{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T10:36:34Z","timestamp":1793356594139,"version":"4.5.0"},"reference-count":34,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T00:00:00Z","timestamp":1778198400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100025314","name":"School of Medicine, Ajou University","doi-asserted-by":"publisher","award":["M2024C046000076"],"award-info":[{"award-number":["M2024C046000076"]}],"id":[{"id":"10.13039\/501100025314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100025314","name":"School of Medicine, Ajou University","doi-asserted-by":"publisher","award":["202501220001"],"award-info":[{"award-number":["202501220001"]}],"id":[{"id":"10.13039\/501100025314","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100014188","name":"Ministry of Science and ICT, South Korea","doi-asserted-by":"publisher","award":["NRF-2022R1F1A1067929"],"award-info":[{"award-number":["NRF-2022R1F1A1067929"]}],"id":[{"id":"10.13039\/501100014188","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Oral Health"],"abstract":"<jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>This pilot study evaluated the feasibility of multi-class dental caries detection using deep learning\u2013based smartphone images.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Method<\/jats:title>\n                    <jats:p>Seventy adults provided six self-taken intraoral smartphone images in a non-clinical setting. Four dentists annotated each image based on the visual assessment of caries using binary (none vs. caries), four-class (none, initial, moderate, or advanced), and five-class (none, initial-1, initial-2, moderate, or advanced), according to two internationally recognized criteria (ICDAS-II and ADA CCS). A YOLOv6-L6 deep learning model was trained on an expert-labeled dataset, with model performance evaluated using sensitivity, specificity, precision, accuracy, F1-score, and mean average precision (mAP).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>Intra-examiner reliability was substantial to almost perfect (\u03ba\u2009=\u20090.765\u20130.952), whereas inter-examiner agreement was low to moderate (\u03ba\u2009=\u20090.358\u20130.406). Across all classification schemes, the models achieved a sensitivity \u226586%, a specificity &amp;gt;97%, a precision &amp;gt;90%, and an accuracy &amp;gt;93%. F1-scores remained high (&amp;gt;88%), declining as the classes increased. The binary classification model demonstrated the highest mAP (65.2%), whereas the four- and five-class models showed progressively lower mAP values. Notably, the five-class model achieved the highest specificity (98.45%).<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>This pilot study demonstrates the feasibility of smartphone-based deep learning as a supportive aid for caries detection and its potential role in patient-driven screening.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/froh.2026.1805448","type":"journal-article","created":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T05:52:07Z","timestamp":1778219527000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Feasibility of multi-class dental caries detection using deep learning\u2013based smartphone images: a pilot prospective study"],"prefix":"10.3389","volume":"7","author":[{"given":"Ji-Yun","family":"Kang","sequence":"first","affiliation":[{"name":"Department of Convergence Medical Science, Graduate School of Medicine, Ajou University","place":["Suwon, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hee-Kyung","family":"Kim","sequence":"additional","affiliation":[{"name":"Department of Prosthodontics, Institute of Oral Health Science, Ajou University School of Medicine","place":["Suwon, Republic of Korea"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,5,8]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"17030","DOI":"10.1038\/nrdp.2017.30","article-title":"Dental caries","volume":"3","author":"Pitts","year":"2017","journal-title":"Nat Rev Dis Primers"},{"key":"B2","doi-asserted-by":"publisher","first-page":"869112","DOI":"10.3389\/froh.2022.869112","article-title":"Added sugar and oral health: a position paper of the Brazilian academy of dentistry","volume":"3","author":"Feldens","year":"2022","journal-title":"Front Oral Health"},{"key":"B3","doi-asserted-by":"publisher","first-page":"657518","DOI":"10.3389\/froh.2021.657518","article-title":"Evidence-based caries management for all ages-practical guidelines","volume":"2","author":"Featherstone","year":"2021","journal-title":"Front Oral Health"},{"key":"B4","doi-asserted-by":"publisher","first-page":"e43489","DOI":"10.7759\/cureus.43489","article-title":"Current approaches to diagnosis of early proximal carious lesion: a literature review","volume":"15","author":"Al Saffan","year":"2023","journal-title":"Cureus"},{"key":"B5","doi-asserted-by":"publisher","first-page":"119","DOI":"10.1016\/j.compbiomed.2015.04.016","article-title":"A computer-aided automated methodology for the detection and classification of occlusal caries from photographic color images","volume":"62","author":"Berdouses","year":"2015","journal-title":"Comput Biol Med"},{"key":"B6","doi-asserted-by":"publisher","first-page":"S3","DOI":"10.1186\/1472-6831-15-s1-s3","article-title":"Detection and diagnosis of the early caries lesion","author":"Gomez","year":"2015","journal-title":"BMC Oral Health"},{"key":"B7","doi-asserted-by":"publisher","first-page":"C48","DOI":"10.1177\/154405910408301s10","article-title":"The challenges of validating diagnostic methods and selecting appropriate gold standards","volume":"83","author":"Huysmans","year":"2004","journal-title":"J Dent Res"},{"key":"B8","doi-asserted-by":"publisher","first-page":"8","DOI":"10.1159\/000068230","article-title":"An in vitro comparison of a combined foti\/visual examination of occlusal caries with other caries diagnostic methods and the effect of stain on their diagnostic performance","volume":"37","author":"C\u00f4rtes","year":"2003","journal-title":"Caries Res"},{"key":"B9","doi-asserted-by":"publisher","first-page":"63","DOI":"10.17096\/jiufd.38691","article-title":"Icdas ii criteria (international caries detection and assessment system)","volume":"49","author":"Dikmen","year":"2015","journal-title":"J Istanb Univ Fac Dent"},{"key":"B10","doi-asserted-by":"publisher","first-page":"e479","DOI":"10.4317\/jced.56445","article-title":"Optical magnification has No benefits on the detection of occlusal caries lesions in permanent molars using different visual scoring systems: an in vitro study","volume":"12","author":"Wilde","year":"2020","journal-title":"J Clin Exp Dent"},{"key":"B11","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1159\/000331212","article-title":"Measurement of histological and radiographic depth and width of occlusal caries lesions: a methodological study","volume":"45","author":"Bakhshandeh","year":"2011","journal-title":"Caries Res"},{"key":"B12","doi-asserted-by":"publisher","first-page":"133","DOI":"10.2341\/10-006-l","article-title":"In Vitro evaluation of icdas and radiographic examination of occlusal surfaces and their association with treatment decisions","volume":"36","author":"Diniz","year":"2011","journal-title":"Oper Dent"},{"key":"B13","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1016\/j.adaj.2014.11.018","article-title":"The American dental association caries classification system for clinical practice: a report of the American dental association council on scientific affairs","volume":"146","author":"Young","year":"2015","journal-title":"J Am Dent Assoc"},{"key":"B14","doi-asserted-by":"publisher","first-page":"105737","DOI":"10.1016\/j.jdent.2025.105737","article-title":"Accuracy of clinical photography for the detection of dental caries: a systematic review and meta-analysis","volume":"157","author":"Ku","year":"2025","journal-title":"J Dent"},{"key":"B15","doi-asserted-by":"publisher","first-page":"10","DOI":"10.1186\/1472-6831-12-10","article-title":"Comparison of photographic and visual assessment of occlusal caries with histology as the reference standard","volume":"12","author":"Boye","year":"2012","journal-title":"BMC Oral Health"},{"key":"B16","doi-asserted-by":"publisher","first-page":"158","DOI":"10.1177\/00220345211032524","article-title":"Caries detection on intraoral images using artificial intelligence","volume":"101","author":"K\u00fchnisch","year":"2022","journal-title":"J Dent Res"},{"key":"B17","doi-asserted-by":"publisher","first-page":"104821","DOI":"10.1016\/j.jdent.2023.104821","article-title":"Ai-Based dental caries and tooth number detection in intraoral photos: model development and performance evaluation","volume":"141","author":"Yoon","year":"2024","journal-title":"J Dent"},{"key":"B18","doi-asserted-by":"publisher","first-page":"168","DOI":"10.1111\/ajd.12758","article-title":"Smartphone apps for skin cancer diagnosis: implications for patients and practitioners","volume":"59","author":"Abbott","year":"2018","journal-title":"Australas J Dermatol"},{"key":"B19","doi-asserted-by":"publisher","first-page":"1029991","DOI":"10.3389\/fsurg.2022.1029991","article-title":"A deep learning based multimodal fusion model for skin lesion diagnosis using smartphone collected clinical images and metadata","volume":"9","author":"Ou","year":"2022","journal-title":"Front Surg"},{"key":"B20","doi-asserted-by":"publisher","first-page":"086007","DOI":"10.1117\/1.Jbo.26.8.086007","article-title":"Automatic detection of oral cancer in smartphone-based images using deep learning for early diagnosis","volume":"26","author":"Lin","year":"2021","journal-title":"J Biomed Opt"},{"key":"B21","doi-asserted-by":"publisher","first-page":"1470706","DOI":"10.3389\/froh.2025.1470706","article-title":"Validity and reliability of a smartphone-based photographic method for detection of dental caries in adults for use in teledentistry","volume":"6","author":"Lamas-Lara","year":"2025","journal-title":"Front Oral Health"},{"key":"B22","doi-asserted-by":"publisher","first-page":"585","DOI":"10.1067\/mpr.2002.129803","article-title":"The repeatability of an intraoral dental colorimeter","volume":"88","author":"Tung","year":"2002","journal-title":"J Prosthet Dent"},{"key":"B23","doi-asserted-by":"publisher","first-page":"79","DOI":"10.1159\/000113160","article-title":"Reproducibility and accuracy of the icdas-ii for detection of occlusal caries in vitro","volume":"42","author":"Jablonski-Momeni","year":"2008","journal-title":"Caries Res"},{"key":"B24","doi-asserted-by":"publisher","first-page":"2849","DOI":"10.1007\/s00405-019-05553-y","article-title":"Inter-rater reliability of seven neurolaryngologists in laryngeal emg signal interpretation","volume":"276","author":"Ho","year":"2019","journal-title":"Eur Arch Otorhinolaryngol"},{"key":"B25","doi-asserted-by":"publisher","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"Landis","year":"1977","journal-title":"Biometrics"},{"key":"B26","doi-asserted-by":"publisher","first-page":"105444","DOI":"10.1016\/j.compbiomed.2022.105444","article-title":"Medical image augmentation for lesion detection using a texture-constrained multichannel progressive gan","volume":"145","author":"Guan","year":"2022","journal-title":"Comput Biol Med"},{"key":"B27","doi-asserted-by":"publisher","first-page":"2575","DOI":"10.1007\/s00521-022-07730-3","article-title":"Automatic detection of indoor occupancy based on improved Yolov5 model","volume":"35","author":"Wang","year":"2023","journal-title":"Neural Comput Appl"},{"key":"B28","doi-asserted-by":"publisher","first-page":"9069","DOI":"10.3390\/s23229069","article-title":"A lightweight human fall detection network","volume":"23","author":"Kan","year":"2023","journal-title":"Sensors"},{"key":"B29","doi-asserted-by":"publisher","first-page":"92","DOI":"10.3390\/s23010092","article-title":"Identity-preserved human posture detection in infrared thermal images: a benchmark","volume":"23","author":"Guo","year":"2022","journal-title":"Sensors"},{"key":"B30","doi-asserted-by":"publisher","first-page":"e33256","DOI":"10.7759\/cureus.33256","article-title":"The efficacy of dental caries telediagnosis using smartphone: a diagnostic study in geriatric patients","volume":"15","author":"Pandey","year":"2023","journal-title":"Cureus"},{"key":"B31","doi-asserted-by":"publisher","first-page":"26752","DOI":"10.1038\/s41598-024-78184-x","article-title":"Developing an ai-based application for caries Index detection on intraoral photographs","volume":"14","author":"Adnan","year":"2024","journal-title":"Sci Rep"},{"key":"B32","doi-asserted-by":"publisher","first-page":"1297","DOI":"10.1038\/s41597-025-05647-9","article-title":"Annotated intraoral image dataset for dental caries detection","volume":"12","author":"Ahmed","year":"2025","journal-title":"Sci Data"},{"key":"B33","doi-asserted-by":"publisher","first-page":"104891","DOI":"10.1016\/j.jdent.2024.104891","article-title":"Performance evaluation of three versions of a convolutional neural network for object detection and segmentation using a multiclass and reduced panoramic radiograph dataset","volume":"144","author":"Bonfanti-Gris","year":"2024","journal-title":"J Dent"},{"key":"B34","article-title":"Pediatric Dentistry: A Clinical Approach","author":"Koch","year":"2009"}],"container-title":["Frontiers in Oral Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/froh.2026.1805448\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T05:52:08Z","timestamp":1778219528000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/froh.2026.1805448\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,8]]},"references-count":34,"alternative-id":["10.3389\/froh.2026.1805448"],"URL":"https:\/\/doi.org\/10.3389\/froh.2026.1805448","relation":{},"ISSN":["2673-4842"],"issn-type":[{"value":"2673-4842","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5,8]]},"article-number":"1805448"}}