{"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":1793276166891,"version":"4.5.0"},"reference-count":40,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2023,11,17]],"date-time":"2023-11-17T00:00:00Z","timestamp":1700179200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Bioeng. Biotechnol."],"abstract":"<jats:p>Accurate 3D localization of the mandibular canal is crucial for the success of digitally-assisted dental surgeries. Damage to the mandibular canal may result in severe consequences for the patient, including acute pain, numbness, or even facial paralysis. As such, the development of a fast, stable, and highly precise method for mandibular canal segmentation is paramount for enhancing the success rate of dental surgical procedures. Nonetheless, the task of mandibular canal segmentation is fraught with challenges, including a severe imbalance between positive and negative samples and indistinct boundaries, which often compromise the completeness of existing segmentation methods. To surmount these challenges, we propose an innovative, fully automated segmentation approach for the mandibular canal. Our methodology employs a Transformer architecture in conjunction with cl-Dice loss to ensure that the model concentrates on the connectivity of the mandibular canal. Additionally, we introduce a pixel-level feature fusion technique to bolster the model\u2019s sensitivity to fine-grained details of the canal structure. To tackle the issue of sample imbalance and vague boundaries, we implement a strategy founded on mandibular foramen localization to isolate the maximally connected domain of the mandibular canal. Furthermore, a contrast enhancement technique is employed for pre-processing the raw data. We also adopt a Deep Label Fusion strategy for pre-training on synthetic datasets, which substantially elevates the model\u2019s performance. Empirical evaluations on a publicly accessible mandibular canal dataset reveal superior performance metrics: a Dice score of 0.844, click score of 0.961, IoU of 0.731, and HD95 of 2.947\u00a0mm. These results not only validate the efficacy of our approach but also establish its state-of-the-art performance on the public mandibular canal dataset.<\/jats:p>","DOI":"10.3389\/fbioe.2023.1302524","type":"journal-article","created":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T10:21:52Z","timestamp":1700302912000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":27,"title":["Automatic segmentation of mandibular canal using transformer based neural networks"],"prefix":"10.3389","volume":"11","author":[{"given":"Jinxuan","family":"Lv","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajie","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wang","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Gen","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hengyu","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2023,11,17]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"581","DOI":"10.1007\/s11548-016-1484-2","article-title":"Automatic segmentation of mandibular canal in cone beam CT images using conditional statistical shape model and fast marching","volume":"12","author":"Abdolali","year":"2017","journal-title":"Int. J. Comput. assisted radiology Surg."},{"key":"B2","doi-asserted-by":"publisher","first-page":"2213","DOI":"10.1007\/s00784-016-2014-x","article-title":"Tracking of the inferior alveolar nerve: its implication in surgical planning","volume":"21","author":"Agbaje","year":"2017","journal-title":"Clin. Oral Investig."},{"key":"B3","first-page":"35","article-title":"Mental foramen location and its implication in dental treatment plan","volume":"2","author":"Al-Juboori","year":"2014","journal-title":"World J. Med. Med. Sci. Res."},{"key":"B4","unstructured":"Swin-unet: unet-like pure transformer for medical image segmentation\n            CaoH."},{"key":"B5","article-title":"Transunet: transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"B6","doi-asserted-by":"publisher","first-page":"11500","DOI":"10.1109\/ACCESS.2022.3144840","article-title":"Deep segmentation of the mandibular canal: a new 3D annotated dataset of CBCT volumes","volume":"10","author":"Cipriano","year":"","journal-title":"IEEE Access"},{"key":"B7","first-page":"21137","article-title":"Improving segmentation of the inferior alveolar nerve through deep label propagation","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Cipriano","year":""},{"key":"B8","doi-asserted-by":"publisher","first-page":"2096","DOI":"10.1038\/s41467-022-29637-2","article-title":"A fully automatic AI system for tooth and alveolar bone segmentation from cone-beam CT images","volume":"13","author":"Cui","year":"2022","journal-title":"Nat. Commun."},{"key":"B9","first-page":"6361","article-title":"ToothNet: automatic tooth instance segmentation and identification from cone beam CT images","volume-title":"IEEE\/CVF conference on computer vision and pattern recognition (CVPR)","author":"Cui","year":"2019"},{"key":"B10","doi-asserted-by":"publisher","first-page":"279","DOI":"10.1016\/j.neucom.2022.10.060","article-title":"TD-Net: trans-Deformer network for automatic pancreas segmentation","volume":"517","author":"Dai","year":"2023","journal-title":"Neurocomputing"},{"key":"B11","volume-title":"An image is worth 16x16 words: transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"B12","doi-asserted-by":"publisher","first-page":"111272","DOI":"10.1109\/access.2022.3213839","article-title":"Mandibular canal segmentation from CBCT image using 3D convolutional neural network with scSE attention","volume":"10","author":"Du","year":"2022","journal-title":"IEEE Access"},{"key":"B13","doi-asserted-by":"publisher","first-page":"208","DOI":"10.22266\/ijies2021.1231.20","article-title":"Residual fully convolutional network for mandibular canal segmentation","volume":"14","author":"Faradhilla","year":"2021","journal-title":"Int. J. Intelligent Eng. Syst."},{"key":"B14","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1111\/clr.14063","article-title":"Convolutional neural network\u2010based automated maxillary alveolar bone segmentation on cone\u2010beam computed tomography images","volume":"34","author":"Fontenele","year":"2023","journal-title":"Clin. Oral Implants Res."},{"key":"B15","first-page":"574","article-title":"Unetr: transformers for 3d medical image segmentation","volume-title":"Proceedings of the IEEE\/CVF winter conference on applications of computer vision","author":"Hatamizadeh","year":""},{"key":"B16","unstructured":"Swin transformers for semantic segmentation of brain tumors in MRI images\n            HatamizadehA.\n            NathV.\n            TangY.\n            YangD.\n            RothH.\n            XuD.\n            SwinUNETR"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1596","DOI":"10.1109\/TMI.2022.3143833","article-title":"RTNet: relation transformer network for diabetic retinopathy multi-lesion segmentation","volume":"41","author":"Huang","year":"2022","journal-title":"IEEE Trans. Med. Imaging"},{"key":"B18","doi-asserted-by":"publisher","first-page":"5842","DOI":"10.1038\/s41598-020-62321-3","article-title":"Deep learning method for mandibular canal segmentation in dental cone beam computed tomography volumes","volume":"10","author":"Jaskari","year":"2020","journal-title":"Sci. Rep."},{"key":"B19","doi-asserted-by":"publisher","first-page":"13460","DOI":"10.1038\/s41598-022-17341-6","article-title":"Canal-Net for automatic and robust 3D segmentation of mandibular canals in CBCT images using a continuity-aware contextual network","volume":"12","author":"Jeoun","year":"2022","journal-title":"Sci. Rep."},{"key":"B20","first-page":"76","article-title":"Automatic extraction of mandibular nerve and bone from cone-beam CT data","author":"Kainmueller","year":"2009"},{"key":"B21","doi-asserted-by":"publisher","first-page":"253","DOI":"10.1109\/TBME.2010.2089053","article-title":"Automatic extraction of inferior alveolar nerve canal using feature-enhancing panoramic volume rendering","volume":"58","author":"Kim","year":"2010","journal-title":"IEEE Trans. Biomed. Eng."},{"key":"B22","doi-asserted-by":"publisher","first-page":"5711","DOI":"10.1038\/s41598-020-62586-8","article-title":"Automatic mandibular canal detection using a deep convolutional neural network","volume":"10","author":"Kwak","year":"2020","journal-title":"Sci. Rep."},{"key":"B23","doi-asserted-by":"publisher","first-page":"103891","DOI":"10.1016\/j.jdent.2021.103891","article-title":"Development and validation of a novel artificial intelligence driven tool for accurate mandibular canal segmentation on CBCT","volume":"116","author":"Lahoud","year":"2022","journal-title":"J. Dent."},{"key":"B24","first-page":"102762","volume-title":"Transforming medical imaging with Transformers? A comparative review of key properties, current progresses, and future perspectives","author":"Li","year":"2023"},{"key":"B25","first-page":"1782","volume-title":"Association of the inferior alveolar nerve position and nerve injury: a systematic review and meta-analysis","author":"Li","year":"2022"},{"key":"B26","unstructured":"Swin transformer: hierarchical vision transformer using shifted windo\n            LiuZ.\n          2021"},{"key":"B27","article-title":"Medical image analysis based on transformer: a review","author":"Liu","year":"2022"},{"key":"B28","first-page":"327","article-title":"Automated tracking of the mandibular canal in CBCT images using matching and multiple hypotheses methods","volume-title":"Fourth international conference on communications and Electronics (ICCE)","author":"Moris","year":"2012"},{"key":"B29","doi-asserted-by":"publisher","first-page":"85","DOI":"10.1016\/j.patrec.2015.12.001","article-title":"Detection of the mandibular canal in orthopantomography using a Gabor-filtered anisotropic generalized Hough transform","volume":"83","author":"Onchis-Moaca","year":"2016","journal-title":"Pattern Recognit. Lett."},{"key":"B30","doi-asserted-by":"publisher","first-page":"403","DOI":"10.3390\/app12010403","article-title":"MSC-net: multitask learning network for retinal vessel segmentation and centerline extraction","volume":"12","author":"Pan","year":"2021","journal-title":"Appl. Sci."},{"key":"B31","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1117\/12.2611540","article-title":"CVT-Vnet: convolutional-transformer model for head and neck multi-organ segmentation","volume-title":"Medical imaging 2022: computer-aided diagnosis","author":"Pan","year":"2022"},{"key":"B32","first-page":"144","article-title":"Mental foramen: a morphological and morphometrical study","volume":"2","author":"Rai","year":"2014","journal-title":"Int. J. Health Biomed. Res."},{"key":"B33","volume-title":"UNETR++: delving into efficient and accurate 3D medical image segmentation","author":"Shaker","year":"2022"},{"key":"B34","first-page":"16560","article-title":"clDice-a novel topology-preserving loss function for tubular structure segmentation","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Shit","year":"2021"},{"key":"B35","doi-asserted-by":"publisher","first-page":"9877","DOI":"10.3390\/s22249877","article-title":"Dual-stage deeply supervised attention-based convolutional neural networks for mandibular canal segmentation in CBCT scans","volume":"22","author":"Usman","year":"2022","journal-title":"Sens"},{"key":"B36","doi-asserted-by":"publisher","first-page":"103786","DOI":"10.1016\/j.jdent.2021.103786","article-title":"Layered deep learning for automatic mandibular segmentation in cone-beam computed tomography","volume":"114","author":"Verhelst","year":"2021","journal-title":"J. Dent."},{"key":"B37","doi-asserted-by":"publisher","first-page":"68","DOI":"10.1902\/jop.2012.110524","article-title":"Accuracy of linear measurements and visibility of the mandibular canal of cone-beam computed tomography images with different voxel sizes: an in vitro study","volume":"84","author":"Waltrick","year":"2013","journal-title":"J. Periodontology"},{"key":"B38","doi-asserted-by":"publisher","first-page":"7074","DOI":"10.1002\/mp.15274","article-title":"Inferior alveolar canal segmentation based on cone\u2010beam computed tomography","volume":"48","author":"Wei","year":"2021","journal-title":"Med. Phys."},{"key":"B39","doi-asserted-by":"publisher","first-page":"101483","DOI":"10.1109\/access.2022.3208350","article-title":"Dental-yolo: alveolar bone and mandibular canal detection on cone beam computed tomography images for dental implant planning","volume":"10","author":"Widiasri","year":"2022","journal-title":"IEEE Access"},{"key":"B40","first-page":"1863","article-title":"Blood vessel segmentation from low-contrast and wide-field optical microscopic images of cranial window by attention-gate-based network","author":"Wu","year":"2022"}],"container-title":["Frontiers in Bioengineering and Biotechnology"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2023.1302524\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,18]],"date-time":"2023-11-18T10:22:01Z","timestamp":1700302921000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fbioe.2023.1302524\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,11,17]]},"references-count":40,"alternative-id":["10.3389\/fbioe.2023.1302524"],"URL":"https:\/\/doi.org\/10.3389\/fbioe.2023.1302524","relation":{},"ISSN":["2296-4185"],"issn-type":[{"value":"2296-4185","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,11,17]]},"article-number":"1302524"}}