{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,16]],"date-time":"2026-10-16T17:00:55Z","timestamp":1792170055576,"version":"4.4.0"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T00:00:00Z","timestamp":1757116800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T00:00:00Z","timestamp":1757116800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100024990","name":"National Yang Ming Chiao Tung University","doi-asserted-by":"crossref","id":[{"id":"10.13039\/501100024990","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Eur Spine J"],"published-print":{"date-parts":[[2025,11]]},"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Purpose<\/jats:title>\n                    <jats:p>This study aims to address the limitations of radiographic imaging and single-task learning models in adolescent idiopathic scoliosis assessment by developing a noninvasive, radiation-free diagnostic framework.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A multi-task deep learning model was trained using structured back surface data acquired via fringe projection three-dimensional imaging. The model was designed to simultaneously predict the Cobb angle, curve type (thoracic, lumbar, mixed, none), and curve direction (left, right, none) by learning shared morphological features.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The multi-task model achieved a mean absolute error (MAE) of 2.9\u00b0 and a root mean square error (RMSE) of 6.9\u00b0 for Cobb angle prediction, outperforming the single-task baseline (5.4\u00b0 MAE, 12.5\u00b0 RMSE). It showed strong correlation with radiographic measurements (\n                      <jats:italic>R<\/jats:italic>\n                      \u2009=\u20090.96, R\u00b2 = 0.91). For curve classification, it reached 89% sensitivity in lumbar and mixed types, and 80% and 75% sensitivity for right and left directions, respectively, with an 87% positive predictive value for right-sided curves.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>The proposed multi-task learning model demonstrates that jointly learning related clinical tasks allows for the extraction of more robust and clinically meaningful geometric features from surface data. It outperforms traditional single-task approaches in both accuracy and stability. This framework provides a safe, efficient, and non-invasive alternative to X-ray\u2013based scoliosis assessment and has the potential to support real-time screening and long-term monitoring of adolescent idiopathic scoliosis in clinical practice.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00586-025-09340-8","type":"journal-article","created":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T14:35:41Z","timestamp":1757169341000},"page":"5321-5333","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-task learning for classification and prediction of adolescent idiopathic scoliosis based on fringe-projection three-dimensional imaging"],"prefix":"10.1007","volume":"34","author":[{"given":"Chi-Kuang","family":"Feng","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yen-Ju","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quoc-Thinh","family":"Dinh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khac-Tuan","family":"Tran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cheng-Yang","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,6]]},"reference":[{"key":"9340_CR1","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/1748-7161-5-12","volume":"5","author":"P Patias","year":"2010","unstructured":"Patias P, Grivas T, Kaspiris A, Aggouris C, Drakoutos E (2010) A review of the trunk surface metrics used as scoliosis and other deformities evaluation indices. Scoliosis 5:12","journal-title":"Scoliosis"},{"key":"9340_CR2","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-019-46246-0","volume":"9","author":"T Kokabu","year":"2019","unstructured":"Kokabu T, Kawakami N, Uno K, Kotani T, Suzuki T, Abe Y, Maeda K, Inage F, Ito Y, Iwasaki N, Sudo H (2019) Three-dimensional depth sensor imaging to identify adolescent idiopathic scoliosis: a prospective multicenter cohort study. Sci Rep 9:9678","journal-title":"Sci Rep"},{"key":"9340_CR3","doi-asserted-by":"publisher","first-page":"1512","DOI":"10.1056\/NEJMoa1307337","volume":"369","author":"S Weinstein","year":"2013","unstructured":"Weinstein S, Dolan L, Wright J, Dobbs M (2013) Effects of bracing in adolescents with idiopathic scoliosis. N Engl J Med 369:1512\u20131521","journal-title":"N Engl J Med"},{"key":"9340_CR4","doi-asserted-by":"publisher","first-page":"973","DOI":"10.1016\/j.spinee.2013.09.032","volume":"14","author":"A Komeili","year":"2014","unstructured":"Komeili A, Westover L, Parent E, Moreau M, El-Rich M, Adeeb S (2014) Surface topography asymmetry maps categorizing external deformity in scoliosis. Spine J 14:973\u2013983","journal-title":"Spine J"},{"key":"9340_CR5","doi-asserted-by":"publisher","first-page":"834","DOI":"10.1056\/NEJMcp1209063","volume":"368","author":"M Hresko","year":"2013","unstructured":"Hresko M (2013) Idiopathic scoliosis in adolescents. N Engl J Med 368:834\u2013841","journal-title":"N Engl J Med"},{"key":"9340_CR6","doi-asserted-by":"publisher","first-page":"2052","DOI":"10.1097\/00007632-200008150-00009","volume":"25","author":"M Doody","year":"2000","unstructured":"Doody M, Lonstein J, Stovall M, Hacker D, Luckyanov N, Land C (2000) Breast cancer mortality after diagnostic radiography: findings from the U.S. scoliosis cohort study. Spine 25:2052\u20132063","journal-title":"Spine"},{"key":"9340_CR7","doi-asserted-by":"publisher","first-page":"121","DOI":"10.1007\/s00247-006-0191-5","volume":"36","author":"R Kleinerman","year":"2006","unstructured":"Kleinerman R (2006) Cancer risks following diagnostic and therapeutic radiation exposure in children. Pediatr Radiol 36:121\u2013125","journal-title":"Pediatr Radiol"},{"key":"9340_CR8","first-page":"487","volume":"14","author":"A Duke","year":"2022","unstructured":"Duke A, Marchese R, Komatsu D, Barsi J (2022) Radiation in adolescent idiopathic scoliosis management: estimated cumulative pre-operative, intra-operative, and post-operative exposure. Orthop Res Rev 14:487\u2013493","journal-title":"Orthop Res Rev"},{"key":"9340_CR9","doi-asserted-by":"publisher","first-page":"328","DOI":"10.2106\/00004623-199072030-00003","volume":"72","author":"D Carman","year":"1990","unstructured":"Carman D, Browne R, Birch J (1990) Measurement of scoliosis and kyphosis radiographs. Intraobserver and interobserver variation. J Bone Joint Surg Am 72:328\u2013333","journal-title":"J Bone Joint Surg Am"},{"key":"9340_CR10","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1186\/1748-7161-2-18","volume":"2","author":"T Kotwicki","year":"2007","unstructured":"Kotwicki T, Kinel E, Stryla W, Szulc A (2007) Discrepancy in clinical versus radiological parameters describing deformity due to brace treatment for moderate idiopathic scoliosis. Scoliosis 2:18","journal-title":"Scoliosis"},{"key":"9340_CR11","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1097\/01.blo.0000068360.47147.30","volume":"411","author":"G Sapkas","year":"2003","unstructured":"Sapkas G, Papagelopoulos P, Kateros K, Koundis G, Boscainos P, Koukou U, Katonis P (2003) Prediction of cobb angle in idiopathic adolescent scoliosis. Clin Orthop Relat Res 411:32\u201339","journal-title":"Clin Orthop Relat Res"},{"key":"9340_CR12","doi-asserted-by":"publisher","first-page":"796","DOI":"10.1097\/00007632-199804010-00011","volume":"23","author":"P C\u00f4t\u00e9","year":"1998","unstructured":"C\u00f4t\u00e9 P, Kreitz B, Cassidy J, Dzus A, Martel J (1998) A study of the diagnostic accuracy and reliability of the scoliometer and Adam\u2019s forward bend test. Spine 23:796\u2013802","journal-title":"Spine"},{"key":"9340_CR13","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1302\/0301-620X.67B2.3980527","volume":"67","author":"J Daruwalla","year":"1985","unstructured":"Daruwalla J, Balasubramaniam P (1985) Moir\u00e9 topography in scoliosis. Its accuracy in detecting the site and size of the curve. J Bone Joint Surg Br 67:211\u2013213","journal-title":"J Bone Joint Surg Br"},{"key":"9340_CR14","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1001\/jama.2017.11669","volume":"319","author":"J Dunn","year":"2018","unstructured":"Dunn J, Henrikson N, Morrison C, Blasi P, Nguyen M, Lin J (2018) Screening for adolescent idiopathic scoliosis: evidence report and systematic review for the US preventive services task force. JAMA 319:173\u2013187","journal-title":"JAMA"},{"key":"9340_CR15","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-36360-w","volume":"8","author":"H Sudo","year":"2018","unstructured":"Sudo H, Kokabu T, Abe Y, Iwata A, Yamada K, Ito Y, Iwasaki N, Kanai S (2018) Automated noninvasive detection of idiopathic scoliosis in children and adolescents: a principle validation study. Sci Rep 8:17714","journal-title":"Sci Rep"},{"key":"9340_CR16","doi-asserted-by":"publisher","first-page":"980","DOI":"10.1016\/j.spinee.2021.01.022","volume":"21","author":"T Kokabu","year":"2021","unstructured":"Kokabu T, Kanai S, Kawakami N, Uno K, Kotani T, Suzuki T, Tachi H, Abe Y, Iwasaki N, Sudo H (2021) An algorithm for using deep learning convolutional neural networks with three dimensional depth sensor imaging in scoliosis detection. Spine J 21:980\u2013987","journal-title":"Spine J"},{"key":"9340_CR17","doi-asserted-by":"publisher","DOI":"10.1088\/1742-6596\/913\/1\/012004","volume":"913","author":"B Pyakillya","year":"2017","unstructured":"Pyakillya B, Kazachenko N, Mikhailovsky N (2017) An electrochemical microfluidic device for non-enzymatic cholesterol determination using a lab-made disposable electrode. J Phys Conf Ser 913:012004","journal-title":"J Phys Conf Ser"},{"key":"9340_CR18","doi-asserted-by":"publisher","first-page":"196","DOI":"10.1038\/s41524-020-00466-5","volume":"6","author":"L Tiong","year":"2020","unstructured":"Tiong L, Kim J, Han S, Kim D (2020) Identification of crystal symmetry from noisy diffraction patterns by a shape analysis and deep learning. Npj Comput Mater 6:196","journal-title":"Npj Comput Mater"},{"key":"9340_CR19","doi-asserted-by":"publisher","first-page":"330","DOI":"10.1007\/s10489-024-05849-5","volume":"55","author":"X Zhu","year":"2025","unstructured":"Zhu X, Chen R, Guo X, Shao Z, Dai Y, Zhang M, Lang C (2025) Symmetric perception and ordinal regression for detecting scoliosis natural image. Appl Intell 55:330","journal-title":"Appl Intell"},{"key":"9340_CR20","doi-asserted-by":"publisher","first-page":"529","DOI":"10.1007\/s43390-024-01007-6","volume":"13","author":"Y Oquendo","year":"2025","unstructured":"Oquendo Y, Hollyer I, Maschhoff C, Calderon C, DeBaun M, Langner J, Javier N, Bryson X, Richey A, Naz H, Tileston K, Gardner M, Vorhies J (2025) Mobile device-based 3D scanning is superior to scoliometer in assessment of adolescent idiopathic scoliosis. Spine Deform 13:529\u2013537","journal-title":"Spine Deform"},{"key":"9340_CR21","doi-asserted-by":"publisher","first-page":"30","DOI":"10.1093\/nsr\/nwx105","volume":"5","author":"Y Zhang","year":"2018","unstructured":"Zhang Y, Yang Q (2018) An overview of multi-task learning. Natl Sci Rev 5:30\u201343","journal-title":"Natl Sci Rev"},{"key":"9340_CR22","doi-asserted-by":"publisher","first-page":"e25490","DOI":"10.1016\/j.heliyon.2024.e25490","volume":"10","author":"Z Tan","year":"2024","unstructured":"Tan Z, Madzin H, Norafida B, Yang C, Sun W, Nie T, Cai F (2024) Deeppulmotb: a benchmark dataset for multi-task learning of tuberculosis lesions in lung computerized tomography (CT). Heliyon 10:e25490","journal-title":"Heliyon"},{"key":"9340_CR23","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1007\/s11633-022-1339-y","volume":"19","author":"D Wu","year":"2022","unstructured":"Wu D, Liao M, Zhang W, Wang X, Bai X, Cheng W, Liu W (2022) Yolop: you only look once for panoptic driving perception. Mach Intell Res 19:550\u2013562","journal-title":"Mach Intell Res"},{"key":"9340_CR24","doi-asserted-by":"publisher","first-page":"141627","DOI":"10.1109\/ACCESS.2019.2943604","volume":"7","author":"T Gong","year":"2019","unstructured":"Gong T, Lee T, Stephenson C, Renduchintala V, Padhy S, Ndirango A (2019) A comparison of loss weighting strategies for multi task learning in deep neural networks. IEEE Access 7:141627\u2013141632","journal-title":"IEEE Access"},{"key":"9340_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101918","volume":"70","author":"Y Zhou","year":"2021","unstructured":"Zhou Y, Chen H, Li Y, Liu Q, Xu X, Wang S, Yap P, Shen D (2021) Multi-task learning for segmentation and classification of tumors in 3D automated breast ultrasound images. Med Image Anal 70:101918","journal-title":"Med Image Anal"}],"container-title":["European Spine Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00586-025-09340-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00586-025-09340-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00586-025-09340-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,16]],"date-time":"2025-10-16T18:02:16Z","timestamp":1760637736000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00586-025-09340-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,6]]},"references-count":25,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["9340"],"URL":"https:\/\/doi.org\/10.1007\/s00586-025-09340-8","relation":{},"ISSN":["0940-6719","1432-0932"],"issn-type":[{"value":"0940-6719","type":"print"},{"value":"1432-0932","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,6]]},"assertion":[{"value":"15 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 August 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"6 September 2025","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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interests"}}]}}