{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T20:38:42Z","timestamp":1790800722854,"version":"4.1.0"},"reference-count":50,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T00:00:00Z","timestamp":1640217600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100004271","name":"Sapienza Universit\u00e0 di Roma","doi-asserted-by":"publisher","award":["RM11916B7FCB6893 - 2019"],"award-info":[{"award-number":["RM11916B7FCB6893 - 2019"]}],"id":[{"id":"10.13039\/501100004271","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004271","name":"Sapienza Universit\u00e0 di Roma","doi-asserted-by":"publisher","award":["RM11916B7FCB6893 - 2019"],"award-info":[{"award-number":["RM11916B7FCB6893 - 2019"]}],"id":[{"id":"10.13039\/501100004271","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>The aim of our study was to classify scoliosis compared to to healthy patients using non-invasive surface acquisition via Video-raster-stereography, without prior knowledge of radiographic data. Data acquisitions were made using Rasterstereography; unsupervised learning was adopted for clustering and supervised learning was used for prediction model Support Vector Machine and Deep Network architectures were compared. A <jats:italic>M<\/jats:italic>-fold cross validation procedure was performed to evaluate the results. The accuracy and balanced accuracy of the best supervised model were close to 85%. Classification rates by class were measured using the confusion matrix, giving a low percentage of unclassified patients. Rasterstereography has turned out to be a good tool to distinguish subject with scoliosis from healthy patients limiting the exposure to unnecessary radiations.<\/jats:p>","DOI":"10.1371\/journal.pone.0261511","type":"journal-article","created":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T18:44:00Z","timestamp":1640285040000},"page":"e0261511","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":24,"title":["Supervised and unsupervised learning to classify scoliosis and healthy subjects based on non-invasive rasterstereography analysis"],"prefix":"10.1371","volume":"16","author":[{"given":"Tommaso","family":"Colombo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Massimiliano","family":"Mangone","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3162-3473","authenticated-orcid":true,"given":"Francesco","family":"Agostini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Bernetti","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Paoloni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Valter","family":"Santilli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9496-6097","authenticated-orcid":true,"given":"Laura","family":"Palagi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2021,12,23]]},"reference":[{"issue":"16","key":"pone.0261511.ref001","doi-asserted-by":"crossref","first-page":"2052","DOI":"10.1097\/00007632-200008150-00009","article-title":"Breast cancer mortality after diagnostic radiography: findings from the US Scoliosis Cohort Study","volume":"25","author":"MM Doody","year":"2000","journal-title":"Spine"},{"issue":"6","key":"pone.0261511.ref002","doi-asserted-by":"crossref","first-page":"481","DOI":"10.1007\/s002340000420","article-title":"Treatment planning in severe scoliosis: the role of MRI","volume":"43","author":"M Freund","year":"2001","journal-title":"Neuroradiology"},{"issue":"1","key":"pone.0261511.ref003","doi-asserted-by":"crossref","first-page":"41","DOI":"10.1016\/j.ejrad.2005.12.003","article-title":"Imaging in scoliosis from the orthopaedic surgeon\u2019s point of view","volume":"58","author":"M Thomsen","year":"2006","journal-title":"European journal of radiology"},{"issue":"7","key":"pone.0261511.ref004","doi-asserted-by":"crossref","first-page":"1261","DOI":"10.1016\/j.spinee.2018.02.013","article-title":"Prevalence and risk factors for neural axis anomalies in idiopathic scoliosis: a systematic review","volume":"18","author":"JL Heemskerk","year":"2018","journal-title":"The Spine Journal"},{"issue":"7","key":"pone.0261511.ref005","doi-asserted-by":"crossref","first-page":"e36755","DOI":"10.1371\/journal.pone.0036755","article-title":"Pelvis morphology, trunk posture and standing imbalance and their relations to the Cobb angle in moderate and severe untreated AIS","volume":"7","author":"G Dalleau","year":"2012","journal-title":"PloS one"},{"issue":"2","key":"pone.0261511.ref006","doi-asserted-by":"crossref","first-page":"e0243736","DOI":"10.1371\/journal.pone.0243736","article-title":"Assessment of adolescent idiopathic scoliosis from body scanner image by finite element simulations","volume":"16","author":"ATD Gr\u00fcnwald","year":"2021","journal-title":"Plos one"},{"issue":"20","key":"pone.0261511.ref007","doi-asserted-by":"crossref","first-page":"1694","DOI":"10.2106\/JBJS.O.00148","article-title":"Defining the \u201cthree-dimensional sagittal plane\u201d in thoracic adolescent idiopathic scoliosis","volume":"97","author":"PO Newton","year":"2015","journal-title":"JBJS"},{"issue":"1","key":"pone.0261511.ref008","doi-asserted-by":"crossref","first-page":"28","DOI":"10.1016\/0268-0033(94)90055-8","article-title":"Back shape measurement using video rasterstereography and three-dimensional reconstruction of spinal shape","volume":"9","author":"B Drerup","year":"1994","journal-title":"Clinical Biomechanics"},{"issue":"2","key":"pone.0261511.ref009","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1016\/j.artmed.2012.07.002","article-title":"Non invasive classification system of scoliosis curve types using least-squares support vector machines","volume":"56","author":"MM Adankon","year":"2012","journal-title":"Artificial Intelligence in Medicine"},{"issue":"1","key":"pone.0261511.ref010","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/S0933-3657(98)00065-7","article-title":"Medical data mining using evolutionary computation","volume":"16","author":"PS Ngan","year":"1999","journal-title":"Artificial Intelligence in Medicine"},{"key":"pone.0261511.ref011","article-title":"Lumbar Disc Herniation Automatic Detection in Magnetic Resonance Imaging Based on Deep Learning","volume":"9","author":"JY Tsai","year":"2021","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"key":"pone.0261511.ref012","doi-asserted-by":"crossref","first-page":"63","DOI":"10.1016\/j.media.2017.07.002","article-title":"SpineNet: automated classification and evidence visualization in spinal MRIs","volume":"41","author":"A Jamaludin","year":"2017","journal-title":"Medical image analysis"},{"issue":"1","key":"pone.0261511.ref013","doi-asserted-by":"crossref","DOI":"10.21037\/atm-20-5495","article-title":"A narrative review of machine learning as promising revolution in clinical practice of scoliosis","volume":"9","author":"K Chen","year":"2021","journal-title":"Annals of Translational Medicine"},{"issue":"5","key":"pone.0261511.ref014","doi-asserted-by":"crossref","first-page":"496","DOI":"10.1115\/1.1503375","article-title":"Genetic Algorithm\u2013Neural Network Estimation of Cobb Angle from Torso Asymmetry in Scoliosis","volume":"124","author":"JL Jaremko","year":"2002","journal-title":"J Biomech Eng"},{"issue":"1","key":"pone.0261511.ref015","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1109\/TITB.2005.855526","article-title":"A support vector machines classifier to assess the severity of idiopathic scoliosis from surface topography","volume":"10","author":"L Ramirez","year":"2006","journal-title":"Ieee transactions on information technology in biomedicine"},{"issue":"8","key":"pone.0261511.ref016","doi-asserted-by":"crossref","first-page":"2112","DOI":"10.1007\/s00586-016-4833-5","article-title":"Three-dimensional reconstruction using stereoradiography for evaluating adult spinal deformity: a reproducibility study","volume":"26","author":"E Ferrero","year":"2017","journal-title":"European Spine Journal"},{"key":"pone.0261511.ref017","doi-asserted-by":"crossref","DOI":"10.1155\/2014\/315041","article-title":"Formetric 4D rasterstereography","volume":"2014","author":"J Padulo","year":"2014","journal-title":"BioMed research international"},{"issue":"1_suppl","key":"pone.0261511.ref018","doi-asserted-by":"crossref","first-page":"s","DOI":"10.1055\/s-0036-1583055","article-title":"Comparison of the DIERS Formetric 4D Scanner and Plain Radiographs in Terms of Accuracy in Idiopathic Scoliosis Patients","volume":"6","author":"V Kumar","year":"2016","journal-title":"Global Spine Journal"},{"key":"pone.0261511.ref019","first-page":"95:674","article-title":"Ambulante orthopadische Behandlung der Scheuermannschen Krankheit im floriden Stadium","author":"P Stagnara","year":"1965","journal-title":"Schweizmed Wschr"},{"key":"pone.0261511.ref020","first-page":"585","article-title":"Traitement orthopaedique ambulatoire de la maladie de Scheuermann en periode devolution","volume":"52","author":"P Stagnara","year":"1966","journal-title":"Rev chir orthop"},{"issue":"17","key":"pone.0261511.ref021","first-page":"1","article-title":"Imbalanced-learn: A python toolbox to tackle the curse of imbalanced datasets in machine learning","volume":"18","author":"G Lema\u00eetre","year":"2017","journal-title":"Journal of Machine Learning Research"},{"issue":"1","key":"pone.0261511.ref022","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1016\/j.compeleceng.2013.11.024","article-title":"A survey on feature selection methods","volume":"40","author":"G Chandrashekar","year":"2014","journal-title":"Computers & Electrical Engineering"},{"key":"pone.0261511.ref023","first-page":"1","article-title":"Global optimization issues in deep network regression: an overview","author":"L Palagi","year":"2018","journal-title":"Journal of Global Optimization"},{"issue":"3","key":"pone.0261511.ref024","doi-asserted-by":"crossref","first-page":"264","DOI":"10.1145\/331499.331504","article-title":"Data clustering: a review","volume":"31","author":"AK Jain","year":"1999","journal-title":"ACM computing surveys (CSUR)"},{"issue":"8","key":"pone.0261511.ref025","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1016\/j.patrec.2009.09.011","article-title":"Data clustering: 50 years beyond K-means","volume":"31","author":"AK Jain","year":"2010","journal-title":"Pattern Recognition Letters"},{"key":"pone.0261511.ref026","first-page":"1027","volume-title":"Proceedings of the eighteenth annual ACM-SIAM symposium on Discrete algorithms","author":"D Arthur","year":"2007"},{"key":"pone.0261511.ref027","volume-title":"Statistical Learning Theory","author":"VN Vapnik","year":"1998"},{"issue":"3","key":"pone.0261511.ref028","first-page":"27","article-title":"LIBSVM: a library for support vector machines","volume":"2","author":"CC Chang","year":"2011","journal-title":"ACM transactions on intelligent systems and technology (TIST)"},{"key":"pone.0261511.ref029","article-title":"Nonlinear Optimization and Support Vector Machines","author":"V Piccialli","year":"2018","journal-title":"4OR"},{"key":"pone.0261511.ref030","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016"},{"key":"pone.0261511.ref031","doi-asserted-by":"crossref","first-page":"515","DOI":"10.1007\/978-3-319-24553-9_63","volume-title":"Medical Image Computing and Computer-Assisted Intervention\u2014MICCAI 2015","author":"H Chen","year":"2015"},{"key":"pone.0261511.ref032","author":"B Gaonkar","year":"2016","journal-title":"Deep learning in the small sample size setting: cascaded feed forward neural networks for medical image segmentation"},{"key":"pone.0261511.ref033","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"F Pedregosa","year":"2011","journal-title":"the Journal of machine Learning research"},{"key":"pone.0261511.ref034","first-page":"49","article-title":"1-norm support vector machines","author":"J Zhu","year":"2004","journal-title":"Advances in neural information processing systems"},{"issue":"6","key":"pone.0261511.ref035","doi-asserted-by":"crossref","first-page":"066138","DOI":"10.1103\/PhysRevE.69.066138","article-title":"Estimating mutual information","volume":"69","author":"A Kraskov","year":"2004","journal-title":"Physical review E"},{"issue":"2","key":"pone.0261511.ref036","doi-asserted-by":"crossref","first-page":"e87357","DOI":"10.1371\/journal.pone.0087357","article-title":"Mutual information between discrete and continuous data sets","volume":"9","author":"BC Ross","year":"2014","journal-title":"PloS one"},{"key":"pone.0261511.ref037","doi-asserted-by":"crossref","DOI":"10.4135\/9781412983327","volume-title":"Analysis of variance","author":"GR Iversen","year":"1987"},{"key":"pone.0261511.ref038","article-title":"Adam: Amethod for stochastic optimization","author":"DP Kingma","year":"2014","journal-title":"Proc. 3rd Int. Conf. Learn. Representations"},{"key":"pone.0261511.ref039","unstructured":"Chollet F, et al. Keras; 2015. https:\/\/keras.io."},{"key":"pone.0261511.ref040","first-page":"265","article-title":"TensorFlow: A System for Large-Scale Machine Learning","volume":"16","author":"M Abadi","year":"2016","journal-title":"OSDI"},{"issue":"5","key":"pone.0261511.ref041","first-page":"646","article-title":"Idiopathic scoliosis","volume":"24","author":"O Yaman","year":"2014","journal-title":"Turkish neurosurgery"},{"key":"pone.0261511.ref042","first-page":"261","article-title":"Outline for the study of scoliosis","volume":"5","author":"JR Cobb","year":"1948","journal-title":"Instr Course Lect AAOS"},{"issue":"11","key":"pone.0261511.ref043","doi-asserted-by":"crossref","first-page":"780","DOI":"10.1097\/BRS.0000000000002423","article-title":"Prevalence, Risk Factors, and Characteristics of the \u201cadding-on\u201d Phenomenon in Idiopathic Scoliosis After Correction Surgery: A Systematic Review and Meta-analysis","volume":"43","author":"M Yang","year":"2018","journal-title":"Spine"},{"issue":"8","key":"pone.0261511.ref044","doi-asserted-by":"crossref","first-page":"753","DOI":"10.1016\/0021-9290(91)90339-O","article-title":"Analysis of the interaction between vertebral lateral deviation and axial rotation in scoliosis","volume":"24","author":"IA Stokes","year":"1991","journal-title":"Journal of biomechanics"},{"issue":"11","key":"pone.0261511.ref045","doi-asserted-by":"crossref","first-page":"e54","DOI":"10.2106\/JBJS.16.01324","article-title":"Thoracic idiopathic scoliosis severity is highly correlated with 3D measures of thoracic kyphosis","volume":"99","author":"TB Sullivan","year":"2017","journal-title":"JBJS"},{"issue":"9","key":"pone.0261511.ref046","doi-asserted-by":"crossref","first-page":"1330","DOI":"10.2106\/00004623-199609000-00006","article-title":"Late-Onset Idiopathic Scoliosis in Children Six to Fourteen Years Old.: A Cross-Sectional Prevalence Study","volume":"78","author":"AJ Stirling","year":"1996","journal-title":"JBJS"},{"issue":"2","key":"pone.0261511.ref047","doi-asserted-by":"crossref","first-page":"99","DOI":"10.1007\/s005860050038","article-title":"Pelvic incidence: a fundamental pelvic parameter for three-dimensional regulation of spinal sagittal curves","volume":"7","author":"J Legaye","year":"1998","journal-title":"European Spine Journal"},{"issue":"32","key":"pone.0261511.ref048","article-title":"Effect of patient position on the lordosis and scoliosis of patients with degenerative lumbar scoliosis","volume":"96","author":"H Fei","year":"2017","journal-title":"Medicine"},{"issue":"5","key":"pone.0261511.ref049","first-page":"447","article-title":"Radiographic analysis of sagittal spino-pelvic alignment in asymptomatic Chinese adults","author":"Ws Li","year":"2013","journal-title":"Chinese Journal of Orthopaedics"},{"key":"pone.0261511.ref050","first-page":"264","article-title":"How to measure kyphosis in everyday clinical practice: a reliability study on different methods","volume":"176","author":"F Zaina","year":"2012","journal-title":"Studies in health technology and informatics"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0261511","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,23]],"date-time":"2021-12-23T18:44:45Z","timestamp":1640285085000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0261511"}},"subtitle":[],"editor":[{"given":"Yih-Kuen","family":"Jan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2021,12,23]]},"references-count":50,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2021,12,23]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0261511","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,12,23]]}}}