{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T22:35:49Z","timestamp":1792794949374,"version":"4.5.0"},"reference-count":32,"publisher":"Ovid Technologies (Wolters Kluwer Health)","issue":"22","license":[{"start":{"date-parts":[[2025,5,30]],"date-time":"2025-05-30T00:00:00Z","timestamp":1748563200000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"the National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No. 62071161"],"award-info":[{"award-number":["No. 62071161"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"the Project of Strategic Support Force Medical Center","award":["No. 21ZX03"],"award-info":[{"award-number":["No. 21ZX03"]}]},{"name":"Scientific Research Fund of Zhejiang Provincial Department of Education","award":["No. Y202351775"],"award-info":[{"award-number":["No. Y202351775"]}],"id":[{"id":"https:\/\/ror.org\/059md9404","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":["lww.com","ovid.com"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,5,30]]},"abstract":"<jats:p>\n                    Accurate vertebrae segmentation is crucial for modern surgical technologies, and deep learning networks provide valuable tools for this task. This study explores the application of advanced deep learning-based methods for segmenting vertebrae in computed tomography (CT) images of adolescent idiopathic scoliosis (AIS) patients. In this study, we collected a dataset of 31 samples from AIS patients, covering a wide range of spinal regions from cervical to lumbar vertebrae. High-resolution CT images were obtained for each sample, forming the basis of our segmentation analysis. We utilized 2 popular neural networks, U-Net and Attention U-Net, to segment the vertebrae in these CT images. Segmentation performance was rigorously evaluated using 2 key metrics: the Dice Coefficient Score to measure overlap between segmented and ground truth regions, and the Hausdorff distance (HD) to assess boundary dissimilarity. Both networks performed well, with U-Net achieving an average Dice coefficient of 92.2 \u00b1 2.4% and an HD of 9.80 \u00b1 1.34\u2009mm. Attention U-Net showed similar results, with a Dice coefficient of 92.3 \u00b1 2.9% and an HD of 8.67 \u00b1 3.38\u2009mm. When applied to the challenging anatomy of AIS, our findings align with literature results from advanced 3D U-Nets on healthy spines. Although no significant overall difference was observed between the 2 networks (\n                    <jats:italic toggle=\"yes\">P<\/jats:italic>\n                    &gt; .05), Attention U-Net exhibited an improved Dice coefficient (91.5 \u00b1 0.0% vs 88.8 \u00b1 0.1%,\n                    <jats:italic toggle=\"yes\">P<\/jats:italic>\n                    = .151) and a significantly better HD (9.04 \u00b1 4.51 vs. 13.60 \u00b1 2.26\u2009mm,\n                    <jats:italic toggle=\"yes\">P<\/jats:italic>\n                    = .027) in critical scoliosis sites (mid-thoracic region), suggesting enhanced suitability for complex anatomy. Our study indicates that U-Net neural networks are feasible and effective for automated vertebrae segmentation in AIS patients using clinical 3D CT images. Attention U-Net demonstrated improved performance in thoracic levels, which are primary sites of scoliosis and may be more suitable for challenging anatomical regions.\n                  <\/jats:p>","DOI":"10.1097\/md.0000000000042644","type":"journal-article","created":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T16:00:59Z","timestamp":1749744059000},"page":"e42644","update-policy":"https:\/\/doi.org\/10.1097\/lww.0000000000001000","source":"Crossref","is-referenced-by-count":2,"title":["Three-dimensional automated segmentation of adolescent idiopathic scoliosis on computed tomography driven by deep learning: A retrospective study"],"prefix":"10.1097","volume":"104","author":[{"given":"Yong","family":"Ji","sequence":"first","affiliation":[{"name":"Department of Spine II, The Ninth Medical Center, Chinese PLA General Hospital, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiajin","family":"Mei","sequence":"additional","affiliation":[{"name":"College of Automation, Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2318-3077","authenticated-orcid":false,"given":"Rong","family":"Tan","sequence":"additional","affiliation":[{"name":"Department of Spine II, The Ninth Medical Center, Chinese PLA General Hospital, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenxin","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Automation, Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuliang","family":"Ma","sequence":"additional","affiliation":[{"name":"College of Automation, Hangzhou Dianzi University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yun","family":"Peng","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of Houston, Houston, TX."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingchun","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Biomedical Engineering, University of Houston, Houston, TX."}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"276","reference":[{"key":"R1-20250612","doi-asserted-by":"crossref","first-page":"909","DOI":"10.1097\/BRS.0000000000004357","article-title":"Robotic spine surgery: past, present, and future.","volume":"47","author":"Perfetti","year":"2022","journal-title":"Spine"},{"key":"R2-20250612","doi-asserted-by":"crossref","first-page":"1617","DOI":"10.1016\/j.spinee.2021.03.018","article-title":"Augmented and virtual reality in spine surgery, current applications and future potentials.","volume":"21","author":"Ghaednia","year":"2021","journal-title":"Spine J"},{"key":"R3-20250612","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1007\/s43390-021-00403-6","article-title":"State of the art review of new technologies in spine deformity surgery\u2013robotics and navigation.","volume":"10","author":"Sielatycki","year":"2022","journal-title":"Spine Deformity"},{"key":"R4-20250612","doi-asserted-by":"crossref","first-page":"147","DOI":"10.3171\/2018.12.SPINE181397","article-title":"Machine learning for automated 3-dimensional segmentation of the spine and suggested placement of pedicle screws based on intraoperative cone-beam computer tomography.","volume":"31","author":"Burstr\u00f6m","year":"2019","journal-title":"J Neurosurg Spine"},{"key":"R5-20250612","doi-asserted-by":"crossref","first-page":"403","DOI":"10.1109\/TMRB.2022.3155288","article-title":"An automatic path planning method of pedicle screw placement based on preoperative CT images.","volume":"4","author":"Qi","year":"2022","journal-title":"IEEE Trans Med Robot Bionics"},{"key":"R6-20250612","doi-asserted-by":"crossref","first-page":"1666","DOI":"10.1016\/j.spinee.2022.05.002","article-title":"Development and validation of an automated planning tool for navigated lumbosacral pedicle screws using a convolutional neural network.","volume":"22","author":"Scherer","year":"2022","journal-title":"Spine J"},{"key":"R7-20250612","doi-asserted-by":"crossref","first-page":"716007","DOI":"10.3389\/frobt.2021.716007","article-title":"The impact of machine learning on 2D\/3D registration for image-guided interventions: a systematic review and perspective.","volume":"8","author":"Unberath","year":"2021","journal-title":"Front Robot AI"},{"key":"R8-20250612","doi-asserted-by":"crossref","first-page":"e2228","DOI":"10.1002\/rcs.2228","article-title":"Deep learning\u2010based X\u2010ray inpainting for improving spinal 2D\u20103D registration.","volume":"17","author":"Esfandiari","year":"2021","journal-title":"Int J Med Robot Comput Assist Surg"},{"key":"R9-20250612","doi-asserted-by":"crossref","first-page":"135004","DOI":"10.1088\/1361-6560\/acd29d","article-title":"SGReg: segmentation guided 3D\/2D rigid registration for orthogonal x-ray and CT images in spine surgery navigation.","volume":"68","author":"Mi","year":"2023","journal-title":"Phys Med Biol"},{"key":"R10-20250612","doi-asserted-by":"crossref","first-page":"2057","DOI":"10.1007\/s00586-022-07176-0","article-title":"Artificial intelligence in spine care: current applications and future utility.","volume":"31","author":"Hornung","year":"2022","journal-title":"Eur Spine J"},{"key":"R11-20250612","doi-asserted-by":"crossref","first-page":"3454","DOI":"10.21037\/qims-21-939","article-title":"Current development and prospects of deep learning in spine image analysis: a literature review.","volume":"12","author":"Qu","year":"2022","journal-title":"Quant Imaging Med Surg"},{"key":"R12-20250612","doi-asserted-by":"crossref","first-page":"82031","DOI":"10.1109\/ACCESS.2021.3086020","article-title":"U-net and its variants for medical image segmentation: a review of theory and applications.","volume":"9","author":"Siddique","year":"2021","journal-title":"IEEE Access"},{"key":"R13-20250612","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-021-01296-1","article-title":"Automatic vertebrae localization and segmentation in CT with a two-stage Dense-U-Net.","volume":"11","author":"Cheng","year":"2021","journal-title":"Sci Rep"},{"key":"R14-20250612","doi-asserted-by":"crossref","first-page":"1823","DOI":"10.1007\/s00586-021-06842-z","article-title":"Adolescent idiopathic scoliosis 3D vertebral morphology, progression and nomenclature: a current concepts review.","volume":"30","author":"Labrom","year":"2021","journal-title":"Eur Spine J"},{"key":"R15-20250612","doi-asserted-by":"crossref","first-page":"1243","DOI":"10.1049\/ipr2.12419","article-title":"Medical image segmentation using deep learning: a survey.","volume":"16","author":"Wang","year":"2022","journal-title":"IET Image Process"},{"key":"R16-20250612","doi-asserted-by":"crossref","first-page":"86811","DOI":"10.1109\/ACCESS.2021.3084949","article-title":"Deep Learning-based automatic segmentation for reconstructing vertebral anatomy of Healthy Adolescents and Patients with Adolescent Idiopathic Scoliosis (AIS) Using MRI Data.","volume":"9","author":"Antico","year":"2021","journal-title":"IEEE Access"},{"key":"R18-20250612","doi-asserted-by":"crossref","first-page":"102166","DOI":"10.1016\/j.media.2021.102166","article-title":"VerSe: A vertebrae labelling and segmentation benchmark for multi-detector CT images.","volume":"73","author":"Sekuboyina","year":"2021","journal-title":"Med Image Anal"},{"key":"R19-20250612","doi-asserted-by":"crossref","first-page":"102235","DOI":"10.1016\/j.compmedimag.2023.102235","article-title":"Vertebrae localization, segmentation and identification using a graph optimization and an anatomic consistency cycle.","volume":"107","author":"Meng","year":"2023","journal-title":"Comput Med Imaging Graph"},{"key":"R20-20250612","doi-asserted-by":"crossref","first-page":"e13996","DOI":"10.1002\/acm2.13996","article-title":"Lumbar spine segmentation method based on deep learning.","volume":"24","author":"Lu","year":"2023","journal-title":"J Appl Clin Med Phys"},{"key":"R22-20250612","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1007\/s00586-022-07502-6","article-title":"Accuracy of computer-assisted pedicle screw placement for adolescent idiopathic scoliosis: a comparison between robotics and navigation.","volume":"32","author":"Akazawa","year":"2023","journal-title":"Eur Spine J"},{"key":"R23-20250612","first-page":"4259471","article-title":"Automatic segmentation of lumbar spine MRI images based on improved attention U-Net.","volume":"2022","author":"Wang","year":"2022","journal-title":"Comput Intell Neurosci"},{"key":"R24-20250612","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s12880-015-0068-x","article-title":"Metrics for evaluating 3D medical image segmentation: analysis, selection, and tool.","volume":"15","author":"Taha","year":"2015","journal-title":"BMC Med Imaging"},{"key":"R25-20250612","doi-asserted-by":"crossref","first-page":"102258","DOI":"10.1016\/j.media.2021.102258","article-title":"Spine-transformers: Vertebra labeling and segmentation in arbitrary field-of-view spine CTs via 3D transformers.","volume":"75","author":"Tao","year":"2022","journal-title":"Med Image Anal"},{"key":"R26-20250612","doi-asserted-by":"crossref","first-page":"106190","DOI":"10.1016\/j.compbiomed.2022.106190","article-title":"A novel 3D lumbar vertebrae location and segmentation method based on the fusion envelope of 2D hybrid visual projection images.","volume":"151","author":"Wu","year":"2022","journal-title":"Comput Biol Med"},{"key":"R27-20250612","doi-asserted-by":"crossref","first-page":"103230","DOI":"10.1016\/j.bspc.2021.103230","article-title":"Deep learning based vertebral body segmentation with extraction of spinal measurements and disorder disease classification.","volume":"71","author":"Masood","year":"2022","journal-title":"Biomed Signal Proc Control"},{"key":"R28-20250612","doi-asserted-by":"crossref","first-page":"101091","DOI":"10.1016\/j.imu.2022.101091","article-title":"Multi-view parallel vertebra segmentation and identification on computed tomography (CT) images.","volume":"34","author":"Dabiri","year":"2022","journal-title":"Inf Med Unlocked"},{"key":"R29-20250612","doi-asserted-by":"crossref","first-page":"e7300","DOI":"10.1002\/cpe.7300","article-title":"Vertebrae localization and spine segmentation on radiographic images for feature\u2010based curvature classification for scoliosis.","volume":"34","author":"Fatima","year":"2022","journal-title":"Concurrency Comput Pract Exp"},{"key":"R30-20250612","doi-asserted-by":"crossref","first-page":"2115","DOI":"10.1007\/s00586-022-07245-4","article-title":"A deep learning framework for vertebral morphometry and Cobb angle measurement with external validation.","volume":"31","author":"Alukaev","year":"2022","journal-title":"Eur Spine J"},{"key":"R31-20250612","doi-asserted-by":"crossref","first-page":"1969","DOI":"10.1007\/s00586-021-07025-6","article-title":"Comparison of manual versus automated measurement of Cobb angle in idiopathic scoliosis based on a deep learning keypoint detection technology.","volume":"31","author":"Sun","year":"2021","journal-title":"Eur Spine J"},{"key":"R32-20250612","doi-asserted-by":"crossref","first-page":"980","DOI":"10.1016\/j.spinee.2021.01.022","article-title":"An algorithm for using deep learning convolutional neural networks with three dimensional depth sensor imaging in scoliosis detection.","volume":"21","author":"Kokabu","year":"2021","journal-title":"Spine J"},{"key":"R33-20250612","first-page":"20750","article-title":"Attention is all you need.","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv Neural Inf Process Syst"},{"key":"R34-20250612","doi-asserted-by":"crossref","first-page":"S199","DOI":"10.1097\/01.BRS.0000092216.16155.33","article-title":"The Lenke classification of adolescent idiopathic scoliosis: how it organizes curve patterns as a template to perform selective fusions of the spine.","volume":"28","author":"Lenke","year":"2003","journal-title":"Spine"}],"container-title":["Medicine"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000042644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,12]],"date-time":"2025-06-12T16:01:04Z","timestamp":1749744064000},"score":1,"resource":{"primary":{"URL":"https:\/\/journals.lww.com\/10.1097\/MD.0000000000042644"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5,30]]},"references-count":32,"journal-issue":{"issue":"22","published-print":{"date-parts":[[2025]]}},"URL":"https:\/\/doi.org\/10.1097\/md.0000000000042644","relation":{},"ISSN":["0025-7974","1536-5964"],"issn-type":[{"value":"0025-7974","type":"print"},{"value":"1536-5964","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,5,30]]}}}