulliford M.C., Hughes R.A. Incidence of common compressive neuropathies in primary care. J. Neurol. Neurosurg. Psychiatry. 2006;77:263–265. doi: 10.1136/jnnp.2005.066696.
    1. Nakashian M.N., Ireland D., Kane P.M. Cubital tunnel syndrome: Current concepts. Curr. Rev. Musculoskelet. Med. 2020;13:520–524. doi: 10.1007/s12178-020-09650-y.
    1. Naran S., Imbriglia J.E., Bilonick R.A., Taieb A., Wollstein R. A demographic analysis of cubital tunnel syndrome. Ann. Plast. Surg. 2010;64:177–179. doi: 10.1097/SAP.0b013e3181a2c63e.
    1. Schnabl S.M., Kisslinger F., Schramm A., Dragu A., Kneser U., Unglaub F., Horch R.E. Objective outcome of partial medial epicondylectomy in cubital tunnel syndrome. Arch. Orthop. Trauma Surg. 2010;130:1549–1556. doi: 10.1007/s00402-010-1160-x.
    1. American Association of Electrodiagnostic Medicine. Campbell W.W. Guidelines in electrodiagnostic medicine. Practice parameter for electrodiagnostic studies in ulnar neuropathy at the elbow. Muscle Nerve Suppl. 1999;8:S171–S205.
    1. Vucic S., Cordato D.J., Yiannikas C., Schwartz R.S., Shnier R.C. Utility of magnetic resonance imaging in diagnosing ulnar neuropathy at the elbow. Clin. Neurophysiol. 2006;117:590–595. doi: 10.1016/j.clinph.2005.09.022.
    1. Yoon J.S., Walker F.O., Cartwright M.S. Ulnar neuropathy with normal electrodiagnosis and abnormal nerve ultrasound. Arch. Phys. Med. Rehabil. 2010;91:318–320. doi: 10.1016/j.apmr.2009.10.010.
    1. Chen I.J., Chang K.V., Wu W.T., Ozcakar L. Ultrasound parameters other than the direct measurement of ulnar nerve size for diagnosing cubital tunnel syndrome: A systemic review and meta-analysis. Arch. Phys. Med. Rehabil. 2019;100:1114–1130. doi: 10.1016/j.apmr.2018.06.021.
    1. Chang K.V., Wu W.T., Han D.S., Ozcakar L. Ulnar nerve cross-sectional area for the diagnosis of cubital tunnel syndrome: A meta-analysis of ultrasonographic measurements. Arch. Phys. Med. Rehabil. 2018;99:743–757. doi: 10.1016/j.apmr.2017.08.467.
    1. Kalia V., Jacobson J.A. Imaging of Peripheral Nerves of the Upper Extremity. Radiol. Clin. N. Am. 2019;57:1063–1071. doi: 10.1016/j.rcl.2019.04.001.
    1. D’Souza J.C., Sultan L.R., Hunt S.J., Schultz S.M., Brice A.K., Wood A.K.W., Sehgal C.M. B-mode ultrasound for the assessment of hepatic fibrosis: A quantitative multiparametric analysis for a radiomics approach. Sci. Rep. 2019;9:8708. doi: 10.1038/s41598-019-45043-z.
    1. Weston A.D., Korfiatis P., Kline T.L., Philbrick K.A., Kostandy P., Sakinis T., Sugimoto M., Takahashi N., Erickson B.J. Automated abdominal segmentation of CT Scans for body composition analysis using deep learning. Radiology. 2019;290:669–679. doi: 10.1148/radiol.2018181432.
    1. Shin H.C., Roth H.R., Gao M., Lu L., Xu Z., Nogues I., Yao J., Mollura D., Summers R.M. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imaging. 2016;35:1285–1298. doi: 10.1109/TMI.2016.2528162.
    1. Apostolopoulos I.D., Mpesiana T.A. Covid-19: Automatic detection from X-ray images utilizing transfer learning with convolutional neural networks. Phys. Eng. Sci. Med. 2020;43:635–640. doi: 10.1007/s13246-020-00865-4.
    1. Olczak J., Fahlberg N., Maki A., Razavian A.S., Jilert A., Stark A., Skoldenberg O., Gordon M. Artificial intelligence for analyzing orthopedic trauma radiographs. Acta Orthop. 2017;88:581–586. doi: 10.1080/17453674.2017.1344459.
    1. Ma J., Wu F., Zhu J., Xu D., Kong D. A pre-trained convolutional neural network based method for thyroid nodule diagnosis. Ultrasonics. 2017;73:221–230. doi: 10.1016/j.ultras.2016.09.011.
    1. Zhou B., Khosla A., Lapedriza A., Oliva A., Torralba A. Learning deep features for discriminative localization; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR); Vegas, NV, USA. 27–30 June 2016; pp. 2921–2929.
    1. Lalehzarian S.P., Gowd A.K., Liu J.N. Machine learning in orthopaedic surgery. World J. Orthop. 2021;12:685–699. doi: 10.5312/wjo.v12.i9.685.
    1. Xue Y., Zhang R., Deng Y., Chen K., Jiang T. A preliminary examination of the diagnostic value of deep learning in hip osteoarthritis. PLoS ONE. 2017;12:e0178992. doi: 10.1371/journal.pone.0178992.
    1. Ashinsky B.G., Bouhrara M., Coletta C.E., Lehallier B., Urish K.L., Lin P.C., Goldberg I.G., Spencer R.G. Predicting early symptomatic osteoarthritis in the human knee using machine learning classification of magnetic resonance images from the osteoarthritis initiative. J. Orthop. Res. 2017;35:2243–2250. doi: 10.1002/jor.23519.
    1. Shubert D.J., Prud’homme J., Sraj S. Nerve conduction studies in surgical cubital tunnel syndrome patients. Hand. 2021;16:170–173. doi: 10.1177/1558944719840750.
    1. Aminu M., Ahmad N.A., Mohd Noor M.H. COVID-19 detection via deep neural network and occlusion sensitivity maps. Alex. Eng. J. 2021;60:4829–4855. doi: 10.1016/j.aej.2021.03.052.
    1. Srinivas S. A Machine Learning-Based Approach for Predicting Patient Punctuality in Ambulatory Care Centers. Int. J. Environ. Res. Public Health. 2020;17:3703. doi: 10.3390/ijerph17103703.
    1. Matsuo H., Nishio M., Kanda T., Kojita Y., Kono A.K., Hori M., Teshima M., Otsuki N., Nibu K.I., Murakami T. Diagnostic accuracy of deep-learning with anomaly detection for a small amount of imbalanced data: Discriminating malignant parotid tumors in MRI. Sci. Rep. 2020;10:19388. doi: 10.1038/s41598-020-76389-4.
    1. Padua L., Coraci D., Erra C., Pazzaglia C., Paolasso I., Loreti C., Caliandro P., Hobson-Webb L.D. Carpal tunnel syndrome: Clinical features, diagnosis, and management. Lancet Neurol. 2016;15:1273–1284. doi: 10.1016/S1474-4422(16)30231-9.
    1. Ng A.W.H., Griffith J.F., Lee R.K.L., Tse W.L., Wong C.W.Y., Ho P.C. Ultrasound carpal tunnel syndrome: Additional criteria for diagnosis. Clin. Radiol. 2018;73:214.e11–214.e18. doi: 10.1016/j.crad.2017.07.025.
    1. Kerasnoudis A., Tsivgoulis G. Nerve Ultrasound in Peripheral Neuropathies: A Review. J. Neuroimaging. 2015;25:528–538. doi: 10.1111/jon.12261.
    1. Tai T.W., Wu C.Y., Su F.C., Chern T.C., Jou I.M. Ultrasonography for diagnosing carpal tunnel syndrome: A meta-analysis of diagnostic test accuracy. Ultrasound Med. Biol. 2012;38:1121–1128. doi: 10.1016/j.ultrasmedbio.2012.02.026.
    1. Hadjiiski L.M., Tourassi G.D., Bar Y., Diamant I., Wolf L., Greenspan H. Deep learning with non-medical training used for chest pathology identification; Proceedings of the SPIE 9414, Medical Imaging 2015: Computer-Aided Diagnosis; Orlando, FL, USA. 22–25 February 2015;
    1. Jimenez-Sanchez A., Kazi A., Albarqouni S., Kirchhoff C., Biberthaler P., Navab N., Kirchhoff S., Mateus D. Precise proximal femur fracture classification for interactive training and surgical planning. Int. J. Comput. Assist. Radiol. Surg. 2020;15:847–857. doi: 10.1007/s11548-020-02150-x.
    1. Kalmet P.H.S., Sanduleanu S., Primakov S., Wu G., Jochems A., Refaee T., Ibrahim A., Hulst L.V., Lambin P., Poeze M. Deep learning in fracture detection: A narrative review. Acta Orthop. 2020;91:215–220. doi: 10.1080/17453674.2019.1711323.
    1. Tomita N., Cheung Y.Y., Hassanpour S. Deep neural networks for automatic detection of osteoporotic vertebral fractures on CT scans. Comput. Biol. Med. 2018;98:8–15. doi: 10.1016/j.compbiomed.2018.05.011.
    1. Smistad E., Johansen K.F., Iversen D.H., Reinertsen I. Highlighting nerves and blood vessels for ultrasound-guided axillary nerve block procedures using neural networks. J. Med. Imaging. 2018;5:044004. doi: 10.1117/1.JMI.5.4.044004.
    1. Jabeen K., Khan M.A., Alhaisoni M., Tariq U., Zhang Y.D., Hamza A., Mickus A., Damasevicius R. Breast Cancer Classification from Ultrasound Images Using Probability-Based Optimal Deep Learning Feature Fusion. Sensors. 2022;22:807. doi: 10.3390/s22030807.
    1. Tsai K.J., Chou M.C., Li H.M., Liu S.T., Hsu J.H., Yeh W.C., Hung C.M., Yeh C.Y., Hwang S.H. A High-Performance Deep Neural Network Model for BI-RADS Classification of Screening Mammography. Sensors. 2022;22:1160. doi: 10.3390/s22031160.
    1. Meraj T., Alosaimi W., Alouffi B., Rauf H.T., Kumar S.A., Damasevicius R., Alyami H. A quantization assisted U-Net study with ICA and deep features fusion for breast cancer identification using ultrasonic data. PeerJ Comput. Sci. 2021;7:e805. doi: 10.7717/peerj-cs.805.
    1. He K., Zhang X., Ren S., Sun J. Deep Residual Learning for Image Recognition. arXiv. 20151512.03385
    1. Zhang L., Li M., Zhou Y., Lu G., Zhou Q. Deep Learning Approach for Anterior Cruciate Ligament Lesion Detection: Evaluation of Diagnostic Performance Using Arthroscopy as the Reference Standard. J. Magn. Reson. Imaging. 2020;52:1745–1752. doi: 10.1002/jmri.27266.
    1. Zhang H., Han L., Chen K., Peng Y., Lin J. Diagnostic Efficiency of the Breast Ultrasound Computer-Aided Prediction Model Based on Convolutional Neural Network in Breast Cancer. J. Digit. Imaging. 2020;33:1218–1223. doi: 10.1007/s10278-020-00357-7.
    1. Sandler M., Howard A., Zhu M., Zhmoginov A., Chen L.-C. MobileNetV2: Inverted Residuals and Linear Bottlenecks. arXiv. 20191801.04381
    1. Gang L., Haixuan Z., Linning E., Ling Z., Yu L., Juming Z. Recognition of honeycomb lung in CT images based on improved MobileNet model. Med. Phys. 2021;48:4304–4315. doi: 10.1002/mp.14873.
    1. Wang J., Liu Q., Xie H., Yang Z., Zhou H. Boosted EfficientNet: Detection of Lymph Node Metastases in Breast Cancer Using Convolutional Neural Networks. Cancers. 2021;13:661. doi: 10.3390/cancers13040661.
    1. Tan M., Le Q.V. EfficientNet: Rethinking model scaling for convolutional neural networks; Proceedings of the 36th International Conference on Machine Learning; Long Beach, CA, USA. 9–15 June 2019; pp. 6105–6114.
    1. Selvaraju R.R., Cogswell M., Das A., Vedantam R., Parikh D., Batra D. Grad-CAM: Visual explanations from deep networks via gradient-based localization; Proceedings of the IEEE International Conference on Computer Vision (ICCV); Venice, Italy. 22–29 October 2017; pp. 618–626.
    1. Ahsan M.M., Nazim R., Siddique Z., Huebner P. Detection of COVID-19 patients from CT scan and chest X-ray data using modified MobileNetV2 and LIME. Healthcare. 2021;9:1099. doi: 10.3390/healthcare9091099.

Source: PubMed

Sponsoren und Mitarbeiter

Krankheiten

Drogeninterventionen

3
Abonnieren