Automated segmentation of the median nerve in patients with carpal tunnel syndrome.


Journal

Scientific reports
ISSN: 2045-2322
Titre abrégé: Sci Rep
Pays: England
ID NLM: 101563288

Informations de publication

Date de publication:
20 Jul 2024
Historique:
received: 13 03 2024
accepted: 24 06 2024
medline: 21 7 2024
pubmed: 21 7 2024
entrez: 20 7 2024
Statut: epublish

Résumé

Machine learning and deep learning are novel methods which are revolutionizing medical imaging. In our study we trained an algorithm with a U-Net shaped network to recognize ultrasound images of the median nerve in the complete distal half of the forearm and to measure the cross-sectional area at the inlet of the carpal tunnel. Images of 25 patient hands with carpal tunnel syndrome (CTS) and 26 healthy controls were recorded on a video loop covering 15 cm of the distal forearm and 2355 images were manually segmented. We found an average Dice score of 0.76 between manual and automated segmentation of the median nerve in its complete course, while the measurement of the cross-sectional area at the carpal tunnel inlet resulted in a 10.9% difference between manually and automated measurements. We regard this technology as a suitable device for verifying the diagnosis of CTS.

Identifiants

pubmed: 39033223
doi: 10.1038/s41598-024-65840-5
pii: 10.1038/s41598-024-65840-5
doi:

Types de publication

Journal Article

Langues

eng

Sous-ensembles de citation

IM

Pagination

16757

Subventions

Organisme : Joint research Committee
ID : Ref.: 2023/36515
Organisme : The Norwegian Medical Association
ID : Ref.: SAK2022001094
Organisme : Grethe Harbitz Legate
ID : Ref.: P-103661-01

Informations de copyright

© 2024. The Author(s).

Références

Foley, M., Silverstein, B. & Polissar, N. The economic burden of carpal tunnel syndrome: Long-term earnings of CTS claimants in Washington State. Am. J. Ind. Med. 50, 155–172. https://doi.org/10.1002/ajim.20430 (2007).
doi: 10.1002/ajim.20430 pubmed: 17216630
Aroori, S. & Spence, R. A. J. Carpal tunnel syndrome. Ulster Med. J. 77, 6–17 (2008).
pubmed: 18269111 pmcid: 2397020
Atroshi, I. et al. Prevalence of carpal tunnel syndrome in a general population. JAMA 282(2), 153–158. https://doi.org/10.1001/jama.282.2.153 (1999).
doi: 10.1001/jama.282.2.153 pubmed: 10411196
Ferry, S., Pritchard, T., Keenan, J., Croft, P. & Silman, A. Estimating the prevalence of delayed median nerve conduction in the general population. Br. J. Rheumatol. 37(6), 630–635. https://doi.org/10.1093/rheumatology/37.6.630 (1998).
doi: 10.1093/rheumatology/37.6.630 pubmed: 9667616
Stevens, J. C., Sun, S., Beard, C. M., O’Fallon, W. M. & Kurland, L. T. Carpal tunnel syndrome in Rochester, Minnesota, 1961 to 1980. Neurology 38, 134–138. https://doi.org/10.1212/wnl.38.1.134 (1988).
doi: 10.1212/wnl.38.1.134 pubmed: 3336444
Jablecki, C., Andary, M., So, Y., Wilkins, D. & Williams, F. Literature review of the usefulness of nerve conduction studies and electromyography for the evaluation of patients with carpal tunnel syndrome. AAEM Qual. Assur. Comm. Muscle Nerve 16(12), 1392–414. https://doi.org/10.1002/mus.880161220 (1993).
doi: 10.1002/mus.880161220
Keleş, I., Karagülle Kendi, A., Aydin, G., Zöǧ, S. & Orkun, S. Diagnostic precision of ultrasonography in patients with carpal tunnel syndrome. Am. J. Phys. Med. Rehabil. 84(6), 443–450. https://doi.org/10.1097/01.phm.0000163715.11645.96 (2005).
doi: 10.1097/01.phm.0000163715.11645.96 pubmed: 15905658
Cartwright, M. et al. Ultrasound for carpal tunnel syndrome screening in manual laborers. Muscle Nerve 48(1), 127–131. https://doi.org/10.1002/mus.23735 (2013).
doi: 10.1002/mus.23735 pubmed: 23649357 pmcid: 3878605
Tai, T., Wu, C., Su, F., Chern, T. & Jou, I. Ultrasonography for diagnosing carpal tunnel syndrome: A meta-analysis of diagnostic test accuracy. Ultrasound Med. Biol. 38(7), 1121–1128. https://doi.org/10.1016/j.ultrasmedbio.2012.02.026 (2012).
doi: 10.1016/j.ultrasmedbio.2012.02.026 pubmed: 22542258
Erickson, M., Lawrence, M. & Lucado, A. The role of diagnostic ultrasound in the examination of carpal tunnel syndrome: An update and systematic review. J. Hand Ther. 35(2), 215–225. https://doi.org/10.1016/j.jht.2021.04.014 (2022).
doi: 10.1016/j.jht.2021.04.014 pubmed: 34261588
Lundborg, G. & Dahlin, L. Anatomy, function, and pathophysiology of peripheral nerves and nerve compression. Hand Clin. 12(2), 185–193 (1996).
doi: 10.1016/S0749-0712(21)00303-6 pubmed: 8724572
Evans, K., Roll, S., Volz, K. & Freimer, M. Relationship between intraneural vascular flow measured with sonography and carpal tunnel syndrome diagnosis based on electrodiagnostic testing. J. Ultrasound Med. 31(5), 729–736. https://doi.org/10.7863/jum.2012.31.5.729 (2012).
doi: 10.7863/jum.2012.31.5.729 pubmed: 22535720 pmcid: 3673781
Tagliafico, A., Tagliafico, G. & Martinoli, C. Nerve density: A new parameter to evaluate peripheral nerve pathology on ultrasound. Preliminary study. Ultrasound Med. Biol. 36(10), 1588–1593. https://doi.org/10.1016/j.ultrasmedbio.2010.07.009 (2010).
doi: 10.1016/j.ultrasmedbio.2010.07.009 pubmed: 20850025
Torres-Costoso, A., Martínez-Vizcaíno, V., Álvarez Bueno, C., Ferri-Morales, A. & Cavero-Redondo, I. Accuracy of ultrasonography for the diagnosis of carpal tunnel syndrome: A systematic review and meta-analysis. Arch. Phys. Med. Rehabil. https://doi.org/10.1016/j.apmr.2017.08.489 (2018).
doi: 10.1016/j.apmr.2017.08.489 pubmed: 28947163
Terslev, L. et al. Scoring ultrasound synovitis in rheumatoid arthritis: A EULAR-OMERACT ultrasound taskforce-Part 2: Reliability and application to multiple joints of a standardised consensus-based scoring system. RMD Open https://doi.org/10.1136/rmdopen-2016-000427 (2017).
doi: 10.1136/rmdopen-2016-000427 pubmed: 28948984 pmcid: 5597800
Filippucci, E. et al. Ultrasound imaging for the rheumatologist VII. Ultrasound imaging in rheumatoid arthritis. Clin. Exp. Rheumatol. 25, 5–10 (2007).
pubmed: 17417983
Di Cosmo, M. et al. A deep learning approach to median nerve evaluation in ultrasound images of carpal tunnel inlet. Med. Biol. Eng. Comput. 60, 3255–3264. https://doi.org/10.1007/s11517-022-02662-5 (2022).
doi: 10.1007/s11517-022-02662-5 pubmed: 36152237 pmcid: 9537213
Park, S. Artificial intelligence for ultrasonography: Unique opportunities and challenges. Ultrasonography 40(1), 3–6. https://doi.org/10.14366/usg.20078 (2021).
doi: 10.14366/usg.20078 pubmed: 33227844
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 5, 044004. https://doi.org/10.1117/1.JMI.5.4.044004 (2018).
doi: 10.1117/1.JMI.5.4.044004
Ng, A., Chandrasekaran, R., Prakash, A. & Mogali, S. A systematic review: Normative reference values of the median nerve cross-sectional area using ultrasonography in healthy individuals. Sci. Rep. https://doi.org/10.1038/s41598-022-13058-8 (2022).
doi: 10.1038/s41598-022-13058-8 pubmed: 36577798 pmcid: 9797562
Klauser, A. et al. Carpal tunnel syndrome assessment with US: Value of additional cross-sectional area measurements of the median nerve in patients versus healthy volunteers. Radiology 250(1), 171–177. https://doi.org/10.1148/radiol.2501080397 (2009).
doi: 10.1148/radiol.2501080397 pubmed: 19037017
Smistad, E., Østvik, A. & Løvstakken, L. Annotation Web—An open-source web-based annotation tool for ultrasound images. In Proceedings—IEEE Ultrasonics Symposium (Institute of Electrical and Electronics Engineers (IEEE), 2021), accepted 15 February 2022. T12:42:27Z; https://doi.org/10.1109/IUS52206.2021.9593336
Ronneberger, O., Fischer, P. & Brox, T. U-Net: Convolutional networks for biomedical image segmentation. https://doi.org/10.48550/arXiv.1505.04597 (2015). ArXiv:1505.04597 [cs].
Wang, J. et al. Application of deep learning algorithms in automatic sonographic localization and segmentation of the median nerve: A systematic review and meta-analysis. Artif. Intell. Med. https://doi.org/10.1016/j.artmed.2023.102496 (2023).
doi: 10.1016/j.artmed.2023.102496 pubmed: 38184362 pmcid: 10201018
Dejaco, C. et al. Ultrasound for diagnosis of carpal tunnel syndrome: Comparison of different methods to determine median nerve volume and value of power Doppler sonography. Ann. Rheum. Dis. 72, 1934–1939. https://doi.org/10.1136/annrheumdis-2012-202328 (2013).
doi: 10.1136/annrheumdis-2012-202328 pubmed: 23212030
Faeghi, F. et al. Accurate automated diagnosis of carpal tunnel syndrome using radiomics features with ultrasound images: A comparison with radiologists’ assessment. Eur. J. Radiol. https://doi.org/10.1016/j.ejrad.2020.109518 (2021).
doi: 10.1016/j.ejrad.2020.109518 pubmed: 33434859
Rahmani, M. et al. The ultrasonographic correlates of carpal tunnel syndrome in patients with normal electrodiagnostic tests. La Radiol. Medica 116, 489–496. https://doi.org/10.1007/s11547-011-0632-6 (2011).
doi: 10.1007/s11547-011-0632-6
Shinohara, I. et al. Using deep learning for ultrasound images to diagnose carpal tunnel syndrome with high accuracy. Ultrasound Med. Biol. 48, 2052–2059. https://doi.org/10.1016/j.ultrasmedbio.2022.05.030 (2022).
doi: 10.1016/j.ultrasmedbio.2022.05.030 pubmed: 35868907
Ikumi, A. et al. Potential relationships between the median nerve cross-sectional area and physical characteristics in unilateral symptomatic carpal tunnel syndrome patients. J. Clin. Med. 12, 2515. https://doi.org/10.3390/jcm12072515 (2023).
doi: 10.3390/jcm12072515 pubmed: 37048599 pmcid: 10095503
Walker, F. et al. Prevalence of bifid median nerves and persistent median arteries and their association with carpal tunnel syndrome in a sample of Latino poultry processors and other manual workers. Muscle Nerve 48(4), 539–544. https://doi.org/10.1002/mus.23797 (2013) (Epub 2013 Aug 27. Erratum in: Muscle Nerve).
doi: 10.1002/mus.23797 pubmed: 24037717 pmcid: 3836559
Granata, G. et al. Prevalence of bifid median nerve at wrist assessed through ultrasound. Neurol. Sci. Off. J. Italian Neurol. Soc. Italian Soc. Clin. Neurophysiol. 32, 615–618. https://doi.org/10.1007/s10072-011-0582-8 (2011).
doi: 10.1007/s10072-011-0582-8
Smerilli, G. et al. Development of a convolutional neural network for the identification and the measurement of the median nerve on ultrasound images acquired at carpal tunnel level. Arthritis Res. Ther. 24, 38. https://doi.org/10.1186/s13075-022-02729-6 (2022).
doi: 10.1186/s13075-022-02729-6 pubmed: 35135598 pmcid: 8822696

Auteurs

Florentin Moser (F)

Department of Rheumatology, St. Olavs Hospital, Trondheim, Norway. florentin.moser@stolav.no.
Department of Neuromedicine and Movement Science, Norwegian University of Science and Technology, Trondheim, Norway. florentin.moser@stolav.no.

Sébastien Muller (S)

Department of Health Research, SINTEF Digital, Trondheim, Norway.

Torgrim Lie (T)

Department of Health Research, SINTEF Digital, Trondheim, Norway.

Thomas Langø (T)

Department of Health Research, SINTEF Digital, Trondheim, Norway.
Department of Research, St. Olavs Hospital, Trondheim, Norway.

Mari Hoff (M)

Department of Rheumatology, St. Olavs Hospital, Trondheim, Norway.
Department of Neuromedicine and Movement Science, Norwegian University of Science and Technology, Trondheim, Norway.

Articles similaires

[Redispensing of expensive oral anticancer medicines: a practical application].

Lisanne N van Merendonk, Kübra Akgöl, Bastiaan Nuijen
1.00
Humans Antineoplastic Agents Administration, Oral Drug Costs Counterfeit Drugs

Smoking Cessation and Incident Cardiovascular Disease.

Jun Hwan Cho, Seung Yong Shin, Hoseob Kim et al.
1.00
Humans Male Smoking Cessation Cardiovascular Diseases Female
Humans United States Aged Cross-Sectional Studies Medicare Part C
1.00
Humans Yoga Low Back Pain Female Male

Classifications MeSH