{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,24]],"date-time":"2025-09-24T00:14:41Z","timestamp":1758672881890,"version":"3.44.0"},"reference-count":37,"publisher":"IOP Publishing","issue":"5","license":[{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/publishingsupport.iopscience.iop.org\/iop-standard\/v1"},{"start":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T00:00:00Z","timestamp":1758585600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/iopscience.iop.org\/info\/page\/text-and-data-mining"}],"funder":[{"name":"National Key Research and Development Program of China","award":["NO. 2023YFC2411300"],"award-info":[{"award-number":["NO. 2023YFC2411300"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["NO. 52035012"],"award-info":[{"award-number":["NO. 52035012"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Health Commission of Chengdu Medical Program","award":["NO. 2024108"],"award-info":[{"award-number":["NO. 2024108"]}]},{"name":"Health Commission of Sichuan Province Medical Science and Technology Program","award":["NO. 24CXTD20"],"award-info":[{"award-number":["NO. 24CXTD20"]}]}],"content-domain":{"domain":["iopscience.iop.org"],"crossmark-restriction":false},"short-container-title":["Biomed. Phys. Eng. Express"],"published-print":{"date-parts":[[2025,9,30]]},"abstract":"<jats:title>Abstract<\/jats:title>\n               <jats:p>Total hip arthroplasty (THA) is the primary treatment for end-stage hip osteoarthritis, with successful outcomes depending on precise preoperative planning that requires accurate segmentation and reconstruction of periarticular bone of the hip joint. However, patients with hip osteoarthritis typically exhibit pathological characteristics, including joint space narrowing, femoroacetabular impingement, osteophyte formation. These changes present significant challenges for traditional manual or semi-automatic segmentation methods. To address these challenges, this study proposed a novel 3D UNet-based multi-task network to achieve rapid and accurate segmentation and reconstruction of the periarticular bone in hip osteoarthritis patients. The bone segmentation main network incorporated the Transformer module during the encoder to effectively capture spatial anatomical features, while a boundary-optimization branch was designed to address segmentation challenges at the acetabular-femoral interface. These branches were jointly optimized through a multi-task loss function, with an oversampling strategy introduced to enhance the network\u2019s feature learning capability for complex structures. The experimental results showed that the proposed method achieved excellent performance on the test set with hip osteoarthritis. The average Dice coefficient was 0.945 (0.96 for femur, 0.93 for hip), with an overall precision of 0.95 and recall of 0.97. In terms of the boundary matching metrics, the average surface distance (ASD) and the 95% Hausdorff distance (HD95) were 0.58 mm and 3.55 mm, respectively. The metrics showed that the proposed automatic segmentation network achieved high accuracy in segmenting the periarticular bone of the hip joint, generating reliable 2D masks and 3D models, thereby demonstrating significant potential for supporting THA surgical planning.<\/jats:p>","DOI":"10.1088\/2057-1976\/ae0593","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T22:47:37Z","timestamp":1757544457000},"page":"055042","update-policy":"https:\/\/doi.org\/10.1088\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["A 3D multi-task network for the automatic segmentation of CT images featuring hip osteoarthritis"],"prefix":"10.1088","volume":"11","author":[{"given":"Hongjie","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4608-5401","authenticated-orcid":true,"given":"Xiaogang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shihong","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolong","family":"Zheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yali","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyun","family":"Xie","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongmin","family":"Jin","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"266","published-online":{"date-parts":[[2025,9,23]]},"reference":[{"key":"bpexae0593bib1","doi-asserted-by":"publisher","first-page":"e508","DOI":"10.1016\/S2665-9913(23)00163-7","type":"journal-article","article-title":"Global, regional, and national burden of osteoarthritis, 1990\u20132020 and projections to 2050: a systematic analysis for the Global Burden of Disease Study 2021","volume":"5","author":"Steinmetz","year":"2023","journal-title":"The Lancet Rheumatology"},{"key":"bpexae0593bib2","doi-asserted-by":"publisher","first-page":"2418","DOI":"10.1016\/j.arth.2021.02.051","type":"journal-article","article-title":"The changing characteristics of arthroplasty patients: a retrospective cohort study","volume":"36","author":"Ekhtiari","year":"2021","journal-title":"The Journal of Arthroplasty"},{"key":"bpexae0593bib3","doi-asserted-by":"publisher","first-page":"231","DOI":"10.1016\/j.compbiomed.2009.11.020","type":"journal-article","article-title":"Fast segmentation of bone in CT images using 3D adaptive thresholding","volume":"40","author":"Zhang","year":"2010","journal-title":"Comput. Biol. Med."},{"key":"bpexae0593bib4","doi-asserted-by":"publisher","first-page":"161","DOI":"10.1016\/j.cmpb.2017.11.007","type":"journal-article","article-title":"Fully automated segmentation of a hip joint using the patient-specific optimal thresholding and watershed algorithm","volume":"154","author":"Kim","year":"2018","journal-title":"Comput. Methods Programs Biomed."},{"key":"bpexae0593bib5","doi-asserted-by":"publisher","first-page":"165","DOI":"10.1007\/s00138-010-0274-z","type":"journal-article","article-title":"Fast parameter-free region growing segmentation with application to surgical planning","volume":"23","author":"S\u00e1nchez Mendoza","year":"2012","journal-title":"Mach. Vis. Appl."},{"key":"bpexae0593bib6","doi-asserted-by":"publisher","first-page":"1410\u20134","DOI":"10.1109\/CISP.2010.5646352","type":"conference-proceedings","article-title":"Image segmentation using edge detection and region distribution","volume":"3","author":"Huang","year":"2010"},{"key":"bpexae0593bib7","first-page":"804","type":"journal-article","article-title":"Image segmentation by using edge detection","volume":"2","author":"Al-Amri","year":"2010","journal-title":"International journal on computer science and engineering"},{"key":"bpexae0593bib8","doi-asserted-by":"publisher","first-page":"6345","DOI":"10.1109\/IEMBS.2009.5333269","type":"conference-proceedings","article-title":"An articulated statistical shape model for accurate hip joint segmentation","volume":"2009","author":"Kainmueller","year":"2009"},{"key":"bpexae0593bib9","doi-asserted-by":"publisher","first-page":"811\u20138","DOI":"10.1007\/978-3-642-04271-3_98","type":"conference-proceedings","article-title":"Automated segmentation of the femur and pelvis from 3D CT data of diseased hip using hierarchical statistical shape model of joint structure","volume":"12","author":"Yokota","year":"2009"},{"key":"bpexae0593bib10","doi-asserted-by":"publisher","first-page":"189","DOI":"10.1007\/s11548-013-0950-3","type":"journal-article","article-title":"Fully automatic segmentation of the femur from 3D-CT images using primitive shape recognition and statistical shape models","volume":"9","author":"Ben Younes","year":"2014","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"bpexae0593bib11","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-34817-6","type":"journal-article","article-title":"Segmentation of the proximal femur from MR images using deep convolutional neural networks","volume":"8","author":"Deniz","year":"2018","journal-title":"Sci. Rep."},{"key":"bpexae0593bib12","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/s11548-018-1883-7","type":"journal-article","article-title":"Automatic bone segmentation in whole-body CT images","volume":"14","author":"Klein","year":"2019","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"bpexae0593bib13","doi-asserted-by":"publisher","first-page":"1090","DOI":"10.1109\/TENCON50793.2020.9293750","type":"conference-proceedings","article-title":"Semantic segmentation of femur bone from MRI images of patients with hematologic malignancies","author":"Peng","year":"2020"},{"key":"bpexae0593bib14","doi-asserted-by":"publisher","first-page":"1043","DOI":"10.1007\/s11760-020-01637-z","type":"journal-article","article-title":"Femoral head segmentation based on improved fully convolutional neural network for ultrasound images","volume":"14","author":"Chen","year":"2020","journal-title":"Signal, Image and Video Processing"},{"key":"bpexae0593bib15","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.103767","type":"journal-article","article-title":"Bone segmentation on whole-body CT using convolutional neural network with novel data augmentation techniques","volume":"121","author":"Noguchi","year":"2020","journal-title":"Comput. Biol. Med."},{"key":"bpexae0593bib16","doi-asserted-by":"publisher","DOI":"10.3389\/fsurg.2022.913385","type":"journal-article","article-title":"Accuracy and reliability analysis of a machine learning based segmentation tool for intertrochanteric femoral fracture CT","volume":"9","author":"Wang","year":"2022","journal-title":"Frontiers in Surgery"},{"key":"bpexae0593bib17","doi-asserted-by":"publisher","first-page":"3066","DOI":"10.1109\/CAC48633.2019.8996989","type":"conference-proceedings","article-title":"Automatic segmentation algorithm of femur and tibia based on Vnet-C network","author":"Zhou","year":"2019"},{"key":"bpexae0593bib18","doi-asserted-by":"publisher","first-page":"1417","DOI":"10.1007\/s11517-022-02529-9","type":"journal-article","article-title":"A deep learning-based approach to automatic proximal femur segmentation in quantitative CT images","volume":"60","author":"Deng","year":"2022","journal-title":"Med. Biol. Eng. Comput."},{"key":"bpexae0593bib19","doi-asserted-by":"publisher","first-page":"685","DOI":"10.1109\/SIPROCESS.2019.8868690","type":"conference-proceedings","article-title":"Liver segmentation in CT based on ResUNet with 3D probabilistic and geometric post process","author":"Xu","year":"2019"},{"year":"2024","author":"Xie","key":"bpexae0593bib20","doi-asserted-by":"publisher","DOI":"10.21203\/rs.3.rs-4200861\/v1","type":"preprint"},{"key":"bpexae0593bib21","doi-asserted-by":"publisher","first-page":"274","DOI":"10.1007\/978-3-319-67389-9_32","type":"conference-proceedings","article-title":"3D U-net with multi-level deep supervision: fully automatic segmentation of proximal femur in 3D MR images","author":"Zeng","year":"2017"},{"key":"bpexae0593bib22","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1109\/JBHI.2017.2785389","type":"journal-article","article-title":"Three-dimensional feature-enhanced network for automatic femur segmentation","volume":"23","author":"Chen","year":"2017","journal-title":"IEEE journal of biomedical and health informatics"},{"key":"bpexae0593bib23","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s11548-021-02363-8","type":"journal-article","article-title":"Deep learning to segment pelvic bones: large-scale CT datasets and baseline models","volume":"16","author":"Liu","year":"2021","journal-title":"International Journal of Computer Assisted Radiology and Surgery"},{"key":"bpexae0593bib24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/TENSYMP54529.2022.9864546","type":"conference-proceedings","article-title":"A-UNet: attention 3D UNet architecture for multiclass segmentation of Brain Tumor","author":"Agarwala","year":"2022"},{"year":"2021","author":"Chen","key":"bpexae0593bib25","type":"preprint"},{"key":"bpexae0593bib26","doi-asserted-by":"publisher","DOI":"10.7812\/TPP\/17-084","type":"journal-article","article-title":"Hip osteoarthritis: a primer","volume":"22","author":"Lespasio","year":"2018","journal-title":"The Permanente Journal"},{"key":"bpexae0593bib27","doi-asserted-by":"publisher","first-page":"568","DOI":"10.1001\/jama.2020.22171","type":"journal-article","article-title":"Diagnosis and treatment of hip and knee osteoarthritis: a review","volume":"325","author":"Katz","year":"2021","journal-title":"JAMA"},{"key":"bpexae0593bib28","doi-asserted-by":"publisher","first-page":"283","DOI":"10.1016\/j.recot.2014.04.005","type":"journal-article","article-title":"Calidad de vida en pacientes con artrosis de rodilla y\/o cadera","volume":"58","author":"Bernad-Pineda","year":"2014","journal-title":"Revista Espa\u00f1ola de Cirug\u00eda Ortop\u00e9dica y Traumatolog\u00eda"},{"key":"bpexae0593bib29","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-031-16443-9_1","type":"conference-proceedings","article-title":"Automatic segmentation of hip osteophytes in dxa scans using u-nets","author":"Ebsim","year":"2022"},{"key":"bpexae0593bib30","doi-asserted-by":"publisher","first-page":"196394","DOI":"10.1109\/ACCESS.2020.3034418","type":"journal-article","article-title":"Deep 3D convolutional networks to segment bones affected by severe osteoarthritis in CT scans for PSI-based knee surgical planning","volume":"8","author":"Marzorati","year":"2020","journal-title":"IEEE Access"},{"key":"bpexae0593bib31","doi-asserted-by":"publisher","first-page":"5039","DOI":"10.1109\/EMBC48229.2022.9871953","type":"conference-proceedings","article-title":"CEL-Unet: a novel CNN architecture for 3D segmentation of knee bones affected by severe osteoarthritis for PSI-Based surgical planning","author":"Marsilio","year":"2022"},{"key":"bpexae0593bib32","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1109\/3DV.2016.79","type":"conference-proceedings","article-title":"V-net: Fully convolutional neural networks for volumetric medical image segmentation","author":"Milletari","year":"2016"},{"key":"bpexae0593bib33","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2024.103280","type":"journal-article","article-title":"TransUNet: rethinking the U-Net architecture design for medical image segmentation through the lens of transformers","volume":"97","author":"Chen","year":"2024","journal-title":"Med. Image Anal."},{"key":"bpexae0593bib34","doi-asserted-by":"publisher","first-page":"2999\u20133007","DOI":"10.1109\/ICCV.2017.324","type":"conference-proceedings","article-title":"Focal loss for dense object detection","author":"Lin","year":"2017"},{"key":"bpexae0593bib35","first-page":"285","type":"conference-proceedings","article-title":"Boundary loss for highly unbalanced segmentation","author":"Kervadec","year":"2019"},{"key":"bpexae0593bib36","doi-asserted-by":"publisher","DOI":"10.7937\/K9\/TCIA.2015.AQIIDCNM","type":"other","article-title":"A new 2.5D representation for lymph node detection in CT [Data set]","author":"Roth","year":"2015"},{"key":"bpexae0593bib37","type":"conference-proceedings","article-title":"A method for stochastic optimization","volume":"5","author":"Kinga","year":"2015"}],"container-title":["Biomedical Physics &amp; Engineering Express"],"original-title":[],"link":[{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae0593","content-type":"text\/html","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae0593\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae0593","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae0593\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae0593\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae0593\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"syndication"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae0593\/pdf","content-type":"application\/pdf","content-version":"am","intended-application":"similarity-checking"},{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae0593\/pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,23]],"date-time":"2025-09-23T11:24:13Z","timestamp":1758626653000},"score":1,"resource":{"primary":{"URL":"https:\/\/iopscience.iop.org\/article\/10.1088\/2057-1976\/ae0593"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,23]]},"references-count":37,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2025,9,23]]},"published-print":{"date-parts":[[2025,9,30]]}},"URL":"https:\/\/doi.org\/10.1088\/2057-1976\/ae0593","relation":{},"ISSN":["2057-1976"],"issn-type":[{"type":"electronic","value":"2057-1976"}],"subject":[],"published":{"date-parts":[[2025,9,23]]},"assertion":[{"value":"A 3D multi-task network for the automatic segmentation of CT images featuring hip osteoarthritis","name":"article_title","label":"Article Title"},{"value":"Biomedical Physics & Engineering Express","name":"journal_title","label":"Journal Title"},{"value":"paper","name":"article_type","label":"Article Type"},{"value":"\u00a9 2025 IOP Publishing Ltd. All rights, including for text and data mining, AI training, and similar technologies, are reserved.","name":"copyright_information","label":"Copyright Information"},{"value":"2025-06-04","name":"date_received","label":"Date Received","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-09-10","name":"date_accepted","label":"Date Accepted","group":{"name":"publication_dates","label":"Publication dates"}},{"value":"2025-09-23","name":"date_epub","label":"Online publication date","group":{"name":"publication_dates","label":"Publication dates"}}]}}