{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:55:11Z","timestamp":1793321711217,"version":"4.5.0"},"reference-count":29,"publisher":"Public Library of Science (PLoS)","issue":"12","license":[{"start":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T00:00:00Z","timestamp":1735603200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100005790","name":"Thammasat University","doi-asserted-by":"publisher","award":["TUFT 68\/2567. There was no additional external funding received for this study."],"award-info":[{"award-number":["TUFT 68\/2567. There was no additional external funding received for this study."]}],"id":[{"id":"10.13039\/501100005790","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["www.plosone.org"],"crossmark-restriction":false},"short-container-title":["PLoS ONE"],"abstract":"<jats:p>This study aimed to evaluate the performance of a deep learning-based segmentation model for predicting outcomes of non-surgical endodontic treatment. Preoperative and 3-year postoperative periapical radiographic images of each tooth from routine root canal treatments performed by endodontists from 2015 to 2021 were obtained retrospectively from Thammasat University hospital. Preoperative radiographic images of 1200 teeth with 3-year follow-up results (440 healed, 400 healing, and 360 disease) were collected. Mask Region-based Convolutional Neural Network (Mask R-CNN) was used to pixel-wise segment the root from other structures in the image and trained to predict class label into healed, healing and disease. Three endodontists annotated 1080 images used for model training, validation, and testing. The performance of the model was evaluated on a test set and also by comparison with the performance of clinicians (general practitioners and endodontists) with and without the help of the model on independent 120 images. The performance of the Mask R-CNN prediction model was high with the mean average precision (mAP) of 0.88 (95% CI 0.83\u20130.93) and area under the precision-recall curve of 0.91 (95% CI 0.88\u20130.94), 0.83 (95% CI 0.81\u20130.85), 0.91 (95% CI 0.90\u20130.92) on healed, healing and disease, respectively. The prediction metrics of general practitioners and endodontists significantly improved with the help of Mask R-CNN outperforming clinicians alone with mAP increasing from 0.75 (95% CI 0.72\u20130.78) to 0.84 (95% CI 0.81\u20130.87) and 0.88 (95% CI 0.85\u20130.91) to 0.92 (95% CI 0.89\u20130.95), respectively. In conclusion, deep learning-based segmentation model had the potential to predict non-surgical endodontic treatment outcomes from periapical radiographic images and were expected to aid in endodontic treatment.<\/jats:p>","DOI":"10.1371\/journal.pone.0310925","type":"journal-article","created":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T18:56:06Z","timestamp":1735671366000},"page":"e0310925","update-policy":"https:\/\/doi.org\/10.1371\/journal.pone.corrections_policy","source":"Crossref","is-referenced-by-count":11,"title":["Development and evaluation of a deep learning segmentation model for assessing non-surgical endodontic treatment outcomes on periapical radiographs: A retrospective study"],"prefix":"10.1371","volume":"19","author":[{"given":"Dennis","family":"Dennis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1237-1274","authenticated-orcid":true,"given":"Siriwan","family":"Suebnukarn","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sothana","family":"Vicharueang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wasit","family":"Limprasert","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"340","published-online":{"date-parts":[[2024,12,31]]},"reference":[{"key":"pone.0310925.ref001","first-page":"493","article-title":"The success of endodontic therapy\u2010\u2010healing and functionality","volume":"32","author":"S Friedman","year":"2004","journal-title":"J Calif Dent Assoc"},{"key":"pone.0310925.ref002","doi-asserted-by":"crossref","first-page":"59","DOI":"10.1016\/j.cden.2016.08.009","volume":"61","author":"N Chugal","year":"2017","journal-title":"Endodontic Treatment Outcomes. Dent Clin North Am"},{"key":"pone.0310925.ref003","doi-asserted-by":"crossref","first-page":"140","DOI":"10.1111\/iej.13835","article-title":"Tooth survival after endodontic treatment","volume":"56","author":"H Fransson","year":"2023","journal-title":"Int Endod J"},{"key":"pone.0310925.ref004","doi-asserted-by":"crossref","first-page":"908","DOI":"10.3390\/jcm10050908","article-title":"Clinical outcomes of endodontic treatments and restorations with and without posts up to 18 years","volume":"10","author":"DIK Pontoriero","year":"2021","journal-title":"J Clin Med"},{"key":"pone.0310925.ref005","doi-asserted-by":"crossref","first-page":"82","DOI":"10.1111\/iej.13897","article-title":"Factors that affect the outcomes of root canal treatment and retreatment- A reframing of the principles","volume":"56","author":"K Gulabivala","year":"2023","journal-title":"Int Endod J"},{"key":"pone.0310925.ref006","doi-asserted-by":"crossref","first-page":"603","DOI":"10.1016\/j.joen.2007.01.016","article-title":"Influence of the endodontic treatment on mechanical properties of root dentin","volume":"33","author":"CJ Soares","year":"2007","journal-title":"J Endod"},{"key":"pone.0310925.ref007","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1038\/s41591-018-0300-7","article-title":"High-performance medicine: the convergence of human and artificial intelligence","volume":"25","author":"EJ Topol","year":"2019","journal-title":"Nat Med"},{"key":"pone.0310925.ref008","doi-asserted-by":"crossref","first-page":"1452","DOI":"10.1177\/00220345211013808","article-title":"Artificial Intelligence and Ethics in Dentistry: A Scoping Review","volume":"100","author":"CM M\u00f6rch","year":"2021","journal-title":"J Dent Res"},{"key":"pone.0310925.ref009","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1177\/0022034520915714","article-title":"Artificial Intelligence in Dentistry: Chances and Challenges","volume":"99","author":"F Schwendicke","year":"2020","journal-title":"J Dent Res"},{"key":"pone.0310925.ref010","first-page":"1352","volume":"47","author":"A Aminoshariae","year":"2021","journal-title":"Artificial Intelligence in Endodontics: Current Applications and Future Directions. J Endod"},{"key":"pone.0310925.ref011","doi-asserted-by":"crossref","first-page":"20180218","DOI":"10.1259\/dmfr.20180218","article-title":"A deep-learning artificial intelligence system for assessment of root morphology of the mandibular first molar on panoramic radiography","volume":"48","author":"T Hiraiwa","year":"2019","journal-title":"Dentomaxillofac Radiol"},{"key":"pone.0310925.ref012","doi-asserted-by":"crossref","first-page":"917","DOI":"10.1016\/j.joen.2019.03.016","article-title":"Deep Learning for the Radiographic Detection of Apical Lesions","volume":"45","author":"T Ekert","year":"2019","journal-title":"J Endod"},{"key":"pone.0310925.ref013","doi-asserted-by":"crossref","first-page":"680","DOI":"10.1111\/iej.13265","article-title":"Evaluation of artificial intelligence for detecting periapical pathosis on cone-beam computed tomography scans","volume":"53","author":"K Orhan","year":"2020","journal-title":"Int Endod J"},{"key":"pone.0310925.ref014","doi-asserted-by":"crossref","first-page":"1085","DOI":"10.1111\/iej.13828","article-title":"Present status and future directions: Imaging techniques for the detection of periapical lesions","volume":"55","author":"E Cotti","year":"2022","journal-title":"Int Endod J"},{"key":"pone.0310925.ref015","doi-asserted-by":"crossref","first-page":"386","DOI":"10.1109\/TPAMI.2018.2844175","article-title":"Mask R-CNN","volume":"42","author":"K He","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"pone.0310925.ref016","doi-asserted-by":"crossref","first-page":"279","DOI":"10.3390\/electronics10030279","article-title":"A comparative analysis of object detection metrics with a companion open-source toolkit","volume":"10","author":"R Padilla","year":"2021","journal-title":"Electronics"},{"key":"pone.0310925.ref017","first-page":"360","article-title":"Understanding interobserver agreement: the kappa statistic","volume":"37","author":"AJ Viera","year":"2005","journal-title":"Fam Med"},{"key":"pone.0310925.ref018","doi-asserted-by":"crossref","first-page":"159","DOI":"10.2307\/2529310","article-title":"The measurement of observer agreement for categorical data","volume":"33","author":"JR Landis","year":"1977","journal-title":"Biometrics"},{"key":"pone.0310925.ref019","doi-asserted-by":"crossref","first-page":"653","DOI":"10.1016\/j.diii.2021.09.002","article-title":"Breast nodule classification with two-dimensional ultrasound using Mask-RCNN ensemble aggregation","volume":"102","author":"E Evain","year":"2021","journal-title":"Diagn Interv Imaging"},{"key":"pone.0310925.ref020","doi-asserted-by":"crossref","first-page":"301","DOI":"10.1109\/JBHI.2021.3081111","article-title":"Cross-Model Attention-Guided Tumor Segmentation for 3D Automated Breast Ultrasound (ABUS) Images","volume":"26","author":"Y Zhou","year":"2022","journal-title":"IEEE J Biomed Health Inform"},{"key":"pone.0310925.ref021","doi-asserted-by":"crossref","first-page":"105547","DOI":"10.1016\/j.compbiomed.2022.105547","article-title":"An enhanced tooth segmentation and numbering according to FDI notation in bitewing radiographs","volume":"146","author":"BY Tekin","year":"2022","journal-title":"Comput Biol Med"},{"key":"pone.0310925.ref022","first-page":"1617","article-title":"Recognizing Occlusal Caries in Dental Intraoral Images Using Deep Learning","volume":"2019","author":"K Moutselos","year":"2019","journal-title":"Annu Int Conf IEEE Eng Med Biol Soc"},{"key":"pone.0310925.ref023","first-page":"18","article-title":"Artificial intelligence for caries detection: a novel diagnostic tool using deep learning algorithms","author":"Y Liu","year":"2024","journal-title":"Oral Radiol"},{"key":"pone.0310925.ref024","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1007\/s00784-021-04043-y","article-title":"Deep learning for categorization of endodontic lesion based on radiographic periapical index scoring system","volume":"26","author":"NP Moidu","year":"2022","journal-title":"Clin Oral Investig"},{"key":"pone.0310925.ref025","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1007\/s11282-019-00409-x","article-title":"Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiography","volume":"36","author":"M Fukuda","year":"2020","journal-title":"Oral Radiol"},{"key":"pone.0310925.ref026","doi-asserted-by":"crossref","first-page":"20220209","DOI":"10.1259\/dmfr.20220209","article-title":"Detection of the separated root canal instrument on panoramic radiograph: a comparison of LSTM and CNN deep learning methods","volume":"52","author":"C Buyuk","year":"2023","journal-title":"Dentomaxillofac Radiol"},{"key":"pone.0310925.ref027","doi-asserted-by":"crossref","first-page":"102750","DOI":"10.1016\/j.media.2023.102750","article-title":"Root canal treatment planning by automatic tooth and root canal segmentation in dental CBCT with deep multi-task feature learning","volume":"85","author":"Y Wang","year":"2023","journal-title":"Med Image Anal"},{"key":"pone.0310925.ref028","doi-asserted-by":"crossref","first-page":"641","DOI":"10.1007\/s00784-018-2338-9","article-title":"3D imaging, 3D printing and 3D virtual planning in endodontics","volume":"22","author":"P Shah","year":"2018","journal-title":"Clin Oral Investig"},{"key":"pone.0310925.ref029","doi-asserted-by":"crossref","first-page":"102190","DOI":"10.1016\/j.artmed.2021.102190","article-title":"A healthy debate: Exploring the views of medical doctors on the ethics of artificial intelligence","volume":"121","author":"A Martinho","year":"2021","journal-title":"Artif Intell Med"}],"container-title":["PLOS ONE"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0310925","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,31]],"date-time":"2024-12-31T18:56:18Z","timestamp":1735671378000},"score":1,"resource":{"primary":{"URL":"https:\/\/dx.plos.org\/10.1371\/journal.pone.0310925"}},"subtitle":[],"editor":[{"given":"Sonam","family":"Khurana","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2024,12,31]]},"references-count":29,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2024,12,31]]}},"URL":"https:\/\/doi.org\/10.1371\/journal.pone.0310925","relation":{},"ISSN":["1932-6203"],"issn-type":[{"value":"1932-6203","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,31]]}}}