{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,14]],"date-time":"2026-10-14T11:09:49Z","timestamp":1791976189516,"version":"4.4.0"},"reference-count":18,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,12,11]],"date-time":"2021-12-11T00:00:00Z","timestamp":1639180800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,12,11]],"date-time":"2021-12-11T00:00:00Z","timestamp":1639180800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003161","name":"forschungskuratorium textil, bundesministerium f\u00fcr wirtschaft und energie","doi-asserted-by":"publisher","award":["01MK20003P"],"award-info":[{"award-number":["01MK20003P"]}],"id":[{"id":"10.13039\/501100003161","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Universit\u00e4tsklinikum Leipzig"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Spine J"],"published-print":{"date-parts":[[2022,3]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This single-center study aimed to develop a convolutional neural network to segment multiple consecutive axial magnetic resonance imaging (MRI) slices of the lumbar spinal muscles of patients with lower back pain and automatically classify fatty muscle degeneration.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We developed a fully connected deep convolutional neural network (CNN) with a pre-trained U-Net model trained on a dataset of 3,650 axial T2-weighted MRI images from 100 patients with lower back pain. We included all qualities of MRI; the exclusion criteria were fractures, tumors, infection, or spine implants. The training was performed using k-fold cross-validation (k\u2009=\u200910), and performance was evaluated using the dice similarity coefficient (DSC) and cross-sectional area error (CSA error). For clinical correlation, we used a simplified Goutallier classification (SGC) system with three classes.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The mean DSC was high for overall muscle (0.91) and muscle tissue segmentation (0.83) but showed deficiencies in fatty tissue segmentation (0.51). The CSA error was small for the overall muscle area of 8.42%, and fatty tissue segmentation showed a high mean CSA error of 40.74%. The SGC classification was correctly predicted in 75% of the patients.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Our fully connected CNN segmented overall muscle and muscle tissue with high precision and recall, as well as good DSC values. The mean predicted SGC values of all available patient axial slices showed promising results. With an overall Error of 25%, further development is needed for clinical implementation. Larger datasets and training of other model architectures are required to segment fatty tissue more accurately.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00586-021-07073-y","type":"journal-article","created":{"date-parts":[[2021,12,11]],"date-time":"2021-12-11T03:02:30Z","timestamp":1639191750000},"page":"774-782","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Analysis of the paraspinal muscle morphology of the lumbar spine using a convolutional neural network (CNN)"],"prefix":"10.1007","volume":"31","author":[{"given":"David","family":"Baur","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Richard","family":"Bieck","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Johann","family":"Berger","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juliane","family":"Neumann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jeanette","family":"Henkelmann","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thomas","family":"Neumuth","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christoph-E.","family":"Heyde","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2715-5438","authenticated-orcid":false,"given":"Anna","family":"Voelker","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,12,11]]},"reference":[{"key":"7073_CR1","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1186\/1741-7015-5-2","volume":"5","author":"P Kjaer","year":"2007","unstructured":"Kjaer P, Bendix T, Sorensen JS, Korsholm L, Leboeuf-Yde C (2007) Are MRI-defined fat infiltrations in the multifidus muscles associated with low back pain? BMC Med 5:2. https:\/\/doi.org\/10.1186\/1741-7015-5-2","journal-title":"BMC Med"},{"issue":"1","key":"7073_CR2","doi-asserted-by":"publisher","first-page":"414","DOI":"10.1186\/s12891-019-2786-7","volume":"20","author":"C Faur","year":"2019","unstructured":"Faur C, Patrascu JM, Haragus H, Anglitoiu B (2019) Correlation between multifidus fatty atrophy and lumbar disc degeneration in low back pain. BMC Musculoskelet Disord 20(1):414. https:\/\/doi.org\/10.1186\/s12891-019-2786-7","journal-title":"BMC Musculoskelet Disord"},{"key":"7073_CR3","doi-asserted-by":"publisher","first-page":"20200015","DOI":"10.2490\/prm.20200015","volume":"5","author":"T Miki","year":"2020","unstructured":"Miki T, Naoki F, Takashima H, Takebayashi T (2020) Associations between paraspinal muscle morphology, disc degeneration, and clinical features in patients with lumbar spinal stenosis. Prog rehabil med 5:20200015. https:\/\/doi.org\/10.2490\/prm.20200015","journal-title":"Prog rehabil med"},{"key":"7073_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.3171\/2020.6.SPINE20238","volume":"30","author":"P-G Duan","year":"2020","unstructured":"Duan P-G, Mummaneni PV, Guinn JMV, Rivera J, Berven SH, Chou D (2020) Is the Goutallier grade of multifidus fat infiltration associated with adjacent-segment degeneration after lumbar spinal fusion? Journal Neurosurg Spine 30:1\u20136. https:\/\/doi.org\/10.3171\/2020.6.SPINE20238","journal-title":"Journal Neurosurg Spine"},{"key":"7073_CR5","doi-asserted-by":"publisher","DOI":"10.1007\/s00402-021-03754-x","author":"A Stanuszek","year":"2021","unstructured":"Stanuszek A, J\u0119drzejek A, Gancarczyk-Urlik E, Ko\u0142odziej I, Pisarska-Adamczyk M, Milczarek O et al (2021) Preoperative paraspinal and psoas major muscle atrophy and paraspinal muscle fatty degeneration as factors influencing the results of surgical treatment of lumbar disc disease. Arch Orthop Trauma Surg. https:\/\/doi.org\/10.1007\/s00402-021-03754-x","journal-title":"Arch Orthop Trauma Surg"},{"issue":"6","key":"7073_CR6","doi-asserted-by":"publisher","first-page":"401","DOI":"10.1097\/RLI.0000000000000755","volume":"56","author":"T Kart","year":"2021","unstructured":"Kart T, Fischer M, K\u00fcstner T, Hepp T, Bamberg F, Winzeck S et al (2021) Deep learning-based automated abdominal organ segmentation in the UK Biobank and German national cohort magnetic resonance imaging studies. Invest Radiol 56(6):401\u2013408. https:\/\/doi.org\/10.1097\/RLI.0000000000000755","journal-title":"Invest Radiol"},{"issue":"1","key":"7073_CR7","doi-asserted-by":"publisher","first-page":"88","DOI":"10.3348\/kjr.2019.0470","volume":"21","author":"HJ Park","year":"2020","unstructured":"Park HJ, Shin Y, Park J, Kim H, Lee IS, Seo DW et al (2020) Development and validation of a deep learning system for segmentation of abdominal muscle and fat on computed tomography. Korean J Radiol 21(1):88\u2013100. https:\/\/doi.org\/10.3348\/kjr.2019.0470","journal-title":"Korean J Radiol"},{"issue":"9","key":"7073_CR8","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.3390\/app8091656","volume":"8","author":"S Kim","year":"2018","unstructured":"Kim S, Bae WC, Masuda K, Chung CB, Hwang D (2018) Fine-Grain segmentation of the intervertebral discs from MR spine images using deep convolutional neural networks: BSU-net. Appl sci. 8(9):1656. https:\/\/doi.org\/10.3390\/app8091656","journal-title":"Appl sci."},{"key":"7073_CR9","doi-asserted-by":"publisher","first-page":"82031","DOI":"10.1109\/ACCESS.2021.3086020","volume":"9","author":"N Siddique","year":"2021","unstructured":"Siddique N, Sidike P, Elkin C, Devabhaktuni V (2021) U-Net and its variants for medical image segmentation: theory and applications. IEEE Access 9:82031\u201382057. https:\/\/doi.org\/10.1109\/ACCESS.2021.3086020","journal-title":"IEEE Access"},{"issue":"8","key":"7073_CR10","doi-asserted-by":"publisher","first-page":"1199","DOI":"10.3390\/electronics9081199","volume":"9","author":"M Bardis","year":"2020","unstructured":"Bardis M, Houshyar R, Chantaduly C, Ushinsky A, Glavis-Bloom J, Shaver M (2020) Deep learning with limited data: organ segmentation performance by U net. In: Electronics 9(8):1199. https:\/\/doi.org\/10.3390\/electronics9081199","journal-title":"In: Electronics"},{"issue":"1","key":"7073_CR11","doi-asserted-by":"publisher","first-page":"176","DOI":"10.2106\/JBJS.G.01311","volume":"91","author":"SR Ward","year":"2009","unstructured":"Ward SR, Kim CW, Eng CM, Gottschalk LJ, Tomiya A, Garfin SR, Lieber RL (2009) Architectural analysis and intraoperative measurements demonstrate the unique design of the multifidus muscle for lumbar spine stability. The J. bone and joint surg American Vol. 91(1):176\u2013185","journal-title":"The J. bone and joint surg American Vol."},{"issue":"8","key":"7073_CR12","doi-asserted-by":"publisher","first-page":"1728","DOI":"10.1177\/0363546512452714","volume":"40","author":"MA Slabaugh","year":"2012","unstructured":"Slabaugh MA, Friel NA, Karas V, Romeo AA, Verma NN, Cole BJ (2012) Interobserver and intraobserver reliability of the Goutallier classification using magnetic resonance imaging: proposal of a simplified classification system to increase reliability. Am J Sports Med 40(8):1728\u20131734. https:\/\/doi.org\/10.1177\/0363546512452714","journal-title":"Am J Sports Med"},{"key":"7073_CR13","unstructured":"Ronneberger O, Fischer P, Brox T (2015) U-Net: Convolutional networks for biomedical image segmentation. Accessed on 6\/19\/2021 at http:\/\/arxiv.org\/pdf\/1505.04597v1"},{"issue":"2","key":"7073_CR14","doi-asserted-by":"publisher","first-page":"125","DOI":"10.3390\/info11020125","volume":"11","author":"A Buslaev","year":"2020","unstructured":"Buslaev A, Iglovikov VI, Khvedchenya E, Parinov A, Druzhinin M, Kalinin AA (2020) Albumentations: fast and flexible image augmentations. Information 11(2):125. https:\/\/doi.org\/10.3390\/info11020125","journal-title":"Information"},{"key":"7073_CR15","doi-asserted-by":"crossref","unstructured":"Wang P, Chung, ACS (2018) Focal Dice Loss and Image Dilation for Brain Tumor Segmentation. In: Stoyanov D, Taylor Z, Carneiro G, Syeda-Mahmood T, Martel A, Maier-Hein L et al. (Hg.): Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support, Bd. 11045. Cham: Springer International Publishing (Lecture Notes in Computer Science), p 119\u2013127","DOI":"10.1007\/978-3-030-00889-5_14"},{"issue":"12","key":"7073_CR16","doi-asserted-by":"publisher","first-page":"1686","DOI":"10.1016\/j.acra.2019.06.017","volume":"26","author":"R Barnard","year":"2019","unstructured":"Barnard R, Tan J, Roller B, Chiles C, Weaver AA, Boutin RD et al (2019) Machine learning for automatic paraspinous muscle area and attenuation measures on low-dose chest CT scans. Acad Radiol 26(12):1686\u20131694. https:\/\/doi.org\/10.1016\/j.acra.2019.06.017","journal-title":"Acad Radiol"},{"issue":"1","key":"7073_CR17","doi-asserted-by":"publisher","first-page":"92","DOI":"10.1016\/j.jocd.2018.04.001","volume":"3","author":"AKO Wong","year":"2020","unstructured":"Wong AKO, Manske SL (2020) A comparison of peripheral imaging technologies for bone and muscle quantification: a review of segmentation techniques. J Clin Densitom 3(1):92\u2013107. https:\/\/doi.org\/10.1016\/j.jocd.2018.04.001","journal-title":"J Clin Densitom"},{"issue":"1","key":"7073_CR18","doi-asserted-by":"publisher","first-page":"7973","DOI":"10.1038\/s41598-019-44416-8","volume":"9","author":"K Weber","year":"2019","unstructured":"Weber K, Smith A, Wasielewski M, Eghtesad K, Upadhyayula P, Wintermark M (2019) Deep learning convolutional neural networks for the automatic quantification of muscle fat infiltration following whiplash injury. Scientific rep 9(1):7973. https:\/\/doi.org\/10.1038\/s41598-019-44416-8","journal-title":"Scientific rep"}],"container-title":["European Spine Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00586-021-07073-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00586-021-07073-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00586-021-07073-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,23]],"date-time":"2022-03-23T07:30:55Z","timestamp":1648020655000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00586-021-07073-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,12,11]]},"references-count":18,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["7073"],"URL":"https:\/\/doi.org\/10.1007\/s00586-021-07073-y","relation":{},"ISSN":["0940-6719","1432-0932"],"issn-type":[{"value":"0940-6719","type":"print"},{"value":"1432-0932","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,11]]},"assertion":[{"value":"12 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 November 2021","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 November 2021","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 December 2021","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"This retrospective study protocol was approved by the ethics committee of the Medical Faculty at the University of Leipzig, Germany (Ethics Committee; 025\/21-ek) and in accordance with the 1964 Helsinki declaration and its later amendments or comparable ethical standards. Written consent was obtained from the participants. All relevant data generated or analyzed during the current study have been presented in the manuscript.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}