{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T03:02:03Z","timestamp":1787022123876,"version":"build-2736575974"},"reference-count":50,"publisher":"Public Library of Science (PLoS)","issue":"5","license":[{"start":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T00:00:00Z","timestamp":1684713600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002701","name":"Ministry of Education","doi-asserted-by":"publisher","award":["2021R1A6A3A01088445"],"award-info":[{"award-number":["2021R1A6A3A01088445"]}],"id":[{"id":"10.13039\/501100002701","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:sec id=\"sec001\">\n                    <jats:title>Objective<\/jats:title>\n                    <jats:p>Conventional computer-aided diagnosis using convolutional neural networks (CNN) has limitations in detecting sensitive changes and determining accurate decision boundaries in spectral and structural diseases such as scoliosis. We devised a new method to detect and diagnose adolescent idiopathic scoliosis in chest X-rays (CXRs) employing the latent space\u2019s discriminative ability in the generative adversarial network (GAN) and a simple multi-layer perceptron (MLP) to screen adolescent idiopathic scoliosis CXRs.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec002\">\n                    <jats:title>Materials and methods<\/jats:title>\n                    <jats:p>Our model was trained and validated in a two-step manner. First, we trained a GAN using CXRs with various scoliosis severities and utilized the trained network as a feature extractor using the GAN inversion method. Second, we classified each vector from the latent space using a simple MLP.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec003\">\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>The 2-layer MLP exhibited the best classification in the ablation study. With this model, the area under the receiver operating characteristic (AUROC) curves were 0.850 in the internal and 0.847 in the external datasets. Furthermore, when the sensitivity was fixed at 0.9, the model\u2019s specificity was 0.697 in the internal and 0.646 in the external datasets.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec id=\"sec004\">\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>We developed a classifier for Adolescent idiopathic scoliosis (AIS) through generative representation learning. Our model shows good AUROC under screening chest radiographs in both the internal and external datasets. Our model has learned the spectral severity of AIS, enabling it to generate normal images even when trained solely on scoliosis radiographs.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1371\/journal.pone.0285489","type":"journal-article","created":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T13:24:18Z","timestamp":1684761858000},"page":"e0285489","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":12,"title":["Screening of adolescent idiopathic scoliosis using generative adversarial network (GAN) inversion method in chest radiographs"],"prefix":"10.1371","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0886-6119","authenticated-orcid":true,"given":"Jun Soo","family":"Lee","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5028-5716","authenticated-orcid":true,"given":"Keewon","family":"Shin","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6946-1428","authenticated-orcid":true,"given":"Seung Min","family":"Ryu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-1054-6175","authenticated-orcid":true,"given":"Seong Gyu","family":"Jegal","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5185-8531","authenticated-orcid":true,"given":"Woojin","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min A.","family":"Yoon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gil-Sun","family":"Hong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanghyun","family":"Paik","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3438-2217","authenticated-orcid":true,"given":"Namkug","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2023,5,22]]},"reference":[{"issue":"8934","key":"pone.0285489.ref001","doi-asserted-by":"crossref","first-page":"1407","DOI":"10.1016\/S0140-6736(94)90572-X","article-title":"Adolescent idiopathic scoliosis","volume":"344","author":"JE Lonstein","year":"1994","journal-title":"Lancet"},{"key":"pone.0285489.ref002","doi-asserted-by":"crossref","first-page":"390","DOI":"10.1038\/s42003-019-0635-8","article-title":"Development and validation of deep learning algorithms for scoliosis screening using back images","volume":"2","author":"J Yang","year":"2019","journal-title":"Commun Biol"},{"issue":"1","key":"pone.0285489.ref003","doi-asserted-by":"crossref","first-page":"3","DOI":"10.1007\/s11832-012-0457-4","article-title":"Epidemiology of adolescent idiopathic scoliosis","volume":"7","author":"MR Konieczny","year":"2013","journal-title":"J Child Orthop"},{"issue":"7","key":"pone.0285489.ref004","doi-asserted-by":"crossref","first-page":"1087","DOI":"10.1007\/s00586-011-1695-8","article-title":"Idiopathic scoliosis in Korean schoolchildren: a prospective screening study of over 1 million children","volume":"20","author":"SW Suh","year":"2011","journal-title":"Eur Spine J"},{"issue":"2","key":"pone.0285489.ref005","doi-asserted-by":"crossref","first-page":"402","DOI":"10.1148\/radiology.218.2.r01ja32402","article-title":"Digital radiography of scoliosis with a scanning method: initial evaluation","volume":"218","author":"H Geijer","year":"2001","journal-title":"Radiology"},{"issue":"3","key":"pone.0285489.ref006","doi-asserted-by":"crossref","first-page":"543","DOI":"10.1007\/s00330-002-1476-1","article-title":"Digital radiography of scoliosis with a scanning method: radiation dose optimization","volume":"13","author":"H Geijer","year":"2003","journal-title":"Eur Radiol"},{"issue":"7","key":"pone.0285489.ref007","doi-asserted-by":"crossref","first-page":"517","DOI":"10.1007\/BF00223081","article-title":"Variation in Cobb angle measurements in scoliosis","volume":"23","author":"JE Pruijs","year":"1994","journal-title":"Skeletal Radiol"},{"issue":"6","key":"pone.0285489.ref008","doi-asserted-by":"crossref","first-page":"383","DOI":"10.1097\/BSD.0b013e3181bb9a3c","article-title":"A computer-aided Cobb angle measurement method and its reliability","volume":"23","author":"J Zhang","year":"2010","journal-title":"J Spinal Disord Tech"},{"issue":"1","key":"pone.0285489.ref009","doi-asserted-by":"crossref","first-page":"5494","DOI":"10.1038\/s41598-022-09293-8","article-title":"A union of deep learning and swarm-based optimization for 3D human action recognition","volume":"12","author":"H Basak","year":"2022","journal-title":"Sci Rep"},{"key":"pone.0285489.ref010","article-title":"Automatic measurement algorithm of scoliosis Cobb angle based on deep learning","volume":"1187","author":"YC Tu","year":"2019","journal-title":"J Phys Conf Ser"},{"issue":"2","key":"pone.0285489.ref011","doi-asserted-by":"crossref","DOI":"10.3390\/diagnostics12020396","article-title":"Automated Cobb Angle Measurement for Adolescent Idiopathic Scoliosis Using Convolutional Neural Network","volume":"12","author":"W Caesarendra","year":"2022","journal-title":"Diagnostics"},{"issue":"10","key":"pone.0285489.ref012","doi-asserted-by":"crossref","first-page":"4755","DOI":"10.1007\/s00521-020-05533-y","article-title":"An automated estimator for Cobb angle measurement using multi-task networks","volume":"33","author":"XL Fu","year":"2021","journal-title":"Neural Comput Appl"},{"key":"pone.0285489.ref013","unstructured":"Geirhos R, Rubisch P, Michaelis C, Bethge M, Wichmann FA, Brendel WJapa. ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness. 2018."},{"key":"pone.0285489.ref014","doi-asserted-by":"crossref","unstructured":"Doersch C, Zisserman A, editors. Multi-task self-supervised visual learning. Proceedings of the IEEE International Conference on Computer Vision; 2017.","DOI":"10.1109\/ICCV.2017.226"},{"key":"pone.0285489.ref015","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA, editors. Colorful image colorization. European conference on computer vision; 2016: Springer.","DOI":"10.1007\/978-3-319-46487-9_40"},{"key":"pone.0285489.ref016","doi-asserted-by":"crossref","unstructured":"Noroozi M, Favaro P, editors. Unsupervised learning of visual representations by solving jigsaw puzzles. European conference on computer vision; 2016: Springer.","DOI":"10.1007\/978-3-319-46466-4_5"},{"issue":"7","key":"pone.0285489.ref017","doi-asserted-by":"crossref","first-page":"1527","DOI":"10.1162\/neco.2006.18.7.1527","article-title":"A fast learning algorithm for deep belief nets","volume":"18","author":"GE Hinton","year":"2006","journal-title":"Neural computation"},{"key":"pone.0285489.ref018","unstructured":"Kingma DP, Welling M. Auto-encoding variational bayes. arXiv preprint arXiv:13126114. 2013."},{"key":"pone.0285489.ref019","unstructured":"Goodfellow I, Pouget-Abadie J, Mirza M, Xu B, Warde-Farley D, Ozair S, et al. Generative adversarial nets. Advances in neural information processing systems. 2014;27."},{"key":"pone.0285489.ref020","unstructured":"Arora S, Risteski A, Zhang Y, editors. Do GANs learn the distribution? some theory and empirics. International Conference on Learning Representations; 2018."},{"key":"pone.0285489.ref021","first-page":"2234","article-title":"Improved techniques for training gans","volume":"29","author":"T Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"pone.0285489.ref022","doi-asserted-by":"crossref","first-page":"1566123","DOI":"10.1155\/2023\/1566123","article-title":"Variational Autoencoders-BasedSelf-Learning Model for Tumor Identification and Impact Analysis from 2-D MRI Images","volume":"2023","author":"P Naga Srinivasu","year":"2023","journal-title":"J Healthc Eng"},{"key":"pone.0285489.ref023","doi-asserted-by":"crossref","unstructured":"He KM, Chen XL, Xie SN, Li YH, Dollar P, Girshick R. Masked Autoencoders Are Scalable Vision Learners. Proc Cvpr Ieee. 2022:15979\u201388.","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"pone.0285489.ref024","doi-asserted-by":"crossref","unstructured":"Karras T, Laine S, Aila T, editors. A style-based generator architecture for generative adversarial networks. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2019.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"pone.0285489.ref025","doi-asserted-by":"crossref","unstructured":"Shen Y, Zhou B, editors. Closed-form factorization of latent semantics in gans. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition; 2021.","DOI":"10.1109\/CVPR46437.2021.00158"},{"key":"pone.0285489.ref026","doi-asserted-by":"crossref","unstructured":"Abdal R, Qin Y, Wonka P, editors. Image2stylegan: How to embed images into the stylegan latent space? Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2019.","DOI":"10.1109\/ICCV.2019.00453"},{"issue":"3","key":"pone.0285489.ref027","first-page":"14","article-title":"World Medical Association Declaration of Helsinki: ethical principles for medical research involving human subjects","volume":"81","author":"Association GAotWM","year":"2014","journal-title":"The Journal of the American College of Dentists"},{"issue":"2","key":"pone.0285489.ref028","doi-asserted-by":"crossref","first-page":"165","DOI":"10.1001\/jama.2017.19342","article-title":"Screening for Adolescent Idiopathic Scoliosis: US Preventive Services Task Force Recommendation Statement","volume":"319","author":"Force USPST","year":"2018","journal-title":"JAMA"},{"issue":"3","key":"pone.0285489.ref029","doi-asserted-by":"crossref","first-page":"355","DOI":"10.1016\/S0734-189X(87)80186-X","article-title":"Adaptive histogram equalization and its variations","volume":"39","author":"SM Pizer","year":"1987","journal-title":"Computer vision, graphics, and image processing"},{"key":"pone.0285489.ref030","doi-asserted-by":"crossref","unstructured":"Zuiderveld K. Contrast limited adaptive histogram equalization. Graphics gems. 1994:474\u201385.","DOI":"10.1016\/B978-0-12-336156-1.50061-6"},{"key":"pone.0285489.ref031","unstructured":"Shahbazi M, Danelljan M, Paudel DP, Van Gool L. Collapse by Conditioning: Training Class-conditional GANs with Limited Data. arXiv preprint arXiv:220106578. 2022."},{"key":"pone.0285489.ref032","doi-asserted-by":"crossref","first-page":"10","DOI":"10.1097\/00003086-197306000-00003","article-title":"Classification and terminology of scoliosis","volume":"93","author":"L Goldstein","year":"1973","journal-title":"Clinical Orthopaedics and Related Research\u00ae"},{"issue":"2","key":"pone.0285489.ref033","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1302\/0301-620X.71B2.2925744","article-title":"Curve patterns in idiopathic scoliosis. A clinical and radiographic study","volume":"71","author":"J Cruickshank","year":"1989","journal-title":"The Journal of bone and joint surgery British volume"},{"issue":"5","key":"pone.0285489.ref034","doi-asserted-by":"crossref","first-page":"1451","DOI":"10.1007\/s11263-020-01429-5","article-title":"Semantic hierarchy emerges in deep generative representations for scene synthesis","volume":"129","author":"C Yang","year":"2021","journal-title":"International Journal of Computer Vision"},{"key":"pone.0285489.ref035","unstructured":"Chen T, Kornblith S, Norouzi M, Hinton G, editors. A simple framework for contrastive learning of visual representations. International conference on machine learning; 2020: PMLR."},{"key":"pone.0285489.ref036","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros AA, editors. Split-brain autoencoders: Unsupervised learning by cross-channel prediction. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2017.","DOI":"10.1109\/CVPR.2017.76"},{"key":"pone.0285489.ref037","unstructured":"Nair V, Hinton GE, editors. Rectified linear units improve restricted boltzmann machines. Icml; 2010."},{"key":"pone.0285489.ref038","unstructured":"Ioffe S, Szegedy C, editors. Batch normalization: Accelerating deep network training by reducing internal covariate shift. International conference on machine learning; 2015: PMLR."},{"key":"pone.0285489.ref039","doi-asserted-by":"crossref","unstructured":"Schlegl T, Seeb\u00f6ck P, Waldstein SM, Schmidt-Erfurth U, Langs G, editors. Unsupervised anomaly detection with generative adversarial networks to guide marker discovery. International conference on information processing in medical imaging; 2017: Springer.","DOI":"10.1007\/978-3-319-59050-9_12"},{"key":"pone.0285489.ref040","unstructured":"Karras T, Aittala M, Hellsten J, Laine S, Lehtinen J, Aila T. Training generative adversarial networks with limited data. arXiv preprint arXiv:200606676. 2020."},{"key":"pone.0285489.ref041","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","volume":"32","author":"A Paszke","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"pone.0285489.ref042","unstructured":"Mescheder L, Geiger A, Nowozin S, editors. Which training methods for GANs do actually converge? International conference on machine learning; 2018: PMLR."},{"key":"pone.0285489.ref043","unstructured":"Kingma DP, Ba J. Adam: A method for stochastic optimization. arXiv preprint arXiv:14126980. 2014."},{"key":"pone.0285489.ref044","unstructured":"Heusel M, Ramsauer H, Unterthiner T, Nessler B, Hochreiter S. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems. 2017;30."},{"issue":"4","key":"pone.0285489.ref045","doi-asserted-by":"crossref","first-page":"600","DOI":"10.1109\/TIP.2003.819861","article-title":"Image quality assessment: from error visibility to structural similarity","volume":"13","author":"Z Wang","year":"2004","journal-title":"IEEE transactions on image processing"},{"issue":"3","key":"pone.0285489.ref046","first-page":"193","article-title":"Adolescent Idiopathic Scoliosis: Diagnosis and Management","volume":"89","author":"JP Horne","year":"2014","journal-title":"Am Fam Physician"},{"key":"pone.0285489.ref047","doi-asserted-by":"crossref","unstructured":"Chen X, Xie S, He K, editors. An empirical study of training self-supervised vision transformers. Proceedings of the IEEE\/CVF International Conference on Computer Vision; 2021.","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"pone.0285489.ref048","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"J-B Grill","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"pone.0285489.ref049","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume":"33","author":"T Chen","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"pone.0285489.ref050","unstructured":"Grigoryev T, Voynov A, Babenko A, editors. When, Why, and Which Pretrained GANs Are Useful? International Conference on Learning Representations; 2021."}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0285489","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,5,22]],"date-time":"2023-05-22T13:24:59Z","timestamp":1684761899000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0285489"}},"subtitle":[],"editor":[{"given":"Muhammad Fazal","family":"Ijaz","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,5,22]]},"references-count":50,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,5,22]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0285489","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,22]]}}}