{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,29]],"date-time":"2026-10-29T12:16:06Z","timestamp":1793276166829,"version":"4.5.0"},"reference-count":40,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T00:00:00Z","timestamp":1751932800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","award":["2023R1A2C200532611"],"award-info":[{"award-number":["2023R1A2C200532611"]}],"id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"name":"the Ministry of Trade Industry & Energy","award":["RS-2025-14322975"],"award-info":[{"award-number":["RS-2025-14322975"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Oral Health"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>The purpose of this study was to compare the performances of 2D, 2.5D, and 3D CNN-based segmentation networks, along with a 3D vision transformer-based segmentation network, for segmenting mandibular canals (MCs) on the public and external CBCT datasets under the same GPU memory capacity. We also performed ablation studies for an image-cropping (IC) technique and segmentation loss functions. 3D-UNet showed the highest segmentation performance for the MC than those of 2D and 2.5D segmentation networks on public test datasets, achieving 0.569\u2009\u00b1\u20090.107, 0.719\u2009\u00b1\u20090.092, 0.664\u2009\u00b1\u20090.131, and 0.812\u2009\u00b1\u20090.095 in terms of JI, DSC, PR, and RC, respectively. On the external test dataset, 3D-UNet achieved 0.564\u2009\u00b1\u20090.092, 0.716\u2009\u00b1\u20090.081, 0.812\u2009\u00b1\u20090.087, and 0.652\u2009\u00b1\u20090.103 in terms of JI, DSC, PR, and RC, respectively. The IC technique and multi-planar Dice loss improved the boundary details and structural connectivity of the MC from the mental foramen to the mandibular foramen. The 3D-UNet demonstrated superior segmentation performance for the MC by learning 3D volumetric context information for the entire MC in the CBCT volume.<\/jats:p>","DOI":"10.1186\/s12903-025-06483-4","type":"journal-article","created":{"date-parts":[[2025,7,8]],"date-time":"2025-07-08T05:54:59Z","timestamp":1751954099000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Comparison of 2D, 2.5D, and 3D segmentation networks for mandibular canals in CBCT images: a study on public and external datasets"],"prefix":"10.1186","volume":"25","author":[{"given":"Su","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jong Soo","family":"Jeong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dahyun","family":"Song","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji Yong","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sang-Heon","family":"Lim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sujeong","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ji-Yong","family":"Yoo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun-Min","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jo-Eun","family":"Kim","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kyung-Hoe","family":"Huh","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sam-Sun","family":"Lee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Min-Suk","family":"Heo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Won-Jin","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,8]]},"reference":[{"key":"6483_CR1","doi-asserted-by":"publisher","first-page":"387","DOI":"10.1007\/s00784-011-0544-9","volume":"16","author":"C de Oliveira-Santos","year":"2012","unstructured":"de Oliveira-Santos C, et al. Assessment of variations of the mandibular canal through cone beam computed tomography. Clin Oral Invest. 2012;16:387\u201393.","journal-title":"Clin Oral Invest"},{"key":"6483_CR2","doi-asserted-by":"publisher","first-page":"151580","DOI":"10.1016\/j.aanat.2020.151580","volume":"232","author":"J Iwanaga","year":"2020","unstructured":"Iwanaga J, et al. Anatomy of the mandibular canal and surrounding structures: part i: morphology of the superior wall of the mandibular canal. Ann Anatomy-Anatomischer Anzeiger. 2020;232:151580.","journal-title":"Ann Anatomy-Anatomischer Anzeiger"},{"issue":"4","key":"6483_CR3","doi-asserted-by":"crossref","first-page":"e2","DOI":"10.5037\/jomr.2014.5402","volume":"5","author":"I Shavit","year":"2014","unstructured":"Shavit I, Juodzbalys G. Inferior alveolar nerve injuries following implant placement - importance of early diagnosis and treatment: a systematic review. J Oral Maxillofac Res. 2014;5(4):e2.","journal-title":"J Oral Maxillofac Res"},{"issue":"12","key":"6483_CR4","doi-asserted-by":"publisher","first-page":"1933","DOI":"10.1902\/jop.2006.060197","volume":"77","author":"G Greenstein","year":"2006","unstructured":"Greenstein G, Tarnow D. The mental foramen and nerve: clinical and anatomical factors related to dental implant placement: a literature review. J Periodontol. 2006;77(12):1933\u201343.","journal-title":"J Periodontol"},{"issue":"4","key":"6483_CR5","doi-asserted-by":"publisher","first-page":"e1","DOI":"10.5037\/jomr.2014.5401","volume":"5","author":"R Sarikov","year":"2014","unstructured":"Sarikov R, Juodzbalys G. Inferior alveolar nerve injury after mandibular third molar extraction: a literature review. J Oral Maxillofacial Res. 2014;5(4):e1.","journal-title":"J Oral Maxillofacial Res"},{"issue":"8","key":"6483_CR6","doi-asserted-by":"publisher","first-page":"e215","DOI":"10.1016\/j.bjoms.2013.01.011","volume":"51","author":"G-Z Xu","year":"2013","unstructured":"Xu G-Z, et al. Anatomic relationship between impacted third mandibular molar and the mandibular canal as the risk factor of inferior alveolar nerve injury. Br J Oral Maxillofac Surg. 2013;51(8):e215\u20139.","journal-title":"Br J Oral Maxillofac Surg"},{"issue":"9","key":"6483_CR7","doi-asserted-by":"publisher","first-page":"964","DOI":"10.1016\/j.ijom.2009.06.007","volume":"38","author":"H Ghaeminia","year":"2009","unstructured":"Ghaeminia H, et al. Position of the impacted third molar in relation to the mandibular canal. Diagnostic accuracy of cone beam computed tomography compared with panoramic radiography. Int J Oral Maxillofac Surg. 2009;38(9):964\u201371.","journal-title":"Int J Oral Maxillofac Surg"},{"issue":"3","key":"6483_CR8","doi-asserted-by":"publisher","first-page":"308","DOI":"10.1002\/jemt.22980","volume":"81","author":"U Aksoy","year":"2018","unstructured":"Aksoy U, Aksoy S, Orhan K. A cone-beam computed tomography study of the anatomical relationships between mandibular teeth and the mandibular canal, with a review of the current literature. Microsc Res Tech. 2018;81(3):308\u201314.","journal-title":"Microsc Res Tech"},{"key":"6483_CR9","doi-asserted-by":"publisher","first-page":"609","DOI":"10.1007\/s00276-017-1928-6","volume":"40","author":"L Gu","year":"2018","unstructured":"Gu L, et al. Anatomic study of the position of the mandibular canal and corresponding mandibular third molar on cone-beam computed tomography images. Surg Radiol Anat. 2018;40:609\u201314.","journal-title":"Surg Radiol Anat"},{"issue":"2","key":"6483_CR10","doi-asserted-by":"publisher","first-page":"183","DOI":"10.1111\/j.1600-0501.2011.02314.x","volume":"24","author":"G Juodzbalys","year":"2013","unstructured":"Juodzbalys G, et al. Inferior alveolar nerve injury associated with implant surgery. Clin Oral Implant Res. 2013;24(2):183\u201390.","journal-title":"Clin Oral Implant Res"},{"issue":"1","key":"6483_CR11","doi-asserted-by":"publisher","first-page":"13460","DOI":"10.1038\/s41598-022-17341-6","volume":"12","author":"B-S Jeoun","year":"2022","unstructured":"Jeoun B-S, et al. Canal-Net for automatic and robust 3D segmentation of mandibular canals in CBCT images using a continuity-aware contextual network. Sci Rep. 2022;12(1):13460.","journal-title":"Sci Rep"},{"issue":"3","key":"6483_CR12","doi-asserted-by":"publisher","first-page":"240","DOI":"10.1590\/S1678-77572011000300011","volume":"19","author":"C Oliveira-Santos","year":"2011","unstructured":"Oliveira-Santos C, et al. Visibility of the mandibular canal on CBCT cross-sectional images. J Appl Oral Sci. 2011;19(3):240\u20133.","journal-title":"J Appl Oral Sci"},{"key":"6483_CR13","doi-asserted-by":"publisher","first-page":"106411","DOI":"10.1016\/j.bspc.2024.106411","volume":"95","author":"S Yang","year":"2024","unstructured":"Yang S, et al. MAFNet: A deep multi-scale attentive fusion network for virtual osteotomy of maxillofacial bones in CT images containing metal artifacts. Biomed Signal Process Control. 2024;95:106411.","journal-title":"Biomed Signal Process Control"},{"issue":"1","key":"6483_CR14","doi-asserted-by":"publisher","first-page":"803","DOI":"10.1186\/s12903-023-03452-7","volume":"23","author":"S Yang","year":"2023","unstructured":"Yang S, et al. Ceph-Net: automatic detection of cephalometric landmarks on scanned lateral cephalograms from children and adolescents using an attention-based stacked regression network. BMC Oral Health. 2023;23(1):803.","journal-title":"BMC Oral Health"},{"key":"6483_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s00414-024-03204-4","volume":"138","author":"SJ Park","year":"2024","unstructured":"Park SJ, et al. Automatic and robust estimation of sex and chronological age from panoramic radiographs using a multi-task deep learning network: a study on a South Korean population. Int J Legal Med. 2024;138:1\u201317.","journal-title":"Int J Legal Med"},{"key":"6483_CR16","doi-asserted-by":"publisher","first-page":"102802","DOI":"10.1016\/j.media.2023.102802","volume":"88","author":"F Shamshad","year":"2023","unstructured":"Shamshad F, et al. Transformers in medical imaging: A survey. Med Image Anal. 2023;88:102802.","journal-title":"Med Image Anal"},{"key":"6483_CR17","doi-asserted-by":"publisher","first-page":"1302524","DOI":"10.3389\/fbioe.2023.1302524","volume":"11","author":"J Lv","year":"2023","unstructured":"Lv J, et al. Automatic segmentation of mandibular canal using transformer based neural networks. Front Bioeng Biotechnol. 2023;11:1302524.","journal-title":"Front Bioeng Biotechnol"},{"key":"6483_CR18","doi-asserted-by":"publisher","first-page":"103891","DOI":"10.1016\/j.jdent.2021.103891","volume":"116","author":"P Lahoud","year":"2022","unstructured":"Lahoud P, et al. Development and validation of a novel artificial intelligence driven tool for accurate mandibular canal segmentation on CBCT. J Dent. 2022;116:103891.","journal-title":"J Dent"},{"key":"6483_CR19","doi-asserted-by":"publisher","first-page":"111272","DOI":"10.1109\/ACCESS.2022.3213839","volume":"10","author":"G Du","year":"2022","unstructured":"Du G, Tian X, Song Y. Mandibular canal segmentation from CBCT image using 3D convolutional neural network with scSE attention. IEEE Access. 2022;10:111272\u201383.","journal-title":"IEEE Access"},{"issue":"1","key":"6483_CR20","doi-asserted-by":"publisher","first-page":"866","DOI":"10.1186\/s12903-023-03607-6","volume":"23","author":"YS Yoo","year":"2023","unstructured":"Yoo YS, et al. Comparison of 2D, 2.5 D, and 3D segmentation networks for maxillary sinuses and lesions in CBCT images. BMC Oral Health. 2023;23(1):866.","journal-title":"BMC Oral Health"},{"issue":"2","key":"6483_CR21","doi-asserted-by":"publisher","first-page":"181","DOI":"10.3390\/bioengineering10020181","volume":"10","author":"A Avesta","year":"2023","unstructured":"Avesta A, et al. Comparing 3D, 2.5 D, and 2D approaches to brain image auto-segmentation. Bioengineering. 2023;10(2):181.","journal-title":"Bioengineering"},{"key":"6483_CR22","doi-asserted-by":"crossref","unstructured":"Lumetti, L., et al., Enhancing Patch-Based Learning for the Segmentation of the Mandibular Canal. IEEE Access, 2024.","DOI":"10.1109\/ACCESS.2024.3408629"},{"key":"6483_CR23","doi-asserted-by":"crossref","unstructured":"Cipriano, M., et al. Improving segmentation of the inferior alveolar nerve through deep label propagation. Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 2022.","DOI":"10.1109\/CVPR52688.2022.02046"},{"key":"6483_CR24","doi-asserted-by":"crossref","unstructured":"He, K., et al. Deep residual learning for image recognition. Proceedings of the IEEE conference on computer vision and pattern recognition. 2016.","DOI":"10.1109\/CVPR.2016.90"},{"key":"6483_CR25","unstructured":"Oktay, O., et al., Attention u-net: Learning where to look for the pancreas. arXiv preprint arXiv:1804.03999, 2018."},{"key":"6483_CR26","doi-asserted-by":"crossref","unstructured":"Ronneberger, O., P. Fischer, and T. Brox. U-net: Convolutional networks for biomedical image segmentation. in International Conference on Medical image computing and computer-assisted intervention. 2015. Springer.","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"6483_CR27","volume-title":"3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation","author":"\u00d6 \u00c7i\u00e7ek","year":"2016","unstructured":"\u00c7i\u00e7ek \u00d6, et al. 3D U-Net: Learning Dense Volumetric Segmentation from Sparse Annotation. Cham: Springer International Publishing; 2016."},{"key":"6483_CR28","doi-asserted-by":"crossref","unstructured":"Hatamizadeh, A., et al. Swin unetr: Swin transformers for semantic segmentation of brain tumors in mri images. International MICCAI brainlesion workshop. 2021. Springer.","DOI":"10.1007\/978-3-031-08999-2_22"},{"key":"6483_CR29","first-page":"148","volume":"1","author":"YJ Zhang","year":"2001","unstructured":"Zhang YJ. A review of recent evaluation methods for image segmentation. IEEE. 2001;1:148\u201351.","journal-title":"IEEE"},{"key":"6483_CR30","doi-asserted-by":"publisher","first-page":"98","DOI":"10.1007\/s12663-019-01224-x","volume":"19","author":"A Komal","year":"2020","unstructured":"Komal A, et al. Study of normal anatomy of mandibular canal and its variations in Indian population using CBCT. J Maxillofacial Oral Surg. 2020;19:98\u2013105.","journal-title":"J Maxillofacial Oral Surg"},{"key":"6483_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s40537-021-00444-8","volume":"8","author":"L Alzubaidi","year":"2021","unstructured":"Alzubaidi L, et al. Review of deep learning: concepts, CNN architectures, challenges, applications, future directions. J Big Data. 2021;8:1\u201374.","journal-title":"J Big Data"},{"key":"6483_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10278-024-00981-7","volume":"37","author":"W Yao","year":"2024","unstructured":"Yao W, et al. From cnn to transformer: a review of medical image segmentation models. J Imaging Inform Med. 2024;37:1\u201319.","journal-title":"J Imaging Inform Med"},{"key":"6483_CR33","doi-asserted-by":"publisher","first-page":"102762","DOI":"10.1016\/j.media.2023.102762","volume":"85","author":"J Li","year":"2023","unstructured":"Li J, et al. Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives. Med Image Anal. 2023;85:102762.","journal-title":"Med Image Anal"},{"key":"6483_CR34","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.ejmp.2021.02.006","volume":"83","author":"I Castiglioni","year":"2021","unstructured":"Castiglioni I, et al. AI applications to medical images: From machine learning to deep learning. Physica Med. 2021;83:9\u201324.","journal-title":"Physica Med"},{"issue":"4","key":"6483_CR35","first-page":"4396","volume":"45","author":"K Zhou","year":"2022","unstructured":"Zhou K, et al. Domain generalization: a survey. IEEE Trans Pattern Anal Mach Intell. 2022;45(4):4396\u2013415.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"10s","key":"6483_CR36","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3502287","volume":"54","author":"MA Bansal","year":"2022","unstructured":"Bansal MA, Sharma DR, Kathuria DM. A systematic review on data scarcity problem in deep learning: solution and applications. ACM Computing Surveys (Csur). 2022;54(10s):1\u201329.","journal-title":"ACM Computing Surveys (Csur)"},{"issue":"1","key":"6483_CR37","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","volume":"45","author":"K Han","year":"2022","unstructured":"Han K, et al. A survey on vision transformer. IEEE Trans Pattern Anal Mach Intell. 2022;45(1):87\u2013110.","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"11","key":"6483_CR38","doi-asserted-by":"publisher","first-page":"12561","DOI":"10.1007\/s10462-023-10453-z","volume":"56","author":"E Goceri","year":"2023","unstructured":"Goceri E. Medical image data augmentation: techniques, comparisons and interpretations. Artif Intell Rev. 2023;56(11):12561\u2013605.","journal-title":"Artif Intell Rev"},{"key":"6483_CR39","unstructured":"Lim, SH., et al. Anatomy-guided latent diffusion model for fine-grained medical image synthetic augmentation. Medical Imaging with Deep Learning. 2024."},{"key":"6483_CR40","doi-asserted-by":"publisher","first-page":"106803","DOI":"10.1016\/j.compbiomed.2023.106803","volume":"158","author":"S-R Kang","year":"2023","unstructured":"Kang S-R, et al. Structure-preserving quality improvement of cone beam CT images using contrastive learning. Comput Biol Med. 2023;158:106803.","journal-title":"Comput Biol Med"}],"container-title":["BMC Oral Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-025-06483-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12903-025-06483-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-025-06483-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,10]],"date-time":"2025-07-10T09:16:01Z","timestamp":1752138961000},"score":1,"resource":{"primary":{"URL":"https:\/\/bmcoralhealth.biomedcentral.com\/articles\/10.1186\/s12903-025-06483-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,8]]},"references-count":40,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2025,12]]}},"alternative-id":["6483"],"URL":"https:\/\/doi.org\/10.1186\/s12903-025-06483-4","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-5035833\/v1","asserted-by":"object"}]},"ISSN":["1472-6831"],"issn-type":[{"value":"1472-6831","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,8]]},"assertion":[{"value":"5 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study was performed with approval from the Institutional Review Board (IRB) of Seoul National University Dental Hospital (ERI18001). The IRB of Seoul National University Dental Hospital approved the waiver for informed consent because this was a retrospective study. The study was performed in accordance with the Declaration of Helsinki.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval and consent to participate"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Consent for publication"}},{"value":"The authors declare no competing interests.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"1126"}}