{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T05:45:37Z","timestamp":1783489537359,"version":"3.55.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T00:00:00Z","timestamp":1711324800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T00:00:00Z","timestamp":1711324800000},"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":["J Orthop Surg Res"],"abstract":"Abstract<\/jats:title>\n Purpose:<\/jats:title>\n An efficient physics-informed deep learning approach for extracting spinopelvic measures from X-ray images is introduced and its performance is evaluated against manual annotations.<\/jats:p>\n <\/jats:sec>\n Methods:<\/jats:title>\n Two datasets, comprising a total of 1470 images, were collected to evaluate the model\u2019s performance. We propose a novel method of detecting landmarks as objects, incorporating their relationships as constraints (LanDet<\/jats:italic><\/jats:bold>). Using this approach, we trained our deep learning model to extract five spine and pelvis measures: Sacrum Slope (SS), Pelvic Tilt (PT), Pelvic Incidence (PI), Lumbar Lordosis (LL), and Sagittal Vertical Axis (SVA). The results were compared to manually labelled test dataset (GT) as well as measures annotated separately by three surgeons.<\/jats:p>\n <\/jats:sec>\n Results:<\/jats:title>\n The LanDet<\/jats:italic><\/jats:bold> model was evaluated on the two datasets separately and on an extended dataset combining both. The final accuracy for each measure is reported in terms of Mean Absolute Error (MAE), Standard Deviation (SD), and R Pearson correlation coefficient as follows: $$[SS^\\circ : 3.7 (2.7), R = 0.89]$$<\/jats:tex-math>\n \n [<\/mml:mo>\n S<\/mml:mi>\n \n S<\/mml:mi>\n \u2218<\/mml:mo>\n <\/mml:msup>\n :<\/mml:mo>\n 3.7<\/mml:mn>\n \n (<\/mml:mo>\n 2.7<\/mml:mn>\n )<\/mml:mo>\n <\/mml:mrow>\n ,<\/mml:mo>\n R<\/mml:mi>\n =<\/mml:mo>\n 0.89<\/mml:mn>\n ]<\/mml:mo>\n <\/mml:mrow>\n <\/mml:math><\/jats:alternatives><\/jats:inline-formula>, $$[PT^\\circ : 1.3 (1.1), R = 0.98], [PI^\\circ : 4.2 (3.1), R = 0.93], [LL^\\circ : 5.1 (6.4), R=0.83], [SVA(mm): 2.1 (1.9), R = 0.96]$$<\/jats:tex-math>\n \n \n [<\/mml:mo>\n P<\/mml:mi>\n \n T<\/mml:mi>\n \u2218<\/mml:mo>\n <\/mml:msup>\n :<\/mml:mo>\n 1.3<\/mml:mn>\n \n (<\/mml:mo>\n 1.1<\/mml:mn>\n )<\/mml:mo>\n <\/mml:mrow>\n ,<\/mml:mo>\n R<\/mml:mi>\n =<\/mml:mo>\n 0.98<\/mml:mn>\n ]<\/mml:mo>\n <\/mml:mrow>\n ,<\/mml:mo>\n \n [<\/mml:mo>\n P<\/mml:mi>\n \n I<\/mml:mi>\n \u2218<\/mml:mo>\n <\/mml:msup>\n :<\/mml:mo>\n 4.2<\/mml:mn>\n \n (<\/mml:mo>\n 3.1<\/mml:mn>\n )<\/mml:mo>\n <\/mml:mrow>\n ,<\/mml:mo>\n R<\/mml:mi>\n =<\/mml:mo>\n 0.93<\/mml:mn>\n ]<\/mml:mo>\n <\/mml:mrow>\n ,<\/mml:mo>\n \n [<\/mml:mo>\n L<\/mml:mi>\n \n L<\/mml:mi>\n \u2218<\/mml:mo>\n <\/mml:msup>\n :<\/mml:mo>\n 5.1<\/mml:mn>\n \n (<\/mml:mo>\n 6.4<\/mml:mn>\n )<\/mml:mo>\n <\/mml:mrow>\n ,<\/mml:mo>\n R<\/mml:mi>\n =<\/mml:mo>\n 0.83<\/mml:mn>\n ]<\/mml:mo>\n <\/mml:mrow>\n ,<\/mml:mo>\n \n [<\/mml:mo>\n S<\/mml:mi>\n V<\/mml:mi>\n A<\/mml:mi>\n \n (<\/mml:mo>\n m<\/mml:mi>\n m<\/mml:mi>\n )<\/mml:mo>\n <\/mml:mrow>\n :<\/mml:mo>\n 2.1<\/mml:mn>\n \n (<\/mml:mo>\n 1.9<\/mml:mn>\n )<\/mml:mo>\n <\/mml:mrow>\n ,<\/mml:mo>\n R<\/mml:mi>\n =<\/mml:mo>\n 0.96<\/mml:mn>\n ]<\/mml:mo>\n <\/mml:mrow>\n <\/mml:mrow>\n <\/mml:math><\/jats:alternatives><\/jats:inline-formula>. To assess model reliability and compare it against surgeons, the intraclass correlation coefficient (ICC) metric is used. The model demonstrated better consistency with surgeons with all values over 0.88 compared to what was previously reported in the literature.<\/jats:p>\n <\/jats:sec>\n Conclusion:<\/jats:title>\n The LanDet<\/jats:italic><\/jats:bold> model exhibits competitive performance compared to existing literature. The effectiveness of the physics-informed constraint method, utilized in our landmark detection as object algorithm, is highlighted. Furthermore, we addressed the limitations of heatmap-based methods for anatomical landmark detection and tackled issues related to mis-identifying of similar or adjacent landmarks instead of intended landmark using this novel approach.<\/jats:p>\n <\/jats:sec>","DOI":"10.1186\/s13018-024-04654-7","type":"journal-article","created":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T11:02:10Z","timestamp":1711364530000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["Landet: an efficient physics-informed deep learning approach for automatic detection of anatomical landmarks and measurement of spinopelvic alignment"],"prefix":"10.1186","volume":"19","author":[{"given":"AliAsghar","family":"MohammadiNasrabadi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gemah","family":"Moammer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ahmed","family":"Quateen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kunal","family":"Bhanot","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"John","family":"McPhee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,3,25]]},"reference":[{"key":"4654_CR1","doi-asserted-by":"publisher","first-page":"2031","DOI":"10.1007\/s00586-022-07155-5","volume":"31","author":"T Vrtovec","year":"2022","unstructured":"Vrtovec T, Ibragimov B. Spinopelvic measurements of sagittal balance with deep learning: systematic review and critical evaluation. Eur Spine J. 2022;31:2031\u201345.","journal-title":"Eur Spine J"},{"key":"4654_CR2","doi-asserted-by":"publisher","first-page":"593","DOI":"10.1007\/s00586-009-0913-0","volume":"18","author":"T Vrtovec","year":"2009","unstructured":"Vrtovec T, Pernu\u0161 F, Likar B. A review of methods for quantitative evaluation of spinal curvature. Eur Spine J. 2009;18:593\u2013607.","journal-title":"Eur Spine J"},{"key":"4654_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1002\/rcs.2122","volume":"16","author":"G Amirkhani","year":"2020","unstructured":"Amirkhani G, Farahmand F, Yazdian SM, Mirbagheri A. An extended algorithm for autonomous grasping of soft tissues during robotic surgery. Int J Med Robot Comput Assist Surg. 2020;16:1\u201315.","journal-title":"Int J Med Robot Comput Assist Surg"},{"key":"4654_CR4","doi-asserted-by":"publisher","first-page":"1202","DOI":"10.1016\/j.spinee.2017.03.016","volume":"17","author":"TP Schl\u00f6sser","year":"2017","unstructured":"Schl\u00f6sser TP, et al. The odyssey of sagittal pelvic morphology during human evolution: a perspective on different hominoidae. Spine J. 2017;17:1202\u20136.","journal-title":"Spine J"},{"key":"4654_CR5","doi-asserted-by":"publisher","first-page":"2295","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. 2020;29:2295\u2013305.","journal-title":"Eur Spine J"},{"key":"4654_CR6","doi-asserted-by":"publisher","first-page":"E640","DOI":"10.1097\/BRS.0000000000000904","volume":"40","author":"K Yamada","year":"2015","unstructured":"Yamada K, et al. Accuracies in measuring spinopelvic parameters in full-spine lateral standing radiograph. Spine. 2015;40:E640\u20136.","journal-title":"Spine"},{"key":"4654_CR7","doi-asserted-by":"publisher","first-page":"e1044","DOI":"10.1002\/jsp2.1044","volume":"2","author":"F Galbusera","year":"2019","unstructured":"Galbusera F, Casaroli G, Bassani T. Artificial intelligence and machine learning in spine research. JOR Spine. 2019;2:e1044.","journal-title":"JOR Spine"},{"key":"4654_CR8","unstructured":"Mohammadi Nasrabadi A, McNally W, Moammer G, McPhee J. Automatic extraction of spinopelvic parameters using deep learning to detect landmarks as objects. Med Imaging Deep Learn. 2022."},{"key":"4654_CR9","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. 2018;48:1\u201311.","journal-title":"Med Image Anal"},{"key":"4654_CR10","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. 2019;28:951\u201360.","journal-title":"Eur Spine J"},{"key":"4654_CR11","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s00586-019-06264-y","volume":"29","author":"T Zhang","year":"2020","unstructured":"Zhang T, et al. A novel tool to provide predictable alignment data irrespective of source and image quality acquired on mobile phones: what engineers can offer clinicians. Eur Spine J. 2020;29:387\u201395.","journal-title":"Eur Spine J"},{"key":"4654_CR12","doi-asserted-by":"publisher","first-page":"1896","DOI":"10.1002\/jor.25213","volume":"40","author":"C Iriondo","year":"2022","unstructured":"Iriondo C, et al. Institution-wide shape analysis of 3d spinal curvature and global alignment parameters. J Orthop Res. 2022;40:1896\u2013908.","journal-title":"J Orthop Res"},{"key":"4654_CR13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-021-87141-x","volume":"11","author":"Y-C Yeh","year":"2021","unstructured":"Yeh Y-C, et al. Deep learning approach for automatic landmark detection and alignment analysis in whole-spine lateral radiographs. Sci Rep. 2021;11:1\u201315.","journal-title":"Sci Rep"},{"key":"4654_CR14","doi-asserted-by":"publisher","first-page":"1826","DOI":"10.3390\/jcm8111826","volume":"8","author":"C-H Weng","year":"2019","unstructured":"Weng C-H, et al. Artificial intelligence for automatic measurement of sagittal vertical axis using resunet framework. J Clin Med. 2019;8:1826.","journal-title":"J Clin Med"},{"key":"4654_CR15","doi-asserted-by":"publisher","first-page":"110071","DOI":"10.1016\/j.ejrad.2021.110071","volume":"146","author":"S Zhou","year":"2022","unstructured":"Zhou S, et al. Artificial intelligence x-ray measurement technology of anatomical parameters related to lumbosacral stability. Eur J Radiol. 2022;146:110071.","journal-title":"Eur J Radiol"},{"key":"4654_CR16","doi-asserted-by":"publisher","first-page":"451","DOI":"10.1007\/BF02368136","volume":"20","author":"G Duval-Beaupere","year":"1992","unstructured":"Duval-Beaupere G, Schmidt C, Cosson P. A barycentremetric study of the sagittal shape of spine and pelvis: the conditions required for an economic standing position. Ann Biomed Eng. 1992;20:451\u201362.","journal-title":"Ann Biomed Eng"},{"key":"4654_CR17","doi-asserted-by":"publisher","first-page":"616","DOI":"10.1007\/s00586-014-3558-6","volume":"23","author":"D Garbossa","year":"2014","unstructured":"Garbossa D, et al. Pelvic parameters and global spine balance for spine degenerative disease: the importance of containing for the well being of content. Eur Spine J. 2014;23:616\u201327.","journal-title":"Eur Spine J"},{"key":"4654_CR18","doi-asserted-by":"publisher","first-page":"4","DOI":"10.5371\/hp.2019.31.1.4","volume":"31","author":"SH Lee","year":"2019","unstructured":"Lee SH, Lim CW, Choi KY, Jo S. Effect of spine-pelvis relationship in total hip arthroplasty. Hip Pelvis. 2019;31:4\u201310.","journal-title":"Hip Pelvis"},{"key":"4654_CR19","doi-asserted-by":"crossref","unstructured":"McNally W, Vats K, Wong A, McPhee, J. Rethinking keypoint representations: Modeling keypoints and poses as objects for multi-person human pose estimation. arXiv preprintarXiv:2111.08557 (2021).","DOI":"10.1007\/978-3-031-20068-7_3"},{"key":"4654_CR20","doi-asserted-by":"crossref","unstructured":"Redmon J, Divvala S, Girshick R, Farhadi A. You only look once: Unified, real-time object detection. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition; 2016. p. 779\u2013788.","DOI":"10.1109\/CVPR.2016.91"},{"key":"4654_CR21","doi-asserted-by":"crossref","unstructured":"Wang C-Y. et\u00a0al. Cspnet: A new backbone that can enhance learning capability of cnn. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops; 2020. p. 390\u2013391.","DOI":"10.1109\/CVPRW50498.2020.00203"},{"key":"4654_CR22","unstructured":"Jocher G. et\u00a0al. ultralytics\/yolov5: v5. 0-yolov5-p6 1280 models, aws, supervise. ly and youtube integrations. Zenodo (2021)."},{"key":"4654_CR23","doi-asserted-by":"crossref","unstructured":"Wang C-Y, Bochkovskiy A, Liao H-Y\u00a0M. Scaled-yolov4: Scaling cross stage partial network. In: Proceedings of the IEEE\/cvf Conference on Computer Vision and Pattern Recognition; 2021. p. 13029\u201313038.","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"4654_CR24","first-page":"12993","volume":"34","author":"Z Zheng","year":"2020","unstructured":"Zheng Z, et al. Distance-iou loss: faster and better learning for bounding box regression. Proc AAAI Conf Artif Intell. 2020;34:12993\u20133000.","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"4654_CR25","doi-asserted-by":"publisher","first-page":"e0219854","DOI":"10.1371\/journal.pone.0219854","volume":"14","author":"D Liljequist","year":"2019","unstructured":"Liljequist D, Elfving B, Skavberg Roaldsen K. Intraclass correlation-a discussion and demonstration of basic features. PLoS ONE. 2019;14:e0219854.","journal-title":"PLoS ONE"},{"key":"4654_CR26","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1007\/s10278-021-00533-3","volume":"35","author":"TP Nguyen","year":"2022","unstructured":"Nguyen TP, Jung JW, Yoo YJ, Choi SH, Yoon J. Intelligent evaluation of global spinal alignment by a decentralized convolutional neural network. J Digit Imaging. 2022;35:213\u201325.","journal-title":"J Digit Imaging"},{"key":"4654_CR27","doi-asserted-by":"publisher","first-page":"E253","DOI":"10.1097\/BRS.0000000000000720","volume":"40","author":"A Vila-Casademunt","year":"2015","unstructured":"Vila-Casademunt A, et al. The reliability of sagittal pelvic parameters: the effect of lumbosacral instrumentation and measurement experience. Spine. 2015;40:E253\u20138.","journal-title":"Spine"}],"container-title":["Journal of Orthopaedic Surgery and Research"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13018-024-04654-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s13018-024-04654-7\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s13018-024-04654-7.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,25]],"date-time":"2024-03-25T11:06:17Z","timestamp":1711364777000},"score":1,"resource":{"primary":{"URL":"https:\/\/josr-online.biomedcentral.com\/articles\/10.1186\/s13018-024-04654-7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,3,25]]},"references-count":27,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["4654"],"URL":"https:\/\/doi.org\/10.1186\/s13018-024-04654-7","relation":{},"ISSN":["1749-799X"],"issn-type":[{"value":"1749-799X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,3,25]]},"assertion":[{"value":"23 October 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 March 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 March 2024","order":3,"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, financial or personal, that could influence the results or interpretation of this research.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"This study involving human subjects received approval from the University of Waterloo and THREB Ethical Review Boards. The research was conducted in accordance with the\u201d\u201d.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to partcipate"}}],"article-number":"199"}}