{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T05:09:12Z","timestamp":1779340152248,"version":"3.51.4"},"reference-count":31,"publisher":"Springer Science and Business Media LLC","license":[{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T00:00:00Z","timestamp":1779321600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Okan University"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Odontology"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study aims to develop a deep learning model for the detection and segmentation of multiple anatomical landmarks on periapical radiographs from the maxilla and mandible. A total of 1930 paralleling-technique periapical radiographs with 21 annotated anatomical landmarks were divided into training (80%), validation (10%), and test (10%) sets. Geometry-preserving preprocessing was applied before dataset splitting, while appearance-based augmentation was performed exclusively on the training subset after the split. A YOLOv8x-seg architecture was trained for multi-class detection and instance segmentation. Performance was evaluated using precision, recall, F1-score, Dice coefficient, Intersection-over-Union, mean average precision, and receiver operating characteristic analysis. The model demonstrated stable training and consistent performance. Overall precision, recall, and F1-score were 0.820, 0.725, and 0.769, respectively, with an overall Dice coefficient of 0.621. High detection accuracy was achieved for well-defined structures such as the maxillary sinus, nasal fossa, nasal fossa floor, and nasal septum, whereas low-contrast landmarks showed reduced performance. Confidence-dependent analysis indicated optimal performance at low confidence thresholds (approximately 0.05\u20130.10). In conclusion, the proposed model effectively detected major anatomical landmarks on periapical radiographs while demonstrating expected limitations for small or low-contrast structures. Despite substantial anatomical variability across maxillary and mandibular regions, anterior\u2013posterior sites, and projection-dependent appearances of similar structures, these findings demonstrate that deep learning can reliably identify key anatomical landmarks, supporting safer, more consistent, and clinically meaningful radiographic interpretation in routine dental practice.<\/jats:p>","DOI":"10.1007\/s10266-026-01409-0","type":"journal-article","created":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:21:48Z","timestamp":1779337308000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-class anatomical landmark detection in periapical radiographs with deep learning"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8126-0928","authenticated-orcid":false,"given":"Cansu","family":"Buyuk","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alperen","family":"Saruhan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9328-4895","authenticated-orcid":false,"given":"Fatma","family":"Yuce","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4409-3101","authenticated-orcid":false,"given":"Ozer","family":"Celik","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9521-4682","authenticated-orcid":false,"given":"Elif","family":"Bilgir","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5036-9867","authenticated-orcid":false,"given":"\u0130brahim Sevki","family":"Bayrakdar","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2026,5,21]]},"reference":[{"key":"1409_CR1","first-page":"86","volume-title":"Oral Radiology: Principles and Interpretation","author":"SC White","year":"2014","unstructured":"White SC, Pharoah MJ. Oral radiology: principles and interpretation. 7th ed. St Louis, MO: Elsevier; 2014. p. 86.","edition":"7"},{"key":"1409_CR2","first-page":"81","volume-title":"Oral Radiology: Principles and Interpretation","author":"SC White","year":"2014","unstructured":"White SC, Pharoah MJ. Oral radiology: principles and interpretation. 7th ed. St Louis, MO: Elsevier; 2014. p. 81.","edition":"7"},{"issue":"1","key":"1409_CR3","first-page":"147","volume":"57","author":"K Kaji","year":"2023","unstructured":"Kaji K, Kotaki S, Maesoma A, et al. Hands-on periapical radiography training for dental hygiene students. J Osaka Dent Univ. 2023;57(1):147\u201352.","journal-title":"J Osaka Dent Univ"},{"issue":"3","key":"1409_CR4","doi-asserted-by":"publisher","first-page":"307","DOI":"10.5624\/isd.20210035","volume":"51","author":"R Shahrour","year":"2021","unstructured":"Shahrour R, Shah P, Withana T, Jung J, Syed AZ. Oroantral communication: causes, complications, treatments, and radiographic features\u2014a pictorial review. Imaging Sci Dent. 2021;51(3):307.","journal-title":"Imaging Sci Dent"},{"key":"1409_CR5","doi-asserted-by":"publisher","first-page":"469","DOI":"10.1007\/s00276-015-1565-x","volume":"38","author":"AE Laher","year":"2016","unstructured":"Laher AE, Wells M, Motara F, Kramer E, Moolla M, Mahomed Z. Finding the mental foramen. Surg Radiol Anat. 2016;38:469\u201376.","journal-title":"Surg Radiol Anat"},{"issue":"2","key":"1409_CR6","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1016\/j.joen.2010.11.014","volume":"37","author":"MM Bornstein","year":"2011","unstructured":"Bornstein MM, Lauber R, Sendi P, von Arx T. Comparison of periapical radiography and limited cone-beam computed tomography in mandibular molars for analysis of anatomical landmarks before apical surgery. J Endod. 2011;37(2):151\u20137.","journal-title":"J Endod"},{"key":"1409_CR7","doi-asserted-by":"publisher","unstructured":"Do\u011framaci EJ, Decurcio DDA, Chen CJ, Estrela C, Rossi-Fedele G. Accuracy of periapical and panoramic radiography for detection of root morphologies: a comparative study. Braz Oral Res. 2021;35:e065. https:\/\/doi.org\/10.1590\/1807-3107bor-2021.vol35.0065.","DOI":"10.1590\/1807-3107bor-2021.vol35.0065"},{"issue":"3","key":"1409_CR8","doi-asserted-by":"publisher","first-page":"20170305","DOI":"10.1259\/dmfr.20170305","volume":"47","author":"N Kadesj\u00f6","year":"2018","unstructured":"Kadesj\u00f6 N, Lynds R, Nilsson M, Shi XQ. Radiation dose from X-ray examinations of impacted canines: cone beam CT vs two-dimensional imaging. Dentomaxillofac Radiol. 2018;47(3):20170305.","journal-title":"Dentomaxillofac Radiol"},{"issue":"2","key":"1409_CR9","doi-asserted-by":"publisher","first-page":"640","DOI":"10.4067\/S0717-95022025000200640","volume":"43","author":"D Gerardi","year":"2025","unstructured":"Gerardi D, Angiolani F, K\u00ebrpi B, et al. Clinical oral anatomy in clinical dental practice: a scoping review. Int J Morp. 2025;43(2):640\u201350.","journal-title":"Int J Morp"},{"issue":"4","key":"1409_CR10","doi-asserted-by":"publisher","first-page":"444","DOI":"10.3390\/tomography10040034","volume":"10","author":"S Bernardi","year":"2024","unstructured":"Bernardi S, Bianchi S, Gerardi D, et al. Anatomy of maxillary sinus: Focus on vascularization and underwood septa via 3D imaging. Tomography Cureus. 2024;10(4):444\u201358.","journal-title":"Tomography Cureus"},{"key":"1409_CR11","doi-asserted-by":"publisher","first-page":"109315","DOI":"10.1016\/j.identj.2025.109315","volume":"76","author":"S Shujaat","year":"2025","unstructured":"Shujaat S, Aljadaan H, Alrashid H, Aboalela AA, Riaz M. FDA-approved AI solutions in dental imaging: a narrative review of applications, evidence, and outlook. Int Dent J. 2025;76:109315.","journal-title":"Int Dent J"},{"issue":"3","key":"1409_CR12","doi-asserted-by":"publisher","first-page":"100231","DOI":"10.1016\/j.mcpdig.2025.100231","volume":"3","author":"V Singh","year":"2025","unstructured":"Singh V, Cheng S, Kwan AC, Ebinger J. United States Food and Drug Administration regulation of clinical software in the era of artificial intelligence and machine learning. Mayo Clin Proc Digit Health. 2025;3(3):100231.","journal-title":"Mayo Clin Proc Digit Health"},{"issue":"7","key":"1409_CR13","doi-asserted-by":"publisher","first-page":"439","DOI":"10.1093\/dmfr\/twae028","volume":"53","author":"W Liu","year":"2024","unstructured":"Liu W, Li X, Liu C, Gao G, Xiong Y, Zhu T, et al. Automatic classification and segmentation of multiclass jaw lesions in cone-beam CT using deep learning. Dentomaxillofac Radiol. 2024;53(7):439\u201346.","journal-title":"Dentomaxillofac Radiol"},{"issue":"4","key":"1409_CR14","doi-asserted-by":"publisher","first-page":"468","DOI":"10.1007\/s11282-021-00577-9","volume":"38","author":"IS Bayrakdar","year":"2022","unstructured":"Bayrakdar IS, Orhan K, Akarsu S, \u00c7elik \u00d6, Atasoy S, Pekince A, et al. Deep-learning approach for caries detection and segmentation on dental bitewing radiographs. Oral Radiol. 2022;38(4):468\u201379.","journal-title":"Oral Radiol"},{"key":"1409_CR15","doi-asserted-by":"publisher","first-page":"126629","DOI":"10.1016\/j.neucom.2023.126629","volume":"554","author":"C Huang","year":"2023","unstructured":"Huang C, Wang J, Wang S, Zhang Y. A review of deep learning in dentistry. Neurocomputing. 2023;554:126629.","journal-title":"Neurocomputing"},{"issue":"12","key":"1409_CR16","doi-asserted-by":"publisher","first-page":"2577","DOI":"10.3390\/jcm10122577","volume":"10","author":"JY Cha","year":"2021","unstructured":"Cha JY, Yoon HI, Yeo IS, Huh KH, Han JS. Panoptic segmentation on panoramic radiographs: deep learning-based segmentation of various structures including maxillary sinus and mandibular canal. J Clin Med. 2021;10(12):2577.","journal-title":"J Clin Med"},{"issue":"4","key":"1409_CR17","doi-asserted-by":"publisher","first-page":"562","DOI":"10.1007\/s11282-025-00831-4","volume":"41","author":"F Yuce","year":"2025","unstructured":"Yuce F, Buyuk C, Bilgir E, \u00c7elik \u00d6, Bayrakdar \u0130\u015e. Deploying a novel deep learning framework for segmentation of specific anatomical structures on cone-beam CT. Oral Radiol. 2025;41(4):562\u201370.","journal-title":"Oral Radiol"},{"key":"1409_CR18","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/s11548-021-02319-y","volume":"16","author":"H Chen","year":"2021","unstructured":"Chen H, Li H, Zhao Y, Zhao J, Wang Y. Dental disease detection on periapical radiographs based on deep convolutional neural networks. Int J Comput Assist Radiol Surg. 2021;16:649\u201361.","journal-title":"Int J Comput Assist Radiol Surg"},{"issue":"7","key":"1409_CR19","doi-asserted-by":"publisher","first-page":"917","DOI":"10.1016\/j.joen.2019.03.016","volume":"45","author":"T Ekert","year":"2019","unstructured":"Ekert T, Krois J, Meinhold L, Elhennawy K, Emara R, Golla T, Schwendicke F. Deep learning for the radiographic detection of apical lesions. J Endod. 2019;45(7):917\u201322.","journal-title":"J Endod"},{"key":"1409_CR20","doi-asserted-by":"crossref","unstructured":"Sajad M, Shafi I, Ahmad J. Automatic lesion detection in periapical X-rays. In: Proceedings of the 2019 international conference on electrical, communication, and computer engineering (ICECCE). IEEE; 2019:1\u20136.","DOI":"10.1109\/ICECCE47252.2019.8940661"},{"issue":"15","key":"1409_CR21","doi-asserted-by":"publisher","first-page":"6837","DOI":"10.3390\/s23156837","volume":"23","author":"I Shafi","year":"2023","unstructured":"Shafi I, Sajad M, Fatima A, Aray DG, Lipari V, Diez IDLT, Ashraf I. Teeth lesion detection using deep learning and the Internet of Things post\u2013COVID-19. Sens (Basel). 2023;23(15):6837.","journal-title":"Sens (Basel)"},{"key":"1409_CR22","doi-asserted-by":"publisher","first-page":"105104","DOI":"10.1016\/j.jdent.2024.105104","volume":"105","author":"U Pul","year":"2024","unstructured":"Pul U, Schwendicke F. Artificial intelligence for detecting periapical radiolucencies: a systematic review and meta-analysis. J Dent. 2024;105:105104.","journal-title":"J Dent"},{"issue":"1","key":"1409_CR23","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1186\/s12903-023-03532-8","volume":"23","author":"\u0130 Ba\u011f","year":"2023","unstructured":"Ba\u011f \u0130, Bilgir E, Bayrakdar IS, et al. An artificial intelligence study: automatic description of anatomic landmarks on panoramic radiographs in the pediatric population. BMC Oral Health. 2023;23(1):764.","journal-title":"BMC Oral Health"},{"issue":"1","key":"1409_CR24","doi-asserted-by":"publisher","first-page":"8814","DOI":"10.1038\/s41598-025-93317-6","volume":"15","author":"H Tang","year":"2025","unstructured":"Tang H, Liu S, Shi Y, et al. Automatic segmentation and landmark detection of 3D CBCT images using semi supervised learning for assisting orthognathic surgery planning. Sci Rep. 2025;15(1):8814.","journal-title":"Sci Rep"},{"issue":"1","key":"1409_CR25","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1007\/s10266-013-0144-z","volume":"103","author":"M Shahbazian","year":"2015","unstructured":"Shahbazian M, Vandewoude C, Wyatt J, Jacobs R. Comparative assessment of periapical radiography and CBCT imaging for radiodiagnostics in the posterior maxilla. Odontology. 2015;103(1):97\u2013104. https:\/\/doi.org\/10.1007\/s10266-013-0144-z.","journal-title":"Odontology"},{"issue":"6","key":"1409_CR26","doi-asserted-by":"publisher","first-page":"711","DOI":"10.1016\/j.oooo.2020.08.024","volume":"131","author":"HA Khan","year":"2021","unstructured":"Khan HA, Haider MA, Ansari HA, Ishaq H, Kiyani A, Sohail K, Khurram SA. Automated feature detection in dental periapical radiographs using deep learning. Oral Surg Oral Med Oral Pathol Oral Radiol. 2021;131(6):711\u201320.","journal-title":"Oral Surg Oral Med Oral Pathol Oral Radiol"},{"issue":"10","key":"1409_CR27","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.3390\/bioengineering11101001","volume":"11","author":"R Jagtap","year":"2024","unstructured":"Jagtap R, Samata Y, Parekh A, Tretto P, Roach MD, Sethumanjusha S, Tejaswi C, Jaju P, Friedel A, Briner Garrido M, et al. Clinical Validation of Deep Learning for Segmentation of Multiple Dental Features in Periapical Radiographs. Bioengineering. 2024;11(10):1001. https:\/\/doi.org\/10.3390\/bioengineering11101001.","journal-title":"Bioengineering"},{"issue":"4","key":"1409_CR28","doi-asserted-by":"publisher","first-page":"322","DOI":"10.5005\/jp-journals-10005-1783","volume":"13","author":"K Sheth","year":"2020","unstructured":"Sheth K, Kapoor S, Daveshwar S. Comparison of cone-beam computed tomography and periapical radiography to determine the proximity of periapical lesions to anatomical structures in the premaxillary area prior to surgical endodontics: a clinical study. Int J Clin Pediatr Dent. 2020;13(4):322.","journal-title":"Int J Clin Pediatr Dent"},{"issue":"5","key":"1409_CR29","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1007\/s10916-022-01807-1","volume":"46","author":"T Roland","year":"2022","unstructured":"Roland T, B\u00f6ck C, Tschoellitsch T, Maletzky A, Hochreiter S, Meier J, Klambauer G. Domain shifts in machine learning based Covid-19 diagnosis from blood tests. J Med Syst. 2022;46(5):23.","journal-title":"J Med Syst"},{"issue":"1","key":"1409_CR30","doi-asserted-by":"publisher","first-page":"21302","DOI":"10.1038\/s41598-022-23990-4","volume":"12","author":"O Kilim","year":"2022","unstructured":"Kilim O, Olar A, Jo\u00f3 T, Palicz T, Pollner P, Csabai I. Physical imaging parameter variation drives domain shift. Sci Rep. 2022;12(1):21302.","journal-title":"Sci Rep"},{"issue":"10","key":"1409_CR31","doi-asserted-by":"publisher","first-page":"1583","DOI":"10.1109\/JPROC.2024.3507831","volume":"112","author":"JS Yoon","year":"2024","unstructured":"Yoon JS, Oh K, Shin Y, Mazurowski MA, Suk HI. Domain generalization for medical image analysis: A review. Proc IEEE. 2024;112(10):1583\u2013609.","journal-title":"Proc IEEE"}],"container-title":["Odontology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10266-026-01409-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10266-026-01409-0","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10266-026-01409-0.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T04:21:52Z","timestamp":1779337312000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10266-026-01409-0"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,21]]},"references-count":31,"alternative-id":["1409"],"URL":"https:\/\/doi.org\/10.1007\/s10266-026-01409-0","relation":{},"ISSN":["1618-1247","1618-1255"],"issn-type":[{"value":"1618-1247","type":"print"},{"value":"1618-1255","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,21]]},"assertion":[{"value":"13 February 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 April 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 May 2026","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 that they have no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This study was approved by the Institutional Ethics Committee of Istanbul Okan University (Approval No: 2024\/175-3).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"The requirement for informed consent was waived due to the retrospective nature of the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}},{"value":"During the preparation of this work, the authors used ChatGPT (OpenAI) to assist with language editing, clarity improvement, and refinement of academic writing. After using this tool, the authors critically reviewed and edited all content and take full responsibility for the accuracy, originality, and integrity of the published article.","order":5,"name":"Ethics","group":{"name":"EthicsHeading","label":"Generative AI and AI-assisted technologies in the manuscript preparation process"}}]}}