{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T19:55:23Z","timestamp":1775073323958,"version":"3.50.1"},"reference-count":28,"publisher":"Springer Science and Business Media LLC","issue":"7","license":[{"start":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T00:00:00Z","timestamp":1624233600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T00:00:00Z","timestamp":1624233600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council","doi-asserted-by":"publisher","award":["EP\/P012841\/1"],"award-info":[{"award-number":["EP\/P012841\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Royal Academy of Engineering Chair in Emerging Technologies","award":["CiET1819\/2\/36"],"award-info":[{"award-number":["CiET1819\/2\/36"]}]},{"DOI":"10.13039\/100017149","name":"DeepMind","doi-asserted-by":"crossref","award":["Scholarship"],"award-info":[{"award-number":["Scholarship"]}],"id":[{"id":"10.13039\/100017149","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/100004440","name":"Wellcome Trust","doi-asserted-by":"publisher","award":["WT101957"],"award-info":[{"award-number":["WT101957"]}],"id":[{"id":"10.13039\/100004440","id-type":"DOI","asserted-by":"publisher"}]},{"name":"UK Department of Health\u2019s National Institute for Health Research"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J CARS"],"published-print":{"date-parts":[[2021,7]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>Periodontitis is the sixth most prevalent disease worldwide and periodontal bone loss (PBL) detection is crucial for its early recognition and establishment of the correct diagnosis and prognosis. Current radiographic assessment by clinicians exhibits substantial interobserver variation. Computer-assisted radiographic assessment can calculate bone loss objectively and aid in early bone loss detection. Understanding the rate of disease progression can guide the choice of treatment and lead to early initiation of periodontal therapy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Methodology<\/jats:title><jats:p>We propose an end-to-end system that includes a deep neural network with hourglass architecture to predict dental landmarks in single, double and triple rooted teeth using periapical radiographs. We then estimate the PBL and disease severity stage using the predicted landmarks. We also introduce a novel adaptation of MixUp data augmentation that improves the landmark localisation.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>We evaluate the proposed system using cross-validation on 340 radiographs from 63 patient cases containing 463, 115 and 56 single, double and triple rooted teeth. The landmark localisation achieved Percentage Correct Keypoints (PCK) of 88.9%, 73.9% and 74.4%, respectively, and a combined PCK of 83.3% across all root morphologies, outperforming the next best architecture by 1.7%. When compared to clinicians\u2019 visual evaluations of full radiographs, the average PBL error was 10.69%, with a severity stage accuracy of 58%. This simulates current interobserver variation, implying that diverse data could improve accuracy.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>The system showed a promising capability to localise landmarks and estimate periodontal bone loss on periapical radiographs. An agreement was found with other literature that non-CEJ (Cemento-Enamel Junction) landmarks are the hardest to localise. Honing the system\u2019s clinical pipeline will allow for its use in intervention applications.<\/jats:p><\/jats:sec>","DOI":"10.1007\/s11548-021-02431-z","type":"journal-article","created":{"date-parts":[[2021,6,21]],"date-time":"2021-06-21T11:03:36Z","timestamp":1624273416000},"page":"1189-1199","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":60,"title":["Automating Periodontal bone loss measurement via dental landmark localisation"],"prefix":"10.1007","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9999-7917","authenticated-orcid":false,"given":"Raymond P.","family":"Danks","sequence":"first","affiliation":[]},{"given":"Sophia","family":"Bano","sequence":"additional","affiliation":[]},{"given":"Anastasiya","family":"Orishko","sequence":"additional","affiliation":[]},{"given":"Hong Jin","family":"Tan","sequence":"additional","affiliation":[]},{"given":"Federico","family":"Moreno Sancho","sequence":"additional","affiliation":[]},{"given":"Francesco","family":"D\u2019Aiuto","sequence":"additional","affiliation":[]},{"given":"Danail","family":"Stoyanov","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,6,21]]},"reference":[{"issue":"5","key":"2431_CR1","doi-asserted-by":"publisher","first-page":"326","DOI":"10.1111\/j.1600-051X.1992.tb00654.x","volume":"19","author":"L \u00c5kesson","year":"1992","unstructured":"\u00c5kesson L, H\u00e5kansson J, Rohlin M (1992) Comparison of panoramic and intraoral radiography and pocket probing for the measurement of the marginal bone level. J Clin Periodontol 19(5):326\u2013332","journal-title":"J Clin Periodontol"},{"key":"2431_CR2","doi-asserted-by":"crossref","unstructured":"Andriluka M, Pishchulin L, Gehler P, Schiele B (2014) 2D human pose estimation: new benchmark and state of the art analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 3686\u20133693","DOI":"10.1109\/CVPR.2014.471"},{"key":"2431_CR3","doi-asserted-by":"publisher","first-page":"343","DOI":"10.1109\/TPAMI.2018.2866051","volume":"42","author":"A Bulat","year":"2018","unstructured":"Bulat A, Tzimiropoulos Y (2018) Hierarchical binary CNNs for landmark localization with limited resources. IEEE Trans Pattern Anal Mach Intell 42:343","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"issue":"1","key":"2431_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-56847-4","volume":"10","author":"HJ Chang","year":"2020","unstructured":"Chang HJ, Lee SJ, Yong TH, Shin NY, Jang BG, Kim JE, Huh KH, Lee SS, Heo MS, Choi SC, Kim TI, Yi WJ (2020) Deep learning hybrid method to automatically diagnose periodontal bone loss and stage periodontitis. Sci Rep 10(1):1\u20138","journal-title":"Sci Rep"},{"issue":"3","key":"2431_CR5","doi-asserted-by":"publisher","first-page":"216","DOI":"10.1007\/s10791-009-9110-3","volume":"13","author":"O Chapelle","year":"2010","unstructured":"Chapelle O, Wu M (2010) Gradient descent optimization of smoothed information retrieval metrics. Inf Retr 13(3):216\u2013235","journal-title":"Inf Retr"},{"key":"2431_CR6","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-018-37186-2","volume":"9","author":"H Chen","year":"2019","unstructured":"Chen H, Zhang K, Lyu P, Li H, Zhang L, Wu J, Lee CH (2019) A deep learning approach to automatic teeth detection and numbering based on object detection in dental periapical films. Sci Rep 9:1\u201311","journal-title":"Sci Rep"},{"issue":"2","key":"2431_CR7","doi-asserted-by":"publisher","first-page":"79","DOI":"10.5624\/isd.2018.48.2.79","volume":"48","author":"IGG Choi","year":"2018","unstructured":"Choi IGG, Cortes ARG, Arita ES, Georgetti MAP (2018) Comparison of conventional imaging techniques and CBCT for periodontal evaluation: a systematic review. Imaging Sci Dent 48(2):79\u201386","journal-title":"Imaging Sci Dent"},{"issue":"1","key":"2431_CR8","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1038\/sj.bdj.2019.3","volume":"226","author":"T Dietrich","year":"2019","unstructured":"Dietrich T, Ower P, Tank M, West NX, Walter C, Needleman I, Hughes FJ, Wadia R, Milward MR, Hodge PJ, Chapple ILC (2019) Periodontal diagnosis in the context of the 2017 classification system of periodontal diseases and conditions - implementation in clinical practice. Br Dent J 226(1):16\u201322","journal-title":"Br Dent J"},{"key":"2431_CR9","doi-asserted-by":"crossref","unstructured":"Dutta A, Zisserman A. (2019) The via annotation software for images, audio and video. In: Proceedings of the 27th ACM international conference on multimedia, pp. 2276\u20132279","DOI":"10.1145\/3343031.3350535"},{"key":"2431_CR10","doi-asserted-by":"crossref","unstructured":"Feng ZH, Kittler J, Awais M, Huber P, Wu XJ (2018) Wing loss for robust facial landmark localisation with convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","DOI":"10.1109\/CVPR.2018.00238"},{"key":"2431_CR11","unstructured":"Jaderberg M, Simonyan K, Zisserman A, Kavukcuoglu K (2015) Spatial transformer networks. In: Cortes C, Lawrence N, Lee D, Sugiyama M, Garnett R (eds) Advances in neural information processing systems, vol 28. Curran Associates, Inc. https:\/\/proceedings.neurips.cc\/paper\/2015\/file\/33ceb07bf4eeb3da587e268d663aba1a-Paper.pdf"},{"issue":"3","key":"2431_CR12","doi-asserted-by":"publisher","first-page":"170","DOI":"10.1111\/j.1600-051X.1988.tb01564.x","volume":"15","author":"JT Kaimenyi","year":"1988","unstructured":"Kaimenyi JT, Ashley FP (1988) Assessment of bone loss in periodontitis from panoramic radiographs. J Clin Periodontol 15(3):170\u2013174","journal-title":"J Clin Periodontol"},{"issue":"11","key":"2431_CR13","doi-asserted-by":"publisher","first-page":"1045","DOI":"10.1177\/0022034514552491","volume":"93","author":"N Kassebaum","year":"2014","unstructured":"Kassebaum N, Bernab\u00e9 E, Dahiya M, Bhandari B, Murray C, Marcenes W (2014) Global burden of severe periodontitis in 1990\u20132010: a systematic review and meta-regression. J Dent Res 93(11):1045\u20131053","journal-title":"J Dent Res"},{"issue":"6","key":"2431_CR14","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, Muhammad A, Khurram SA (2021) Automated feature detection in dental periapical radiographs by using deep learning. Oral Surg Oral Med Oral Pathol Oral Radiol 131(6):711\u2013720. https:\/\/doi.org\/10.1016\/j.oooo.2020.08.024","journal-title":"Oral Surg Oral Med Oral Pathol Oral Radiol"},{"key":"2431_CR15","unstructured":"Kingma D, Ba J (2014) Adam: a method for stochastic optimization. In: International conference on learning representations"},{"issue":"1","key":"2431_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s41598-019-44839-3","volume":"9","author":"J Krois","year":"2019","unstructured":"Krois J, Ekert T, Meinhold L, Golla T, Kharbot B, Wittemeier A, D\u00f6rfer C, Schwendicke F (2019) Deep learning for the radiographic detection of periodontal bone loss. Sci Rep 9(1):1\u20136","journal-title":"Sci Rep"},{"key":"2431_CR17","doi-asserted-by":"crossref","unstructured":"Lee JH, Zaigham\u00a0Zaheer M, Astrid M, Lee SI (2020) SmoothMix: a simple yet effective data augmentation to train robust classifiers. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition workshops, pp. 756\u2013757","DOI":"10.1109\/CVPRW50498.2020.00386"},{"key":"2431_CR18","doi-asserted-by":"publisher","first-page":"58774","DOI":"10.1109\/ACCESS.2018.2872698","volume":"6","author":"D Liang","year":"2018","unstructured":"Liang D, Yang F, Zhang T, Yang P (2018) Understanding mixup training methods. IEEEIEEEIEEE Access 6:58774\u201358783","journal-title":"IEEEIEEEIEEE Access"},{"key":"2431_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.cmpb.2017.06.012","volume":"148","author":"P Lin","year":"2017","unstructured":"Lin P, Huang P, Huang P (2017) Automatic methods for alveolar bone loss degree measurement in periodontitis periapical radiographs. Comp Methods Progr Biomed 148:1\u201311","journal-title":"Comp Methods Progr Biomed"},{"key":"2431_CR20","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1111\/jcpe.13406","volume":"48","author":"L Marini","year":"2020","unstructured":"Marini L, Tonetti MS, Nibali L, Rojas MA, Aimetti M, Cairo F, Cavalcanti R, Crea A, Ferrarotti F, Graziani F, Landi L, Sforza NM, Tomasi C, Pilloni A (2020) The staging and grading system in defining periodontitis cases: consistency and accuracy amongst periodontal experts, general dentists and undergraduate students. J Clin Periodontol 48:205","journal-title":"J Clin Periodontol"},{"key":"2431_CR21","doi-asserted-by":"crossref","unstructured":"Newell A, Yang K, Deng J (2016) Stacked hourglass networks for human pose estimation. In: European conference on computer vision. Springer, pp. 483\u2013499","DOI":"10.1007\/978-3-319-46484-8_29"},{"issue":"1","key":"2431_CR22","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1111\/prd.12200","volume":"75","author":"PN Papapanou","year":"2017","unstructured":"Papapanou PN, Susin C (2017) Periodontitis epidemiology: is periodontitis under-recognized, over-diagnosed, or both? Periodontology 75(1):45\u201351","journal-title":"Periodontology"},{"issue":"3","key":"2431_CR23","doi-asserted-by":"publisher","first-page":"272","DOI":"10.1046\/j.1365-2591.1999.00304.x","volume":"33","author":"M Saunders","year":"2000","unstructured":"Saunders M, Gulabivala K, Holt R, Kahan R (2000) Reliability of radiographic observations recorded on a proforma measured using inter-and intra-observer variation: a preliminary study. Int Endod J 33(3):272\u2013278","journal-title":"Int Endod J"},{"key":"2431_CR24","doi-asserted-by":"crossref","unstructured":"Tiulpin A, Melekhov I, Saarakkala S (2019) KNEEL: Knee anatomical landmark localization using hourglass networks. In: 2019 IEEE\/CVF International Conference on Computer Vision Workshop (ICCVW), pp. 352\u2013361","DOI":"10.1109\/ICCVW.2019.00046"},{"key":"2431_CR25","doi-asserted-by":"publisher","first-page":"S159","DOI":"10.1002\/JPER.18-0006","volume":"89","author":"MS Tonetti","year":"2018","unstructured":"Tonetti MS, Greenwell H, Kornman KS (2018) Staging and grading of periodontitis: framework and proposal of a new classification and case definition. J Periodontol 89:S159\u2013S172","journal-title":"J Periodontol"},{"issue":"5","key":"2431_CR26","doi-asserted-by":"publisher","first-page":"456","DOI":"10.1111\/jcpe.12732","volume":"44","author":"MS Tonetti","year":"2017","unstructured":"Tonetti MS, Jepsen S, Jin L, Otomo-Corgel J (2017) Impact of the global burden of periodontal diseases on health, nutrition and wellbeing of mankind: A call for global action. J Clin Periodontol 44(5):456\u2013462","journal-title":"J Clin Periodontol"},{"key":"2431_CR27","doi-asserted-by":"crossref","unstructured":"Yun S, Han D, Oh SJ, Chun S, Choe J, Yoo Y (2019) CutMix: regularization strategy to train strong classifiers with localizable features. In: Proceedings of the IEEE international conference on computer vision, pp. 6023\u20136032","DOI":"10.1109\/ICCV.2019.00612"},{"key":"2431_CR28","unstructured":"Zhang H, Cisse M, Dauphin YN, Lopez-Paz D (2018) MixUp: beyond empirical risk minimization. In: International conference on learning representations"}],"container-title":["International Journal of Computer Assisted Radiology and Surgery"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-021-02431-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11548-021-02431-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11548-021-02431-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,31]],"date-time":"2022-12-31T23:32:19Z","timestamp":1672529539000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11548-021-02431-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6,21]]},"references-count":28,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2021,7]]}},"alternative-id":["2431"],"URL":"https:\/\/doi.org\/10.1007\/s11548-021-02431-z","relation":{},"ISSN":["1861-6410","1861-6429"],"issn-type":[{"value":"1861-6410","type":"print"},{"value":"1861-6429","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,6,21]]},"assertion":[{"value":"23 March 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"7 June 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 June 2021","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 conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}},{"value":"This research study was conducted retrospectively from data obtained for clinical purposes. Ethical approval was obtained from the UCL Research Ethics Committee (Ethics approval number:19419\/001).","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"No animals or humans were involved in this research. All radiographs were fully anonymised before delivery to the researchers.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}