{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T18:39:59Z","timestamp":1792435199699,"version":"4.5.0"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T00:00:00Z","timestamp":1792368000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T00:00:00Z","timestamp":1792368000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Clin Oral Invest"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>The growing application of artificial intelligence in dentistry has opened new opportunities for predicting peri-implantitis (PI) using convolutional neural networks (CNNs). Transfer learning, where knowledge from a model pre-trained on a large dataset is adapted to a new, domain-specific task, may enhance performance, particularly when medical datasets are limited. This study evaluated the ability of several pre-trained CNN architectures applied to baseline 2D intraoral radiographs to predict peri-implantitis onset.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>A retrospective multi-center study was conducted at the University of Michigan and King\u2019s College London. A total of 195 implants (146 from Michigan and 49 from London) placed in 108 maintained patients were included. For each implant, a baseline periapical radiograph taken up to one year after prosthetic restoration was analyzed. Five pre-trained CNN architectures (ResNet50, DenseNet, VGG16, InceptionV3, EfficientNet) were combined with four transfer learning strategies: feature extraction (hybrid and non-hybrid), partial fine-tuning (50% of layers), and full fine-tuning. Models were trained using patient-wise splits to avoid leakage, and performance was evaluated on an independent test set using accuracy, area under the ROC curve (AUC), sensitivity, and specificity.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>All CNN architectures showed variable performance across transfer learning strategies. The non-hybrid feature extraction approach provided the most consistent discrimination, with the best models achieving AUC values between 0.74 and 0.83. InceptionV3 reached the highest AUC (0.83). Fine-tuning strategies yielded modest or low performance, with AUCs generally ranging from 0.42 to 0.69 across architectures.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Non-hybrid feature extraction applied to pre-trained CNNs showed the most promising, though moderate, performance for predicting PI onset from baseline intraoral radiographs. These findings indicate that transfer learning may assist early risk stratification in implant dentistry, but larger prospective studies are needed before clinical adoption.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Clinical relevance<\/jats:title>\n                    <jats:p>Deep learning models may serve as adjunctive tools to identify implants at higher risk for future PI based on routine baseline radiographs, supporting more individualized maintenance protocols and earlier preventive interventions.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1007\/s00784-026-07181-3","type":"journal-article","created":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T01:39:56Z","timestamp":1792373996000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Accuracy of transfer learning in predicting peri-implantitis onset from intraoral radiograph: A multi-center longitudinal retrospective study"],"prefix":"10.1007","volume":"30","author":[{"given":"Muhammad H. A.","family":"Saleh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Luigi","family":"Nibali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Abdusalam E.","family":"Alrmali","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vito Carlo Alberto","family":"Caponio","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pasquale","family":"Santamaria","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3756-3580","authenticated-orcid":false,"given":"Francesco","family":"Fanelli","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khrystyna","family":"Zhurakivska","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hom-Lay","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Giuseppe","family":"Troiano","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,10,19]]},"reference":[{"key":"7181_CR1","doi-asserted-by":"publisher","first-page":"1424","DOI":"10.1177\/0022034518792567","volume":"97","author":"HW Elani","year":"2018","unstructured":"Elani HW, Starr JR, Da Silva JD, Gallucci GO (2018) Trends in Dental Implant Use in the U.S., 1999\u20132016, and Projections to 2026. J Dent Res 97:1424\u20131430","journal-title":"J Dent Res"},{"key":"7181_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.jdent.2017.04.011","volume":"62","author":"CT Lee","year":"2017","unstructured":"Lee CT, Huang YW, Zhu L, Weltman R (2017) Prevalences of peri-implantitis and peri-implant mucositis: systematic review and meta-analysis. J Dent 62:1\u201312","journal-title":"J Dent"},{"key":"7181_CR3","doi-asserted-by":"crossref","unstructured":"Sun TC, Chen CJ, Gallucci GO (2023) Prevention and management of peri-implant disease. Clin Implant Dent Relat Res","DOI":"10.1111\/cid.13206"},{"key":"7181_CR4","first-page":"11","volume":"1","author":"T Albrektsson","year":"1986","unstructured":"Albrektsson T, Zarb G, Worthington P, Eriksson AR (1986) The long-term efficacy of currently used dental implants: a review and proposed criteria of success. Int J Oral Maxillofac Implants 1:11\u201325","journal-title":"Int J Oral Maxillofac Implants"},{"issue":"Suppl 20","key":"7181_CR5","first-page":"S286","volume":"45","author":"T Berglundh","year":"2018","unstructured":"Berglundh T, Armitage G, Araujo MG et al (2018) Peri-implant diseases and conditions: Consensus report of workgroup 4 of the 2017 World Workshop on the Classification of Periodontal and Peri-Implant Diseases and Conditions. J Clin Periodontol 45(Suppl 20):S286\u2013S291","journal-title":"J Clin Periodontol"},{"key":"7181_CR6","doi-asserted-by":"publisher","first-page":"935","DOI":"10.21037\/qims-22-457","volume":"13","author":"C Zhang","year":"2023","unstructured":"Zhang C, Fan L, Zhang S, Zhao J, Gu Y (2023) Deep learning based dental implant failure prediction from periapical and panoramic films. Quant Imaging Med Surg 13:935\u2013945","journal-title":"Quant Imaging Med Surg"},{"key":"7181_CR7","doi-asserted-by":"publisher","first-page":"153","DOI":"10.1111\/clr.13551","volume":"31","author":"LFP Nicolielo","year":"2020","unstructured":"Nicolielo LFP, Van Dessel J, Jacobs R, Quirino Silveira Soares M, Collaert B (2020) Relationship between trabecular bone architecture and early dental implant failure in the posterior region of the mandible. Clin Oral Implants Res 31:153\u2013161","journal-title":"Clin Oral Implants Res"},{"key":"7181_CR8","doi-asserted-by":"publisher","first-page":"102444","DOI":"10.1016\/j.media.2022.102444","volume":"79","author":"X Chen","year":"2022","unstructured":"Chen X, Wang X, Zhang K et al (2022) Recent advances and clinical applications of deep learning in medical image analysis. Med Image Anal 79:102444","journal-title":"Med Image Anal"},{"key":"7181_CR9","doi-asserted-by":"publisher","first-page":"4","DOI":"10.1016\/j.media.2016.06.013","volume":"33","author":"WM Wells","year":"2016","unstructured":"Wells WM (2016) 3rd. Medical Image Analysis - past, present, and future. Med Image Anal 33:4\u20136","journal-title":"Med Image Anal"},{"key":"7181_CR10","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1038\/nrclinonc.2017.141","volume":"14","author":"P Lambin","year":"2017","unstructured":"Lambin P, Leijenaar RTH, Deist TM et al (2017) Radiomics: the bridge between medical imaging and personalized medicine. Nat Rev Clin Oncol 14:749\u2013762","journal-title":"Nat Rev Clin Oncol"},{"key":"7181_CR11","doi-asserted-by":"publisher","first-page":"129","DOI":"10.1016\/j.amjmed.2017.10.035","volume":"131","author":"DD Miller","year":"2018","unstructured":"Miller DD, Brown EW (2018) Artificial Intelligence in Medical Practice: The Question to the Answer? Am J Med 131:129\u2013133","journal-title":"Am J Med"},{"key":"7181_CR12","doi-asserted-by":"publisher","first-page":"426","DOI":"10.1002\/med.21846","volume":"42","author":"J Guiot","year":"2022","unstructured":"Guiot J, Vaidyanathan A, Deprez L et al (2022) A review in radiomics: Making personalized medicine a reality via routine imaging. Med Res Rev 42:426\u2013440","journal-title":"Med Res Rev"},{"key":"7181_CR13","doi-asserted-by":"publisher","first-page":"105533","DOI":"10.1016\/j.jdent.2024.105533","volume":"153","author":"M Bonfanti-Gris","year":"2025","unstructured":"Bonfanti-Gris M, Ruales E, Salido MP, Martinez-Rus F, Ozcan M, Pradies G (2025) Artificial intelligence for dental implant classification and peri-implant pathology identification in 2D radiographs: A systematic review. J Dent 153:105533","journal-title":"J Dent"},{"key":"7181_CR14","doi-asserted-by":"publisher","first-page":"1165","DOI":"10.1016\/j.jds.2023.11.017","volume":"19","author":"WF Lee","year":"2024","unstructured":"Lee WF, Day MY, Fang CY et al (2024) Establishing a novel deep learning model for detecting peri-implantitis. J Dent Sci 19:1165\u20131173","journal-title":"J Dent Sci"},{"key":"7181_CR15","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-33128-3_1","volume":"1213","author":"HP Chan","year":"2020","unstructured":"Chan HP, Samala RK, Hadjiiski LM, Zhou C (2020) Deep Learning in Medical Image Analysis. Adv Exp Med Biol 1213:3\u201321","journal-title":"Adv Exp Med Biol"},{"key":"7181_CR16","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1186\/s12880-022-00793-7","volume":"22","author":"HE Kim","year":"2022","unstructured":"Kim HE, Cosa-Linan A, Santhanam N, Jannesari M, Maros ME, Ganslandt T (2022) Transfer learning for medical image classification: a literature review. BMC Med Imaging 22:69","journal-title":"BMC Med Imaging"},{"key":"7181_CR17","doi-asserted-by":"publisher","first-page":"2191","DOI":"10.1001\/jama.2013.281053","volume":"310","author":"A World Medical","year":"2013","unstructured":"World Medical A (2013) World Medical Association Declaration of Helsinki: ethical principles for medical research involving human subjects. JAMA 310:2191\u20132194","journal-title":"JAMA"},{"key":"7181_CR18","doi-asserted-by":"publisher","first-page":"e297","DOI":"10.1371\/journal.pmed.0040297","volume":"4","author":"JP Vandenbroucke","year":"2007","unstructured":"Vandenbroucke JP, von Elm E, Altman DG et al (2007) Strengthening the Reporting of Observational Studies in Epidemiology (STROBE): explanation and elaboration. PLoS Med 4:e297","journal-title":"PLoS Med"},{"issue":"Suppl 1","key":"7181_CR19","first-page":"S173","volume":"89","author":"PN Papapanou","year":"2018","unstructured":"Papapanou PN, Sanz M, Buduneli N et al (2018) Periodontitis: Consensus report of workgroup 2 of the 2017 World Workshop on the Classification of Periodontal and Peri-Implant Diseases and Conditions. J Periodontol 89(Suppl 1):S173\u2013S182","journal-title":"J Periodontol"},{"issue":"Suppl 20","key":"7181_CR20","first-page":"S149","volume":"45","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 Clin Periodontol 45(Suppl 20):S149\u2013S161","journal-title":"J Clin Periodontol"},{"key":"7181_CR21","doi-asserted-by":"crossref","unstructured":"Stahlschmidt SR, Ulfenborg B, Synnergren J (2022) Multimodal deep learning for biomedical data fusion: a review. Brief Bioinform 23","DOI":"10.1093\/bib\/bbab569"},{"key":"7181_CR22","doi-asserted-by":"crossref","unstructured":"Mohammad-Rahimi H, Motamedian SR, Pirayesh Z et al (2022) Deep learning in periodontology and oral implantology: a scoping review. J Periodontal Res","DOI":"10.1111\/jre.13037"},{"key":"7181_CR23","doi-asserted-by":"publisher","first-page":"769","DOI":"10.1177\/0022034520915714","volume":"99","author":"F Schwendicke","year":"2020","unstructured":"Schwendicke F, Samek W, Krois J (2020) Artificial Intelligence in Dentistry: Chances and Challenges. J Dent Res 99:769\u2013774","journal-title":"J Dent Res"},{"key":"7181_CR24","doi-asserted-by":"publisher","first-page":"872","DOI":"10.1111\/jcpe.13689","volume":"49","author":"N Huang","year":"2022","unstructured":"Huang N, Liu P, Yan Y et al (2022) Predicting the risk of dental implant loss using deep learning. J Clin Periodontol 49:872\u2013883","journal-title":"J Clin Periodontol"},{"key":"7181_CR25","first-page":"367","volume":"14","author":"C Garaicoa-Pazmino","year":"2021","unstructured":"Garaicoa-Pazmino C, Lin GH, Alkandery A, Parra-Carrasquer C, Suarez-Lopez Del Amo F (2021) Influence of implant surface characteristics on the initiation, progression and treatment outcomes of peri-implantitis: A systematic review and meta-analysis based on animal model studies. Int J Oral Implantol (Berl) 14:367\u2013382","journal-title":"Int J Oral Implantol (Berl)"},{"key":"7181_CR26","doi-asserted-by":"publisher","first-page":"630","DOI":"10.1111\/cid.13122","volume":"24","author":"P Galindo-Moreno","year":"2022","unstructured":"Galindo-Moreno P, Catena A, Perez-Sayans M, Fernandez-Barbero JE, O\u2019Valle F, Padial-Molina M (2022) Early marginal bone loss around dental implants to define success in implant dentistry: A retrospective study. Clin Implant Dent Relat Res 24:630\u2013642","journal-title":"Clin Implant Dent Relat Res"},{"key":"7181_CR27","doi-asserted-by":"publisher","first-page":"225","DOI":"10.1111\/jcpe.12829","volume":"45","author":"M Katafuchi","year":"2018","unstructured":"Katafuchi M, Weinstein BF, Leroux BG, Chen YW, Daubert DM (2018) Restoration contour is a risk indicator for peri-implantitis: A cross-sectional radiographic analysis. J Clin Periodontol 45:225\u2013232","journal-title":"J Clin Periodontol"},{"key":"7181_CR28","doi-asserted-by":"publisher","first-page":"1273","DOI":"10.1002\/JPER.21-0723","volume":"93","author":"MV Rodriguez","year":"2022","unstructured":"Rodriguez MV, Ravida A, Saleh MHA et al (2022) Is the degree of physiological bone remodeling a predictive factor for peri-implantitis? J Periodontol 93:1273\u20131282","journal-title":"J Periodontol"},{"key":"7181_CR29","first-page":"263","volume":"14","author":"S Barootchi","year":"2021","unstructured":"Barootchi S, Wang HL (2021) Peri-implant diseases: Current understanding and management. Int J Oral Implantol (Berl) 14:263\u2013282","journal-title":"Int J Oral Implantol (Berl)"},{"key":"7181_CR30","doi-asserted-by":"crossref","unstructured":"Mugri MH (2025) Accuracy of artificial intelligence models in detecting peri-implant bone loss: a systematic review. Diagnostics (Basel) 15","DOI":"10.3390\/diagnostics15060655"},{"key":"7181_CR31","doi-asserted-by":"crossref","unstructured":"Troiano G, Fanelli F, Rapani A et al (2023) Can radiomic features extracted from intra-oral radiographs predict physiological bone remodelling around dental implants? A hypothesis-generating study. J Clin Periodontol","DOI":"10.1111\/jcpe.13797"},{"key":"7181_CR32","first-page":"vdac060","volume":"4","author":"E Calabrese","year":"2022","unstructured":"Calabrese E, Rudie JD, Rauschecker AM et al (2022) Combining radiomics and deep convolutional neural network features from preoperative MRI for predicting clinically relevant genetic biomarkers in glioblastoma. Neurooncol Adv 4:vdac060","journal-title":"Neurooncol Adv"},{"key":"7181_CR33","doi-asserted-by":"publisher","first-page":"397","DOI":"10.1111\/clr.13585","volume":"31","author":"LJA Heitz-Mayfield","year":"2020","unstructured":"Heitz-Mayfield LJA, Heitz F, Lang NP (2020) Implant Disease Risk Assessment IDRA-a tool for preventing peri-implant disease. Clin Oral Implants Res 31:397\u2013403","journal-title":"Clin Oral Implants Res"},{"issue":"Suppl 1","key":"7181_CR34","first-page":"S313","volume":"89","author":"T Berglundh","year":"2018","unstructured":"Berglundh T, Armitage G, Araujo MG et al (2018) Peri-implant diseases and conditions: Consensus report of workgroup 4 of the 2017 World Workshop on the Classification of Periodontal and Peri-Implant Diseases and Conditions. J Periodontol 89(Suppl 1):S313\u2013S318","journal-title":"J Periodontol"},{"key":"7181_CR35","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1177\/0022034515608832","volume":"95","author":"J Derks","year":"2016","unstructured":"Derks J, Schaller D, Hakansson J, Wennstrom JL, Tomasi C, Berglundh T (2016) Effectiveness of Implant Therapy Analyzed in a Swedish Population: Prevalence of Peri-implantitis. J Dent Res 95:43\u201349","journal-title":"J Dent Res"},{"key":"7181_CR36","doi-asserted-by":"publisher","first-page":"690","DOI":"10.11607\/jomi.9523","volume":"37","author":"MH Saleh","year":"2022","unstructured":"Saleh MH, Galli M, Siqueira R, Vera M, Wang HL, Ravida A (2022) The Prosthetic-Biologic Connection and Its Influence on Peri-implant Health: An Overview of the Current Evidence. Int J Oral Maxillofac Implants 37:690\u2013699","journal-title":"Int J Oral Maxillofac Implants"},{"key":"7181_CR37","doi-asserted-by":"publisher","first-page":"661","DOI":"10.1111\/cid.13156","volume":"25","author":"ME Galarraga-Vinueza","year":"2023","unstructured":"Galarraga-Vinueza ME, Tavelli L (2023) Soft tissue features of peri-implant diseases and related treatment. Clin Implant Dent Relat Res 25:661\u2013681","journal-title":"Clin Implant Dent Relat Res"}],"container-title":["Clinical Oral Investigations"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00784-026-07181-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00784-026-07181-3","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00784-026-07181-3.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,10,19]],"date-time":"2026-10-19T18:02:33Z","timestamp":1792432953000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00784-026-07181-3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10,19]]},"references-count":37,"journal-issue":{"issue":"11","published-online":{"date-parts":[[2026,11]]}},"alternative-id":["7181"],"URL":"https:\/\/doi.org\/10.1007\/s00784-026-07181-3","relation":{},"ISSN":["1436-3771"],"issn-type":[{"value":"1436-3771","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,10,19]]},"assertion":[{"value":"4 August 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 October 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This retrospective study was conducted at the Department of Periodontics and Oral Medicine, University of Michigan, Ann Arbor, and the Faculty of Dentistry, Oral and Craniofacial Sciences, King\u2019s College London. Ethical approval was obtained from both institutions: the University of Michigan Institutional Review Board (registration number: IRB00001999) and the London City & East NHS Research Ethics Committee for data collected from London practices as part of a service evaluation (reference 14 LO 0629, Nibali et al., 2017). The research complied with the ethical principles outlined in the Helsinki Declaration as revised in 2013. The need for participant consent was waived by the respective committees due to the retrospective design and use of de-identified data.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable.","order":2,"name":"Ethics","label":"Consent for publication","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no competing interests.","order":3,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"537"}}