{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T10:50:28Z","timestamp":1778323828032,"version":"3.51.4"},"reference-count":40,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T00:00:00Z","timestamp":1763942400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Intramural Research Program of NINDS, NIH"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Bioengineering"],"abstract":"<jats:p>Carpal tunnel syndrome (CTS) is the most common peripheral nerve entrapment, and ultrasound provides a fast, cost-efficient method for visualizing the median nerve. Reliable cross-sectional area (CSA) measurement remains challenging across imaging sites and varying scan qualities, and prior studies report segmentation Dice scores ranging from 0.76 to 0.93. Improving the robustness of automated segmentation is critical for achieving consistent, site-independent CSA assessment. This study evaluates a four-layer U-Net for automated segmentation and CSA estimation at two clinically relevant sites: the wrist crease and distal forearm. A primary dataset of 500 images per site was used to establish baseline performance. A second dataset of 35 wrist and 26 forearm still images was used to test generalizability, followed by intensity-based augmentations (CLAHE, gamma correction, speckle noise). Baseline models were tested on these new stills, and an augmented model was trained and evaluated on the combined datasets. The baseline models performed well on the first dataset but showed markedly reduced generalization on new still images (forearm IoU\/Dice: 0.185\/0.254; wrist IoU\/Dice: 0.137\/0.188). The augmented models improved within-set performance (forearm: 0.944\/0.971; wrist: 0.951\/0.974) and significantly enhanced generalization to new images (forearm: 0.408\/0.533; wrist: 0.705\/0.820). The final combined dataset models achieved Dice\/IoU scores of 0.94\/0.89 (forearm) and 0.96\/0.92 (wrist). CSA measurements showed excellent to moderate correlation with manual tracings across all datasets. These findings demonstrate that targeted intensity-based augmentation substantially improves model generalization and enables robust, reproducible, and site-independent median nerve segmentation, supporting scalable ultrasound-based CTS assessment.<\/jats:p>","DOI":"10.3390\/bioengineering12121289","type":"journal-article","created":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T10:24:17Z","timestamp":1763979857000},"page":"1289","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Utilization of a Deep Learning Algorithm for Automated Segmentation of Median Nerve from Ultrasound Obtained from the Distal Forearm and Wrist"],"prefix":"10.3390","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5432-6194","authenticated-orcid":false,"given":"Amad","family":"Qureshi","sequence":"first","affiliation":[{"name":"Department of Bioengineering, George Mason University, Fairfax, VA 22030, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyle","family":"Tse","sequence":"additional","affiliation":[{"name":"Electromyography Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA"},{"name":"Mid-Atlantic Permanente Medical Group, Department of Neurology, Washington, DC 20002, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6426-2320","authenticated-orcid":false,"given":"Siddhartha","family":"Sikdar","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, George Mason University, Fairfax, VA 22030, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yonatan","family":"Serlin","sequence":"additional","affiliation":[{"name":"Neurophysiology of Epilepsy Unit, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Atsede","family":"Akalu","sequence":"additional","affiliation":[{"name":"Electromyography Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianxia","family":"Wu","sequence":"additional","affiliation":[{"name":"Clinical Trials Unit, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5405-2143","authenticated-orcid":false,"given":"Katharine","family":"Alter","sequence":"additional","affiliation":[{"name":"Department of Rehabilitation Medicine, Clinical Center, National Institutes of Health, Bethesda, MD 20892, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0923-8413","authenticated-orcid":false,"given":"Qi","family":"Wei","sequence":"additional","affiliation":[{"name":"Department of Bioengineering, George Mason University, Fairfax, VA 22030, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6421-505X","authenticated-orcid":false,"given":"Tanya","family":"Lehky","sequence":"additional","affiliation":[{"name":"Electromyography Section, National Institute of Neurological Disorders and Stroke, National Institutes of Health, Bethesda, MD 20892, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2025,11,24]]},"reference":[{"key":"ref_1","first-page":"e63982","article-title":"Neuromuscular Ultrasound of the Median Nerve at the Carpal Tunnel","volume":"188","author":"Penry","year":"2022","journal-title":"J. Vis. Exp."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1055\/s-0041-1741088","article-title":"Ultrasound of Median Nerve in the Diagnosis of Carpal Tunnel Syndrome\u2014Correlation with Electrophysiological Studies","volume":"32","author":"Kanagasabai","year":"2022","journal-title":"Indian J. Radiol. Imaging"},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"1267","DOI":"10.1016\/j.clinph.2020.03.013","article-title":"Very high-resolution ultrasound of the distal median nerve","volume":"131","author":"Ridolfi","year":"2020","journal-title":"Clin. Neurophysiol."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"420","DOI":"10.1111\/jon.12982","article-title":"Median and ulnar nerve fascicle imaging using MR microscopy and high-resolution ultrasound","volume":"32","author":"Igor","year":"2022","journal-title":"J. Neuroimaging"},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Liu, B., Zhang, Y., Zhang, L., Zhang, F., Li, H., Li, S., Liu, Y., Du, J., and Zhao, L. (2017). A rare case of bilateral cervical vagal neurofibromas: Role of high-resolution ultrasound. BMC Neurol., 17.","DOI":"10.1186\/s12883-017-0806-5"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"82","DOI":"10.15557\/JoU.2013.0007","article-title":"Ultrasound assessment of selected peripheral nerve pathologies. Part III: Injuries and postoperative evaluation","volume":"13","author":"Kowalska","year":"2013","journal-title":"J. Ultrason."},{"key":"ref_7","unstructured":"Sevy, J.O., Sina, R.E., and Varacallo, M.A. (2025, November 18). Carpal Tunnel Syndrome, StatPearls, Available online: http:\/\/www.ncbi.nlm.nih.gov\/books\/NBK448179\/."},{"key":"ref_8","first-page":"e27053","article-title":"Carpal Tunnel Syndrome: Pathophysiology and Comprehensive Guidelines for Clinical Evaluation and Treatment","volume":"14","author":"Joshi","year":"2022","journal-title":"Cureus"},{"key":"ref_9","first-page":"e7333","article-title":"Carpal Tunnel Syndrome: A Review of Literature","volume":"12","author":"Genova","year":"2020","journal-title":"Cureus"},{"key":"ref_10","unstructured":"Rosario, N.B., and De Jesus, O. (2024, April 17). Electrodiagnostic Evaluation of Carpal Tunnel Syndrome, StatPearls, Available online: http:\/\/www.ncbi.nlm.nih.gov\/books\/NBK562235\/."},{"key":"ref_11","doi-asserted-by":"crossref","unstructured":"Heiling, B., Wiedfeld, L.I., M\u00fcller, N., Kobler, N.J., Grimm, A., Kloos, C., and Axer, H. (2022). Electrodiagnostic Testing and Nerve Ultrasound of the Carpal Tunnel in Patients with Type 2 Diabetes. J. Clin. Med., 11.","DOI":"10.3390\/jcm11123374"},{"key":"ref_12","doi-asserted-by":"crossref","unstructured":"Dong, Y., Alhaskawi, A., Zhou, H., Zou, X., Liu, Z., Ezzi, S.H.A., Kota, V.G., Abdulla, M.H.A.H., Olga, A., and Abdalbary, S.A. (2023). Imaging diagnosis in peripheral nerve injury. Front. Neurol., 14.","DOI":"10.3389\/fneur.2023.1250808"},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"101","DOI":"10.4329\/wjr.v12.i6.101","article-title":"Current and future applications of ultrasound imaging in peripheral nerve disorders","volume":"12","author":"Carroll","year":"2020","journal-title":"World J. Radiol."},{"key":"ref_14","unstructured":"Hafiane, A., Vieyres, P., and Delbos, A. (2017). Deep Learning with Spatiotemporal Consistency for Nerve Segmentation in Ultrasound Images. arXiv."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"1964","DOI":"10.1016\/j.ultrasmedbio.2021.03.018","article-title":"Automated Segmentation of the Median Nerve in the Carpal Tunnel using U-Net","volume":"47","author":"Festen","year":"2021","journal-title":"Ultrasound Med. Biol."},{"key":"ref_16","first-page":"3025","article-title":"Learning-Based Median Nerve Segmentation From Ultrasound Images For Carpal Tunnel Syndrome Evaluation","volume":"2021","author":"Cosmo","year":"2021","journal-title":"Annu. Int. Conf. IEEE Eng. Med. Biol. Soc."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"38","DOI":"10.1186\/s13075-022-02729-6","article-title":"Development of a convolutional neural network for the identification and the measurement of the median nerve on ultrasound images acquired at carpal tunnel level","volume":"24","author":"Smerilli","year":"2022","journal-title":"Arthritis Res. Ther."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"304","DOI":"10.1016\/j.ultrasmedbio.2023.10.009","article-title":"One-Stop Automated Diagnostic System for Carpal Tunnel Syndrome in Ultrasound Images Using Deep Learning","volume":"50","author":"Peng","year":"2024","journal-title":"Ultrasound Med. Biol."},{"key":"ref_19","doi-asserted-by":"crossref","unstructured":"Moser, F., Muller, S., Lie, T., Lang\u00f8, T., and Hoff, M. (2024). Automated segmentation of the median nerve in patients with carpal tunnel syndrome. Sci. Rep., 14.","DOI":"10.1038\/s41598-024-65840-5"},{"key":"ref_20","first-page":"194","article-title":"Ultrasound parameters to identify and diagnose carpal tunnel syndrome. A review of the literature","volume":"23","author":"Linehan","year":"2020","journal-title":"J. Ultrasound Med."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Yoshii, Y., Zhao, C., and Amadio, P.C. (2020). Recent Advances in Ultrasound Diagnosis of Carpal Tunnel Syndrome. Diagnostics, 10.","DOI":"10.3390\/diagnostics10080596"},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"295","DOI":"10.55519\/JAMC-02-9892","article-title":"Assessment Of Carpal Tunnel Syndrome with Ultrasonography","volume":"34","author":"Ahmed","year":"2022","journal-title":"J. Ayub Med. Coll. Abbottabad"},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"273","DOI":"10.1007\/s10278-019-00211-5","article-title":"Feature Enhancement in Medical Ultrasound Videos Using Contrast-Limited Adaptive Histogram Equalization","volume":"33","author":"Singh","year":"2020","journal-title":"J. Digit. Imaging"},{"key":"ref_24","unstructured":"Tupper, A., and Gagn\u00e9, C. (2025). Revisiting Data Augmentation for Ultrasound Images. arXiv."},{"key":"ref_25","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., Fischer, P., and Brox, T. (2015). U-Net: Convolutional Networks for Biomedical Image Segmentation. Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015, Springer International Publishing.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref_26","doi-asserted-by":"crossref","unstructured":"Qureshi, A., Lim, S., Suh, S.Y., Mutawak, B., Chitnis, P.V., Demer, J.L., and Wei, Q. (2023). Deep-Learning-Based Segmentation of Extraocular Muscles from Magnetic Resonance Images. Bioengineering, 10.","DOI":"10.3390\/bioengineering10060699"},{"key":"ref_27","doi-asserted-by":"crossref","unstructured":"Muller, D., Soto-Rey, I., and Kramer, F. (2022). Towards a guideline for evaluation metrics in medical image segmentation. BMC Res. Notes, 15.","DOI":"10.1186\/s13104-022-06096-y"},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"47","DOI":"10.1111\/j.1552-6569.2008.00256.x","article-title":"Ultrasonographic reference values for assessing the normal median nerve in adults","volume":"19","author":"Cartwright","year":"2009","journal-title":"J. Neuroimaging"},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"102496","DOI":"10.1016\/j.artmed.2023.102496","article-title":"Application of deep learning algorithms in automatic sonographic localization and segmentation of the median nerve: A systematic review and meta-analysis","volume":"137","author":"Wang","year":"2023","journal-title":"Artif. Intell. Med."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"145714","DOI":"10.1109\/ACCESS.2025.3599358","article-title":"Yolo in healthcare: A comprehensive review of detection architectures, domain applications, and future innovations","volume":"13","author":"Palaniappan","year":"2025","journal-title":"IEEE Access"},{"key":"ref_31","first-page":"790","article-title":"Neuromuscular ultrasound in polyneuropathies and motor neuron disease","volume":"47","year":"2023","journal-title":"Muscle Nerve"},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"15","DOI":"10.1109\/TMI.2022.3202248","article-title":"A vit-amc network with adaptive model fusion and multiobjective optimization for interpretable laryngeal tumor grading from histopathological images","volume":"42","author":"Huang","year":"2023","journal-title":"IEEE Trans. Med. Imaging"},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"102333","DOI":"10.1016\/j.inffus.2024.102333","article-title":"MamlFormer: Priori-experience guiding transformer network via manifold adversarial multi-modal learning for laryngeal histopathological grading","volume":"108","author":"Huang","year":"2024","journal-title":"Inf. Fusion"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Qu, Y., Zhou, X., Huang, P., Liu, Y., Mercaldo, F., Santone, A., and Feng, P. (2025). CGAM: An end-to-end causality graph attention Mamba network for esophageal pathology grading. Biomed. Signal Process. Control, 103.","DOI":"10.1016\/j.bspc.2024.107452"},{"key":"ref_35","first-page":"2365","article-title":"Fdts: A feature disentangled transformer for interpretable squamous cell carcinoma grading","volume":"12","author":"Huang","year":"2024","journal-title":"IEEE\/CAA J. Autom. Sin."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"223","DOI":"10.1186\/s13244-025-02113-3","article-title":"Predicting pathological subtypes of pure ground-glass nodules using Swin Transformer deep learning model","volume":"16","author":"Wen","year":"2025","journal-title":"Insights Into Imaging"},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"8581","DOI":"10.1007\/s00432-023-04795-y","article-title":"The Swin-Transformer network based on focal loss is used to identify images of pathological subtypes of lung adenocarcinoma with high similarity and class imbalance","volume":"149","author":"Wang","year":"2023","journal-title":"J. Cancer Res. Clin. Oncol."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"111719","DOI":"10.1016\/j.ymssp.2024.111719","article-title":"Automated ultrasonic-based diagnosis of concrete compressive damage amidst temperature variations utilizing deep learning","volume":"221","author":"Wang","year":"2024","journal-title":"Mech. Syst. Signal Process."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"e30590","DOI":"10.1016\/j.heliyon.2024.e30590","article-title":"Deep convolutional neural network for weld defect classification in radiographic images","volume":"10","year":"2024","journal-title":"Heliyon"},{"key":"ref_40","doi-asserted-by":"crossref","first-page":"1757","DOI":"10.1002\/jum.14864","article-title":"Association between muscle strength and modeling estimates of muscle tissue heterogeneity in young and old adults","volume":"38","author":"Gonzales","year":"2019","journal-title":"J. Ultrasound Med."}],"container-title":["Bioengineering"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/12\/1289\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,24]],"date-time":"2025-11-24T11:19:51Z","timestamp":1763983191000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/2306-5354\/12\/12\/1289"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,24]]},"references-count":40,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["bioengineering12121289"],"URL":"https:\/\/doi.org\/10.3390\/bioengineering12121289","relation":{},"ISSN":["2306-5354"],"issn-type":[{"value":"2306-5354","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,24]]}}}