{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T14:59:19Z","timestamp":1786978759666,"version":"build-2736575974"},"reference-count":25,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,6,11]],"date-time":"2026-06-11T00:00:00Z","timestamp":1781136000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T00:00:00Z","timestamp":1786924800000},"content-version":"vor","delay-in-days":67,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Vellore Institute of Technology- AP University"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["BMC Oral Health"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Early identification of dental caries on Intraoral Periapical Radiographs is clinically important, yet automated detectors often show unstable performance across datasets due to subtle lesion appearance and limited generalization.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>We propose an attention-augmented YOLOv8s detector that inserts two Multi-Head Self-Attention (MHSA) blocks in the deeper backbone and couples this architecture with a compact Genetic Algorithm (GA)\u2013based schedule search to stabilize optimization. Experiments were conducted on a curated dataset collected at Sibar Institute of Dental Sciences, Guntur (1,887 radiographs), standardized and quality screened, and split into 80% for training, 10% for validation, and 10% for testing.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Using identical augmentations and a fixed inference operating point, the proposed YOLOv8s+MHSA+GA achieves Precision 0.98, Recall 0.94, F1 Score 0.96, mAP@0.5 0.97, and mAP@0.5:0.95 0.94. Relative to the next-best baseline (per metric), this corresponds to +0.21 mAP@0.5 (0.97 vs 0.76), +0.61 mAP@0.5:0.95 (0.94 vs 0.33), and +0.26 Recall (0.94 vs 0.68). We further report Wilson 95% confidence intervals for precision and recall to quantify statistical uncertainty.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>These results indicate that deeper-stage self-attention, paired with principled schedule selection, delivers clinically meaningful gains in sensitivity and localization tightness while preserving the efficiency advantages of a one-stage detector, supporting routine AI-assisted diagnosis.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1186\/s12903-026-08806-5","type":"journal-article","created":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T23:24:46Z","timestamp":1781133886000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing YOLOv8s with MHSA and GA for robust caries detection on periapical radiographs"],"prefix":"10.1186","volume":"26","author":[{"given":"D","family":"Meghana","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"A","family":"Manimaran","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,6,11]]},"reference":[{"issue":"1","key":"8806_CR1","doi-asserted-by":"publisher","first-page":"715","DOI":"10.1186\/s12903-025-06086-z","volume":"25","author":"Z Li","year":"2025","unstructured":"Li Z, Yu C, Chen H. Global, regional, and national caries of permanent teeth incidence, prevalence, and disability-adjusted life years, 1990\u20132021: analysis for the global burden of disease study. BMC Oral Health. 2025;25(1):715.","journal-title":"BMC Oral Health"},{"key":"8806_CR2","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1016\/j.media.2017.07.005","volume":"42","author":"G Litjens","year":"2017","unstructured":"Litjens G, Kooi T, Bejnordi BE, Setio AAA, Ciompi F, Ghafoorian M, et al. A survey on deep learning in medical image analysis. Med Image Anal. 2017;42:60\u201388.","journal-title":"Med Image Anal"},{"issue":"7639","key":"8806_CR3","doi-asserted-by":"publisher","first-page":"115","DOI":"10.1038\/nature21056","volume":"542","author":"A Esteva","year":"2017","unstructured":"Esteva A, Kuprel B, Novoa RA, Ko J, Swetter SM, Blau HM. Dermatologist-level classification of skin cancer with deep neural networks. Nature. 2017;542(7639):115\u20138.","journal-title":"Nature"},{"issue":"7","key":"8806_CR4","doi-asserted-by":"publisher","first-page":"949","DOI":"10.1111\/iej.13128","volume":"52","author":"L Bj\u00f8rndal","year":"2019","unstructured":"Bj\u00f8rndal L, Simon S, Tomson P, Duncan H. Management of deep caries and the exposed pulp. Int Endod J. 2019;52(7):949\u201373.","journal-title":"Int Endod J"},{"key":"8806_CR5","doi-asserted-by":"publisher","first-page":"104115","DOI":"10.1016\/j.jdent.2022.104115","volume":"122","author":"H Mohammad-Rahimi","year":"2022","unstructured":"Mohammad-Rahimi H, Motamedian SR, Rohban MH, Krois J, Uribe SE, Mahmoudinia E, et al. Deep learning for caries detection: a systematic review. J Dent. 2022;122:104115.","journal-title":"J Dent"},{"issue":"1","key":"8806_CR6","doi-asserted-by":"publisher","first-page":"4641","DOI":"10.1038\/s41598-024-84737-x","volume":"15","author":"M Bayati","year":"2025","unstructured":"Bayati M, Alizadeh Savareh B, Ahmadinejad H, Mosavat F. Advanced AI-driven detection of interproximal caries in bitewing radiographs using YOLOv8. Sci Rep. 2025;15(1):4641.","journal-title":"Sci Rep"},{"key":"8806_CR7","doi-asserted-by":"crossref","unstructured":"Ayhan B, Ayan E, Karada\u011f G, Bayraktar Y. Evaluation of Caries Detection on Bitewing Radiographs: A Comparative Analysis of the Improved Deep Learning Model and Dentist Performance. J Esthet Restor Dent. 2025;37(7):1949\u201361.","DOI":"10.1111\/jerd.13470"},{"issue":"1","key":"8806_CR8","doi-asserted-by":"publisher","first-page":"25193","DOI":"10.1038\/s41598-024-73297-9","volume":"14","author":"YM Alsakar","year":"2024","unstructured":"Alsakar YM, Elazab N, Nader N, Mohamed W, Ezzat M, Elmogy M. Multi-label dental disorder diagnosis based on MobileNetV2 and swin transformer using bagging ensemble classifier. Sci Rep. 2024;14(1):25193.","journal-title":"Sci Rep"},{"key":"8806_CR9","doi-asserted-by":"crossref","unstructured":"Singh SB, Laishram A, Thongam K, Singh KM. Automatic Detection and Classification of Dental Anomalies and Tooth types using Transformer-based Yolo with GA Optimization. IEEE Access. 2025;13:59326\u201338.","DOI":"10.1109\/ACCESS.2025.3556523"},{"issue":"12","key":"8806_CR10","doi-asserted-by":"publisher","first-page":"7463","DOI":"10.1007\/s00784-023-05335-1","volume":"27","author":"L Kunt","year":"2023","unstructured":"Kunt L, Kybic J, Nagyov\u00e1 V, Tich\u1ef3 A. Automatic caries detection in bitewing radiographs: part I\u2013deep learning. Clin Oral Invest. 2023;27(12):7463\u201371.","journal-title":"Clin Oral Invest"},{"issue":"2","key":"8806_CR11","doi-asserted-by":"publisher","first-page":"133","DOI":"10.1007\/s00784-024-05528-2","volume":"28","author":"A Tich\u1ef3","year":"2024","unstructured":"Tich\u1ef3 A, Kunt L, Nagyov\u00e1 V, Kybic J. Automatic caries detection in bitewing radiographs\u2013Part II: experimental comparison. Clin Oral Invest. 2024;28(2):133.","journal-title":"Clin Oral Invest"},{"key":"8806_CR12","doi-asserted-by":"crossref","unstructured":"P\u00e9rez\u00a0de\u00a0Frutos J, Holden\u00a0Helland R, Desai S, Nymoen LC, Lang\u00f8 T, Remman T, et al. AI-Dentify: deep learning for proximal caries detection on bitewing x-ray-HUNT4 Oral Health Study. BMC Oral Health. 2024;24(1):334.","DOI":"10.1186\/s12903-024-04120-0"},{"issue":"2","key":"8806_CR13","doi-asserted-by":"publisher","first-page":"262","DOI":"10.1016\/j.oooo.2022.03.008","volume":"134","author":"M Estai","year":"2022","unstructured":"Estai M, Tennant M, Gebauer D, Brostek A, Vignarajan J, Mehdizadeh M, et al. Evaluation of a deep learning system for automatic detection of proximal surface dental caries on bitewing radiographs. Oral Surg Oral Med Oral Pathol Oral Radiol. 2022;134(2):262\u201370.","journal-title":"Oral Surg Oral Med Oral Pathol Oral Radiol"},{"issue":"1","key":"8806_CR14","doi-asserted-by":"publisher","first-page":"16807","DOI":"10.1038\/s41598-021-96368-7","volume":"11","author":"S Lee","year":"2021","unstructured":"Lee S, Oh SI, Jo J, Kang S, Shin Y, Park JW. Deep learning for early dental caries detection in bitewing radiographs. Sci Rep. 2021;11(1):16807.","journal-title":"Sci Rep"},{"key":"8806_CR15","doi-asserted-by":"publisher","first-page":"104886","DOI":"10.1016\/j.jdent.2024.104886","volume":"143","author":"ET Chaves","year":"2024","unstructured":"Chaves ET, Vinayahalingam S, van Nistelrooij N, Xi T, Romero VHD, Fl\u00fcgge T, et al. Detection of caries around restorations on bitewings using deep learning. J Dent. 2024;143:104886.","journal-title":"J Dent"},{"issue":"3","key":"8806_CR16","doi-asserted-by":"publisher","first-page":"163","DOI":"10.1159\/000542289","volume":"59","author":"N Van Nistelrooij","year":"2025","unstructured":"Van Nistelrooij N, Chaves ET, Cenci MS, Cao L, Loomans BA, Xi T, et al. Deep learning-based algorithm for staging secondary caries in bitewings. Caries Res. 2025;59(3):163\u201373.","journal-title":"Caries Res"},{"issue":"4","key":"8806_CR17","doi-asserted-by":"publisher","first-page":"1731","DOI":"10.1007\/s00784-022-04801-6","volume":"27","author":"W Panyarak","year":"2023","unstructured":"Panyarak W, Suttapak W, Wantanajittikul K, Charuakkra A, Prapayasatok S. Assessment of YOLOv3 for caries detection in bitewing radiographs based on the ICCMS\u2122 radiographic scoring system. Clin Oral Invest. 2023;27(4):1731\u201342.","journal-title":"Clin Oral Invest"},{"issue":"5\u20136","key":"8806_CR18","doi-asserted-by":"publisher","first-page":"455","DOI":"10.1159\/000527418","volume":"56","author":"X Chen","year":"2022","unstructured":"Chen X, Guo J, Ye J, Zhang M, Liang Y. Detection of proximal caries lesions on bitewing radiographs using deep learning method. Caries Res. 2022;56(5\u20136):455\u201363.","journal-title":"Caries Res"},{"key":"8806_CR19","doi-asserted-by":"crossref","unstructured":"Meghana D, Manimaran A. A Hybrid YOLOv8s+ Swin-T Transformer Approach for Automated Caries Detection on Periapical Radiographs. J Imaging Inform Med. 2025;1\u201318.","DOI":"10.1007\/s10278-025-01763-5"},{"key":"8806_CR20","doi-asserted-by":"publisher","first-page":"103425","DOI":"10.1016\/j.jdent.2020.103425","volume":"100","author":"AG Cantu","year":"2020","unstructured":"Cantu AG, Gehrung S, Krois J, Chaurasia A, Rossi JG, Gaudin R, et al. Detecting caries lesions of different radiographic extension on bitewings using deep learning. J Dent. 2020;100:103425.","journal-title":"J Dent"},{"issue":"1","key":"8806_CR21","doi-asserted-by":"publisher","first-page":"198","DOI":"10.1038\/s41746-023-00944-2","volume":"6","author":"M Felsch","year":"2023","unstructured":"Felsch M, Meyer O, Schlickenrieder A, Engels P, Sch\u00f6newolf J, Z\u00f6llner F, et al. Detection and localization of caries and hypomineralization on dental photographs with a vision transformer model. NPJ Digit Med. 2023;6(1):198.","journal-title":"NPJ Digit Med"},{"key":"8806_CR22","first-page":"1","volume-title":"2017 medical technologies national congress (TIPTEKNO)","author":"AB Oktay","year":"2017","unstructured":"Oktay AB. Tooth detection with convolutional neural networks. In: 2017 medical technologies national congress (TIPTEKNO). IEEE; 2017. p. 1\u20134."},{"key":"8806_CR23","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.compbiomed.2016.11.003","volume":"80","author":"Y Miki","year":"2017","unstructured":"Miki Y, Muramatsu C, Hayashi T, Zhou X, Hara T, Katsumata A, et al. Classification of teeth in cone-beam CT using deep convolutional neural network. Comput Biol Med. 2017;80:24\u20139.","journal-title":"Comput Biol Med"},{"key":"8806_CR24","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.compbiomed.2016.11.013","volume":"80","author":"S Raith","year":"2017","unstructured":"Raith S, Vogel EP, Anees N, Keul C, G\u00fcth JF, Edelhoff D, et al. Artificial Neural Networks as a powerful numerical tool to classify specific features of a tooth based on 3D scan data. Comput Biol Med. 2017;80:65\u201376.","journal-title":"Comput Biol Med"},{"issue":"4","key":"8806_CR25","doi-asserted-by":"publisher","first-page":"577","DOI":"10.1002\/ima.22337","volume":"29","author":"Z Li","year":"2019","unstructured":"Li Z, Wang SH, Fan RR, Cao G, Zhang YD, Guo T. Teeth category classification via seven-layer deep convolutional neural network with max pooling and global average pooling. Int J Imaging Syst Technol. 2019;29(4):577\u201383.","journal-title":"Int J Imaging Syst Technol"}],"container-title":["BMC Oral Health"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/article\/10.1186\/s12903-026-08806-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-026-08806-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1186\/s12903-026-08806-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,17]],"date-time":"2026-08-17T14:02:41Z","timestamp":1786975361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1186\/s12903-026-08806-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,11]]},"references-count":25,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["8806"],"URL":"https:\/\/doi.org\/10.1186\/s12903-026-08806-5","relation":{},"ISSN":["1472-6831"],"issn-type":[{"value":"1472-6831","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,11]]},"assertion":[{"value":"7 January 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 May 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"11 June 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"This retrospective study used de-identified intraoral periapical radiographs obtained from the archives of Sibar Institute of Dental Sciences, Thakkellapadu, Guntur, Andhra Pradesh, India. The study was performed in accordance with the Declaration of Helsinki and relevant institutional guidelines. Approval was granted by the Institutional Ethics Committee, Sibar Institute of Dental Sciences, on 13 December 2024. All radiographs were anonymized prior to analysis by removing personally identifiable information. Owing to the retrospective design and use of fully anonymized data, the requirement for individual informed consent was formally waived by the committee.","order":1,"name":"Ethics","label":"Ethics approval and consent to participate","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"Not applicable. This manuscript contains only de-identified radiographs with no individual person\u2019s data that permit identification. Accordingly, consent for publication was not required, and the Institutional Ethics Committee waiver applies.","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":"1470"}}