{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T18:52:52Z","timestamp":1792435972718,"version":"4.5.0"},"reference-count":26,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T00:00:00Z","timestamp":1620086400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T00:00:00Z","timestamp":1620086400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>In this work we propose to use Deep Learning to automatically calculate the coordinates of the vertebral corners in sagittal x-rays images of the thoracolumbar spine and, from those landmarks, to calculate relevant radiological parameters such as L1\u2013L5 and L1\u2013S1 lordosis and sacral slope. For this purpose, we used 10,193 images annotated with the landmarks coordinates as the ground truth. We realized a model that consists of 2 steps. In step 1, we trained 2 Convolutional Neural Networks to identify each vertebra in the image and calculate the landmarks coordinates respectively. In step 2, we refined the localization using cropped images of a single vertebra as input to another convolutional neural network and we used geometrical transformations to map the corners to the original image. For the localization tasks, we used a differentiable spatial to numerical transform (DSNT) as the top layer. We evaluated the model both qualitatively and quantitatively on a set of 195 test images. The median localization errors relative to the vertebrae dimensions were 1.98% and 1.68% for x and y coordinates respectively. All the predicted angles were highly correlated with the ground truth, despite non-negligible absolute median errors of 1.84\u00b0, 2.43\u00b0 and 1.98\u00b0 for L1\u2013L5, L1\u2013S1 and SS respectively. Our model is able to calculate with good accuracy the coordinates of the vertebral corners and has a large potential for improving the reliability and repeatability of measurements in clinical tasks.<\/jats:p>","DOI":"10.1038\/s41598-021-89102-w","type":"journal-article","created":{"date-parts":[[2021,5,4]],"date-time":"2021-05-04T06:03:29Z","timestamp":1620108209000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":49,"title":["2-step deep learning model for landmarks localization in spine radiographs"],"prefix":"10.1038","volume":"11","author":[{"given":"Andrea","family":"Cina","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tito","family":"Bassani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matteo","family":"Panico","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Andrea","family":"Luca","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Youssef","family":"Masharawi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Marco","family":"Brayda-Bruno","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fabio","family":"Galbusera","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,5,4]]},"reference":[{"key":"89102_CR1","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.copbio.2019.03.004","volume":"58","author":"D Cirillo","year":"2019","unstructured":"Cirillo, D. & Valencia, A. Big data analytics for personalized medicine. Curr. Opin. Biotechnol. 58, 161\u2013167 (2019).","journal-title":"Curr. Opin. Biotechnol."},{"issue":"Suppl 5","key":"89102_CR2","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1007\/s00586-011-1938-8","volume":"20","author":"JC Le Huec","year":"2011","unstructured":"Le Huec, J. C., Charosky, S., Barrey, C., Rigal, J. & Aunoble, S. Sagittal imbalance cascade for simple degenerative spine and consequences: algorithm of decision for appropriate treatment. Eur. Spine J. 20(Suppl 5), 699\u2013703 (2011).","journal-title":"Eur. Spine J."},{"issue":"3","key":"89102_CR3","doi-asserted-by":"publisher","first-page":"328","DOI":"10.2106\/00004623-199072030-00003","volume":"72","author":"DL Carman","year":"1990","unstructured":"Carman, D. L., Browne, R. H. & Birch, J. G. Measurement of scoliosis and kyphosis radiographs. Intraobserver and interobserver variation. J. Bone Joint Surg. Am. 72(3), 328\u2013333 (1990).","journal-title":"J. Bone Joint Surg. Am."},{"key":"89102_CR4","doi-asserted-by":"crossref","unstructured":"Summers R.M. Deep learning and computer-aided diagnosis for medical image processing: a personal perspective. In\u00a0Deep Learning and Convolutional Neural Networks for Medical Image Computing. Springer, Cham, 3\u201310 (2017).","DOI":"10.1007\/978-3-319-42999-1_1"},{"key":"89102_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.media.2018.05.005","volume":"48","author":"H Wu","year":"2018","unstructured":"Wu, H., Bailey, C., Rasoulinejad, P. & Li, S. Automated comprehensive adolescent idiopathic scoliosis assessment using MVC-Net. Med. Image Anal. 48, 1\u201311 (2018).","journal-title":"Med. Image Anal."},{"key":"89102_CR6","doi-asserted-by":"crossref","unstructured":"Sun H. et al. Direct estimation of spinal cobb angles by structured multi-output regression. In\u00a0International Conference on Information Processing in Medical Imaging. Springer, Cham, 529\u2013540 (2017).","DOI":"10.1007\/978-3-319-59050-9_42"},{"key":"89102_CR7","unstructured":"Levine M. et al. Automatic vertebrae localization in spine CT: a deep-learning approach for image guidance and surgical data science. In\u00a0Medical Imaging 2019: Image-Guided Procedures, Robotic Interventions, and Modeling. International Society for Optics and Photonics, 109510S (2019)."},{"key":"89102_CR8","doi-asserted-by":"crossref","unstructured":"Yang D. et al. Automatic vertebra labeling in large-scale 3D CT using deep image-to-image network with message passing and sparsity regularization. In\u00a0International Conference on Information Processing in Medical Imaging. Springer, Cham, 633\u2013644 (2017).","DOI":"10.1007\/978-3-319-59050-9_50"},{"key":"89102_CR9","doi-asserted-by":"crossref","unstructured":"Jakobsen, I. M. G., & Plocharski, M. Automatic detection of cervical vertebral landmarks for fluoroscopic joint motion analysis. In\u00a0Scandinavian Conference on Image Analysis. Springer, Cham, 209\u2013220 (2019).","DOI":"10.1007\/978-3-030-20205-7_18"},{"key":"89102_CR10","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00586-020-06406-7","volume":"29","author":"R Korez","year":"2020","unstructured":"Korez, R., Putzier, M. & Vrtovec, T. A deep learning tool for fully automated measurements of sagittal spinopelvic balance from X-ray images: performance evaluation. Eur. Spine J. 29, 1\u201311 (2020).","journal-title":"Eur. Spine J."},{"key":"89102_CR11","doi-asserted-by":"crossref","unstructured":"Yi, J., Wu, P., Huang, Q., Qu, H., & Metaxas, D. N. Vertebra-focused landmark detection for scoliosis assessment. In 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI). IEEE, 736\u2013740 (2020).","DOI":"10.1109\/ISBI45749.2020.9098675"},{"issue":"5","key":"89102_CR12","doi-asserted-by":"publisher","first-page":"951","DOI":"10.1007\/s00586-019-05944-z","volume":"28","author":"F Galbusera","year":"2019","unstructured":"Galbusera, F. et al. Fully automated radiological analysis of spinal disorders and deformities: a deep learning approach. Eur. Spine J. 28(5), 951\u2013960 (2019).","journal-title":"Eur. Spine J."},{"issue":"3","key":"89102_CR13","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1118\/1.4940792","volume":"43","author":"S Kadoury","year":"2016","unstructured":"Kadoury, S., Labelle, H. & Parent, S. Postoperative 3D spine reconstruction by navigating partitioning manifolds. Med Phys 43(3), 1045\u20131056 (2016).","journal-title":"Med Phys"},{"issue":"12","key":"89102_CR14","doi-asserted-by":"publisher","first-page":"2796","DOI":"10.1109\/TMI.2019.2914400","volume":"38","author":"B Aubert","year":"2019","unstructured":"Aubert, B., Vazquez, C., Cresson, T., Parent, S. & de Guise, J. A. Toward automated 3D spine reconstruction from biplanar radiographs using CNN for statistical spine model fitting. IEEE Trans. Med. Imag. 38(12), 2796\u20132806 (2019).","journal-title":"IEEE Trans. Med. Imag."},{"issue":"4","key":"89102_CR15","doi-asserted-by":"publisher","first-page":"658","DOI":"10.1007\/s00586-018-5807-6","volume":"28","author":"L Gajny","year":"2019","unstructured":"Gajny, L., Ebrahimi, S., Vergari, C., Angelini, E. & Skalli, W. Quasi-automatic 3D reconstruction of the full spine from low-dose biplanar X-rays based on statistical inferences and image analysis. Eur. Spine J. 28(4), 658\u2013664 (2019).","journal-title":"Eur. Spine J."},{"issue":"2","key":"89102_CR16","doi-asserted-by":"publisher","first-page":"175","DOI":"10.14245\/ns.1836054.027","volume":"15","author":"K Kyr\u00f6l\u00e4","year":"2018","unstructured":"Kyr\u00f6l\u00e4, K. et al. Intra-and interrater reliability of sagittal spinopelvic parameters on full-spine radiographs in adults with symptomatic spinal disorders. Neurospine 15(2), 175 (2018).","journal-title":"Neurospine"},{"issue":"5","key":"89102_CR17","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TMI.2016.2528162","volume":"35","author":"HC Shin","year":"2016","unstructured":"Shin, H. C. et al. Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning. IEEE Trans. Med. Imag. 35(5), 1285\u20131298 (2016).","journal-title":"IEEE Trans. Med. Imag."},{"issue":"2","key":"89102_CR18","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.jcm.2016.02.012","volume":"15","author":"TK Koo","year":"2016","unstructured":"Koo, T. K. & Li, M. Y. A guideline of selecting and reporting intraclass correlation coefficients for reliability research. J. Chiropr. Med. 15(2), 155\u2013163 (2016).","journal-title":"J. Chiropr. Med."},{"key":"89102_CR19","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"89102_CR20","doi-asserted-by":"crossref","unstructured":"Deng J. et al. Imagenet: a large-scale hierarchical image database. In\u00a02009 IEEE Conference on Computer Vision and Pattern Recognition. IEEE, 248\u2013255 (2009).","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"10","key":"89102_CR21","doi-asserted-by":"publisher","first-page":"1345","DOI":"10.1109\/TKDE.2009.191","volume":"22","author":"SJ Pan","year":"2009","unstructured":"Pan, S. J. & Yang, Q. A survey on transfer learning. IEEE Trans. Knowl. Data Eng. 22(10), 1345\u20131359 (2009).","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"89102_CR22","doi-asserted-by":"crossref","unstructured":"Szegedy C. et al. Going deeper with convolutions. In\u00a0Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1\u20139 (2015).","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"89102_CR23","unstructured":"Nibali, A., He, Z., Morgan, S., & Prendergast, L. Numerical coordinate regression with convolutional neural networks.\u00a0Preprint at https:\/\/arxiv.org\/abs\/1801.07372 (2018)."},{"key":"89102_CR24","unstructured":"Paszke A. et al. Pytorch: an imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems. 8026\u20138037 (2019)."},{"key":"89102_CR25","doi-asserted-by":"crossref","unstructured":"Toshev, A., & Szegedy, C. Deeppose: Human pose estimation via deep neural networks. In\u00a0Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 1653\u20131660 (2014).","DOI":"10.1109\/CVPR.2014.214"},{"key":"89102_CR26","doi-asserted-by":"crossref","unstructured":"Wei, S. E., Ramakrishna, V., Kanade, T., & Sheikh, Y. Convolutional pose machines. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 4724\u20134732 (2016).","DOI":"10.1109\/CVPR.2016.511"}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-89102-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-89102-w","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-89102-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,3]],"date-time":"2022-12-03T02:46:54Z","timestamp":1670035614000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-021-89102-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5,4]]},"references-count":26,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["89102"],"URL":"https:\/\/doi.org\/10.1038\/s41598-021-89102-w","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5,4]]},"assertion":[{"value":"27 July 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"20 April 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 May 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"9482"}}