{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,1]],"date-time":"2026-07-01T20:37:04Z","timestamp":1782938224283,"version":"3.54.5"},"reference-count":39,"publisher":"Wiley","issue":"7","license":[{"start":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T00:00:00Z","timestamp":1712102400000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"funder":[{"DOI":"10.13039\/100019702","name":"Tokyo Metropolitan Government","doi-asserted-by":"publisher","award":["2023\u20132025"],"award-info":[{"award-number":["2023\u20132025"]}],"id":[{"id":"10.13039\/100019702","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Prosthodontics"],"published-print":{"date-parts":[[2024,8]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:sec><jats:title>Purpose<\/jats:title><jats:p>The study aimed to compare the performance of four pre\u2010trained convolutional neural networks in recognizing seven distinct prosthodontic scenarios involving the maxilla, as a preliminary step in developing an artificial intelligence (AI)\u2010powered prosthesis design system.<\/jats:p><\/jats:sec><jats:sec><jats:title>Materials and methods<\/jats:title><jats:p>Seven distinct classes, including cleft palate, dentulous maxillectomy, edentulous maxillectomy, reconstructed maxillectomy, completely dentulous, partially edentulous, and completely edentulous, were considered for recognition. Utilizing transfer learning and fine\u2010tuned hyperparameters, four AI models (VGG16, Inception\u2010ResNet\u2010V2, DenseNet\u2010201, and Xception) were employed. The dataset, consisting of 3541 preprocessed intraoral occlusal images, was divided into training, validation, and test sets. Model performance metrics encompassed accuracy, precision, recall, F1 score, area under the receiver operating characteristic curve (AUC), and confusion matrix.<\/jats:p><\/jats:sec><jats:sec><jats:title>Results<\/jats:title><jats:p>VGG16, Inception\u2010ResNet\u2010V2, DenseNet\u2010201, and Xception demonstrated comparable performance, with maximum test accuracies of 0.92, 0.90, 0.94, and 0.95, respectively. Xception and DenseNet\u2010201 slightly outperformed the other models, particularly compared with InceptionResNet\u2010V2. Precision, recall, and F1 scores exceeded 90% for most classes in Xception and DenseNet\u2010201 and the average AUC values for all models ranged between 0.98 and 1.00.<\/jats:p><\/jats:sec><jats:sec><jats:title>Conclusions<\/jats:title><jats:p>While DenseNet\u2010201 and Xception demonstrated superior performance, all models consistently achieved diagnostic accuracy exceeding 90%, highlighting their potential in dental image analysis. This AI application could help work assignments based on difficulty levels and enable the development of an automated diagnosis system at patient admission. It also facilitates prosthesis designing by integrating necessary prosthesis morphology, oral function, and treatment difficulty. Furthermore, it tackles dataset size challenges in model optimization, providing valuable insights for future research.<\/jats:p><\/jats:sec>","DOI":"10.1111\/jopr.13853","type":"journal-article","created":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T07:08:50Z","timestamp":1712128130000},"page":"645-654","update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["Advancing maxillofacial prosthodontics by using pre\u2010trained convolutional neural networks: Image\u2010based classification of the maxilla"],"prefix":"10.1111","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5247-1769","authenticated-orcid":false,"given":"Islam E.","family":"Ali","sequence":"first","affiliation":[{"name":"Department of Advanced Prosthodontics Graduate School of Medical and Dental Sciences Tokyo Medical and Dental University  Tokyo Japan"},{"name":"Department of Prosthodontics Faculty of Dentistry Mansoura University  Mansoura Egypt"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3982-8369","authenticated-orcid":false,"given":"Yuka","family":"Sumita","sequence":"additional","affiliation":[{"name":"Division of General Dentistry 4 The Nippon Dental University Hospital  Tokyo Japan"},{"name":"Graduate School of Medical and Dental Sciences Tokyo Medical and Dental University  Tokyo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0517-6756","authenticated-orcid":false,"given":"Noriyuki","family":"Wakabayashi","sequence":"additional","affiliation":[{"name":"Department of Advanced Prosthodontics Graduate School of Medical and Dental Sciences Tokyo Medical and Dental University  Tokyo Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2024,4,3]]},"reference":[{"key":"e_1_2_8_2_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2017.07.005"},{"key":"e_1_2_8_3_1","doi-asserted-by":"publisher","DOI":"10.2186\/jpr.JPOR_2019_354"},{"key":"e_1_2_8_4_1","doi-asserted-by":"publisher","DOI":"10.1097\/MD.0000000000020787"},{"key":"e_1_2_8_5_1","doi-asserted-by":"publisher","DOI":"10.1177\/0022034520969115"},{"key":"e_1_2_8_6_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.zemedi.2018.11.002"},{"issue":"6","key":"e_1_2_8_7_1","first-page":"23","article-title":"Convolutional neural network model in machine learning methods and computer vision for image recognition: a review","volume":"14","author":"Jaapar R","year":"2018","journal-title":"J Appl Sci Res"},{"issue":"19","key":"e_1_2_8_8_1","first-page":"6628","article-title":"The use and performance of artificial intelligence in prosthodontics","volume":"21","author":"Bernauer SA","year":"2021","journal-title":"A Syst Rev Sensors"},{"key":"e_1_2_8_9_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.prosdent.2021.06.001"},{"key":"e_1_2_8_10_1","doi-asserted-by":"publisher","DOI":"10.1038\/srep39364"},{"key":"e_1_2_8_11_1","doi-asserted-by":"publisher","DOI":"10.2334\/josnusd.19-0138"},{"key":"e_1_2_8_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3059785"},{"key":"e_1_2_8_13_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpor.2019.08.006"},{"key":"e_1_2_8_14_1","doi-asserted-by":"publisher","DOI":"10.4103\/jips.jips_149_22"},{"key":"e_1_2_8_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2019.2934907"},{"key":"e_1_2_8_16_1","doi-asserted-by":"publisher","DOI":"10.1515\/cdbme-2016-0152"},{"key":"e_1_2_8_17_1","doi-asserted-by":"publisher","DOI":"10.1515\/bmt-2016-0035"},{"key":"e_1_2_8_18_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-018-29959-6"},{"key":"e_1_2_8_19_1","doi-asserted-by":"publisher","DOI":"10.3390\/jcm9020392"},{"key":"e_1_2_8_20_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2020.104115"},{"key":"e_1_2_8_21_1","doi-asserted-by":"publisher","DOI":"10.1111\/odi.13735"},{"key":"e_1_2_8_22_1","doi-asserted-by":"crossref","unstructured":"HeK ZhangX RenS SunJDeep residual learning for image recognition. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2016. p.770\u2013778.","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_2_8_23_1","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"e_1_2_8_24_1","unstructured":"SimonyanK ZissermanA.Very deep convolutional networks for large\u2010scale image recognition. In:Proceedings of the International Conference on Learning Representations.2015.https:\/\/doi.org\/10.48550\/arXiv.1409.1556"},{"key":"e_1_2_8_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2528162"},{"key":"e_1_2_8_26_1","doi-asserted-by":"crossref","unstructured":"SzegedyC IoffeS VanhouckeV AlemiA.Inception\u2010v4 inception\u2010resnet and the impact of residual connections on learning. In:Proceedings of the AAAI conference on artificial intelligence.2017.4278\u20134284.","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"e_1_2_8_27_1","doi-asserted-by":"crossref","unstructured":"HuangG LiuZ Van Der MaatenL WeinbergerKQ et\u00a0al.Densely connected convolutional networks. In:Proceedings of the IEEE conference on computer vision and pattern recognition.2017. p.4700\u20134708.","DOI":"10.1109\/CVPR.2017.243"},{"key":"e_1_2_8_28_1","doi-asserted-by":"crossref","unstructured":"CholletF.Xception: deep learning with depthwise separable convolutions. In:Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition.2017. p.1251\u20131258.","DOI":"10.1109\/CVPR.2017.195"},{"key":"e_1_2_8_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"issue":"1","key":"e_1_2_8_30_1","article-title":"The ethical adoption of artificial intelligence in radiology","volume":"2","author":"Mudgal KS","year":"2020","journal-title":"BJR| Open"},{"key":"e_1_2_8_31_1","doi-asserted-by":"publisher","DOI":"10.1056\/NEJM200408053510621"},{"key":"e_1_2_8_32_1","doi-asserted-by":"publisher","DOI":"10.1136\/jme.28.5.313"},{"key":"e_1_2_8_33_1","doi-asserted-by":"publisher","DOI":"10.1186\/1471-2288-11-40"},{"key":"e_1_2_8_34_1","doi-asserted-by":"publisher","DOI":"10.1002\/cre2.708"},{"key":"e_1_2_8_35_1","doi-asserted-by":"publisher","DOI":"10.1002\/ima.22812"},{"key":"e_1_2_8_36_1","doi-asserted-by":"publisher","DOI":"10.1067\/mpr.2001.121618"},{"key":"e_1_2_8_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jpor.2017.12.002"},{"key":"e_1_2_8_38_1","doi-asserted-by":"publisher","DOI":"10.1093\/jjco\/hyv088"},{"key":"e_1_2_8_39_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdsr.2021.11.005"},{"key":"e_1_2_8_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jdsr.2022.02.001"}],"container-title":["Journal of Prosthodontics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/jopr.13853","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,9]],"date-time":"2024-08-09T09:24:49Z","timestamp":1723195489000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/jopr.13853"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,3]]},"references-count":39,"journal-issue":{"issue":"7","published-print":{"date-parts":[[2024,8]]}},"alternative-id":["10.1111\/jopr.13853"],"URL":"https:\/\/doi.org\/10.1111\/jopr.13853","archive":["Portico"],"relation":{},"ISSN":["1059-941X","1532-849X"],"issn-type":[{"value":"1059-941X","type":"print"},{"value":"1532-849X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,3]]},"assertion":[{"value":"2023-11-21","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-03-15","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-04-03","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}