{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T09:59:26Z","timestamp":1790589566356,"version":"4.1.0"},"reference-count":41,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T00:00:00Z","timestamp":1790553600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Int Endodontic J"],"abstract":"<jats:title>ABSTRACT<\/jats:title>\n                  <jats:sec>\n                    <jats:title>Aim<\/jats:title>\n                    <jats:p>To develop and validate a machine learning\u2010based automated computational framework using periapical radiographs for the detection, segmentation and classification of root canal curvature in mandibular premolars with single canals, and to evaluate the contribution of geometric and deep learning features towards diagnostic performance.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methodology<\/jats:title>\n                    <jats:p>A retrospective cross\u2010sectional study was performed using 1644 periapical images of mandibular premolars. A four\u2010stage multi\u2010model framework was proposed using a single fixed 10\u2010fold cross\u2010validation partition applied consistently across all four stages to prevent data leakage between training and evaluation. The object detection models were YOLOv8, YOLOv11 and RF\u2010DETR. For segmentation of the root canal, YOLOv8\u2010seg, YOLOv11\u2010seg and Attention U\u2010Net were used. The multiparametric feature extraction included five geometric morphometric features automatically derived from a binary mask and 2048 deep convolutional neural network features from ResNet\u201050. Classification of curvature was defined using an eXtreme Gradient Boosting (XGBoost) classifier with stratified 10\u2010fold cross\u2010validation, with Synthetic Minority Over\u2010sampling Technique (SMOTE) and algorithmic class weighting applied within the training folds of each cross\u2010validation iteration.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      The dataset included 633 straight, 885 moderately curved and 126 severely curved canals. RF\u2010DETR achieved a recall of 97.5%, precision of 93.3% and F1\u2010score of 95.4% for premolar detection. The YOLOv11\u2010seg model was successful in segmenting the root canal with a Dice score of 85.8% and an IoU of 77.5%. All five geometric parameters were statistically significant for different severity groups (\n                      <jats:italic>p<\/jats:italic>\n                      \u2010value &lt;\u20090.001). For the end\u2010to\u2010end curvature classification, the hybrid feature fusion model produced the highest overall metrics, achieving an accuracy of 89.60%, a recall of 83.80% and an F1\u2010score of 86.77%, compared to the models using either geometric features (88.38% accuracy) or deep learning features alone (82.42% accuracy).\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusions<\/jats:title>\n                    <jats:p>The hybrid feature\u2010fusion model reached the highest overall classification accuracy at 89.60%. Although the geometric\u2010only model had higher sensitivity for severe curvature with 80.6% compared to 69.1%, L\u00fciten's angle was the most prominent predictor of curvature severity. Due to the limitations of two\u2010dimensional radiographs in displaying buccolingual curvatures, this framework works best as a screening aid as it helps identify canals that need adjunctive three\u2010dimensional evaluation.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.1111\/iej.70281","type":"journal-article","created":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T09:43:27Z","timestamp":1790588607000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Automated Root Canal Curvature Assessment From Periapical Radiographs Using Geometric and Deep Learning Features"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-8831-3981","authenticated-orcid":false,"given":"Balaganesh","family":"Pachaiappan","sequence":"first","affiliation":[{"name":"Department of Conservative Dentistry and Endodontics Sri Venkateswara Dental College and Hospital  Chennai India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8811-2960","authenticated-orcid":false,"given":"Saravanan","family":"Poorni","sequence":"additional","affiliation":[{"name":"Department of Conservative Dentistry and Endodontics Sri Venkateswara Dental College and Hospital  Chennai India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6929-4594","authenticated-orcid":false,"given":"Srividhya","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Department of Conservative Dentistry and Endodontics Sri Venkateswara Dental College and Hospital  Chennai India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9709-8395","authenticated-orcid":false,"given":"Cruz","family":"Nishanthine","sequence":"additional","affiliation":[{"name":"Department of Conservative Dentistry and Endodontics Sri Venkateswara Dental College and Hospital  Chennai India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3651-181X","authenticated-orcid":false,"given":"Manali Ramakrishnan","family":"Srinivasan","sequence":"additional","affiliation":[{"name":"Department of Conservative Dentistry and Endodontics Sri Venkateswara Dental College and Hospital  Chennai India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9798-3872","authenticated-orcid":false,"given":"Thilla Sekar","family":"Vinothkumar","sequence":"additional","affiliation":[{"name":"Department of Restorative Dental Sciences, College of Dentistry Jazan University  Jazan Saudi Arabia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3783-3156","authenticated-orcid":false,"given":"Venkateshbabu","family":"Nagendrababu","sequence":"additional","affiliation":[{"name":"Department of Restorative Dentistry, College of Dental Medicine University of Sharjah  Sharjah UAE"},{"name":"Department of Conservative Dentistry and Endodontics Dr. D. Y. Patil Dental College &amp; Hospital, Dr. D. Y. Patil Vidyapeeth (Deemed To Be University)  Pimpri India"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0726-7467","authenticated-orcid":false,"given":"Paul M. H.","family":"Dummer","sequence":"additional","affiliation":[{"name":"School of Dentistry, College of Biomedical and Life Sciences Cardiff University  Cardiff UK"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","published-online":{"date-parts":[[2026,9,28]]},"reference":[{"issue":"20","key":"e_1_2_12_2_1","doi-asserted-by":"crossref","first-page":"8589","DOI":"10.3390\/s23208589","article-title":"Improved UNet With Attention for Medical Image Segmentation","volume":"23","author":"AL Qurri A.","year":"2023","journal-title":"Sensors"},{"key":"e_1_2_12_3_1","doi-asserted-by":"crossref","first-page":"3214","DOI":"10.3390\/diagnostics12123214","article-title":"Artificial Intelligence (AI) for Detection and Localization of Unobturated Second Mesial Buccal (MB2) Canals in Cone\u2010Beam Computed Tomography (CBCT)","volume":"12","author":"Albitar L.","year":"2022","journal-title":"Diagnostics"},{"key":"e_1_2_12_4_1","volume-title":"AAE Endodontic Case Difficulty Assessment Form and Guidelines","author":"American Association of Endodontists","year":"2018"},{"issue":"3","key":"e_1_2_12_5_1","doi-asserted-by":"crossref","first-page":"637","DOI":"10.1111\/iej.13698","article-title":"Present Status and Future Directions: Canal Shaping","volume":"55","author":"Arias A.","year":"2022","journal-title":"International Endodontic Journal"},{"issue":"5","key":"e_1_2_12_6_1","doi-asserted-by":"crossref","first-page":"4620","DOI":"10.3390\/ijerph20054620","article-title":"Artificial Intelligence as a Decision\u2010Making Tool in Forensic Dentistry: A Pilot Study With I3M","volume":"20","author":"Bui R.","year":"2023","journal-title":"International Journal of Environmental Research and Public Health"},{"issue":"3","key":"e_1_2_12_7_1","doi-asserted-by":"crossref","first-page":"656","DOI":"10.1111\/iej.13685","article-title":"Present Status and Future Directions: Management of Curved and Calcified Root Canals","volume":"55","author":"Chaniotis A.","year":"2022","journal-title":"International Endodontic Journal"},{"key":"e_1_2_12_8_1","doi-asserted-by":"crossref","first-page":"1565403","DOI":"10.3389\/fbioe.2025.1565403","article-title":"Tooth Image Segmentation and Root Canal Measurement Based on Deep Learning","volume":"13","author":"Chen Z.","year":"2025","journal-title":"Frontiers in Bioengineering and Biotechnology"},{"issue":"2","key":"e_1_2_12_9_1","doi-asserted-by":"crossref","first-page":"552","DOI":"10.1007\/s10266-023-00864-3","article-title":"Second Mesiobuccal Canal Segmentation With YOLOv5 Architecture Using Cone Beam Computed Tomography Images","volume":"112","author":"Duman \u015e. B.","year":"2024","journal-title":"Odontology"},{"issue":"7","key":"e_1_2_12_10_1","doi-asserted-by":"crossref","first-page":"1189","DOI":"10.1111\/iej.13506","article-title":"The Endodontic Complexity Assessment Tool (E\u2010CAT): A Digital Form for Assessing Root Canal Treatment Case Difficulty","volume":"54","author":"Essam O.","year":"2021","journal-title":"International Endodontic Journal"},{"issue":"11","key":"e_1_2_12_11_1","doi-asserted-by":"crossref","first-page":"796","DOI":"10.1097\/01.don.0000158232.77240.01","article-title":"A Comparative Study of Three Different Root Canal Curvature Measurement Techniques and Measuring the Canal Access Angle in Curved Canals","volume":"31","author":"G\u00fcnday M.","year":"2005","journal-title":"Journal of Endodontics"},{"issue":"3","key":"e_1_2_12_12_1","doi-asserted-by":"crossref","first-page":"326","DOI":"10.1111\/iej.13921","article-title":"Efficacy of Imaging Techniques for the Diagnosis of Apical Periodontitis: A Systematic Review","volume":"56","author":"Hilmi A.","year":"2023","journal-title":"International Endodontic Journal"},{"issue":"1","key":"e_1_2_12_13_1","doi-asserted-by":"crossref","first-page":"30","DOI":"10.1111\/j.1601-1546.2005.00152.x","article-title":"Mechanical Preparation of Root Canals: Shaping Goals, Techniques, and Means","volume":"10","author":"H\u00fclsmann M.","year":"2005","journal-title":"Endodontic Topics"},{"issue":"1","key":"e_1_2_12_14_1","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1186\/s12903-024-04235-4","article-title":"Deep Learning for Determining the Difficulty of Endodontic Treatment: A Pilot Study","volume":"24","author":"Karkehabadi H.","year":"2024","journal-title":"BMC Oral Health"},{"key":"e_1_2_12_15_1","doi-asserted-by":"crossref","first-page":"3401","DOI":"10.3390\/jcm13123401","article-title":"Evaluating the Diagnostic Accuracy of an AI\u2010Driven Platform for Assessing Endodontic Treatment Outcomes Using Panoramic Radiographs: A Preliminary Study","volume":"13","author":"Kazimierczak W.","year":"2024","journal-title":"Journal of Clinical Medicine"},{"issue":"5","key":"e_1_2_12_16_1","doi-asserted-by":"crossref","first-page":"1122","DOI":"10.1016\/j.cell.2018.02.010","article-title":"Identifying Medical Diagnoses and Treatable Diseases by Image\u2010Based Deep Learning","volume":"172","author":"Kermany D. S.","year":"2018","journal-title":"Cell"},{"key":"e_1_2_12_17_1","doi-asserted-by":"crossref","first-page":"100146","DOI":"10.1016\/j.cmpbup.2024.100146","article-title":"AI in Diagnostic Imaging: Revolutionising Accuracy and Efficiency","volume":"5","author":"Khalifa M.","year":"2024","journal-title":"Computer Methods and Programs in Biomedicine"},{"issue":"6","key":"e_1_2_12_18_1","doi-asserted-by":"crossref","first-page":"509","DOI":"10.1046\/j.1365-2591.2000.00381.x","article-title":"Periapical Status and Quality of Root Fillings and Coronal Restorations in a Danish Population","volume":"33","author":"Kirkevang L. L.","year":"2000","journal-title":"International Endodontic Journal"},{"issue":"5","key":"e_1_2_12_19_1","doi-asserted-by":"crossref","first-page":"827","DOI":"10.1016\/j.joen.2020.12.020","article-title":"Artificial Intelligence for Fast and Accurate 3\u2010Dimensional Tooth Segmentation on Cone\u2010Beam Computed Tomography","volume":"47","author":"Lahoud P.","year":"2021","journal-title":"Journal of Endodontics"},{"issue":"2","key":"e_1_2_12_20_1","doi-asserted-by":"crossref","first-page":"187","DOI":"10.14219\/jada.archive.2005.0140","article-title":"Do Procedural Errors Cause Endodontic Treatment Failure?","volume":"136","author":"Lin L. M.","year":"2005","journal-title":"Journal of the American Dental Association"},{"issue":"1","key":"e_1_2_12_21_1","doi-asserted-by":"crossref","first-page":"26","DOI":"10.1016\/S0099-2399(06)80553-4","article-title":"A Comparison of Four Instrumentation Techniques on Apical Canal Transportation","volume":"21","author":"Luiten D. J.","year":"1995","journal-title":"Journal of Endodontics"},{"issue":"11","key":"e_1_2_12_22_1","doi-asserted-by":"crossref","first-page":"1566","DOI":"10.1111\/iej.14128","article-title":"Artificial Intelligence in Endodontics: Data Preparation, Clinical Applications, Ethical Considerations, Limitations, and Future Directions","volume":"57","author":"Mohammad\u2010Rahimi H.","year":"2024","journal-title":"International Endodontic Journal"},{"issue":"8","key":"e_1_2_12_23_1","doi-asserted-by":"crossref","first-page":"996","DOI":"10.1111\/iej.14075","article-title":"PRIDASE 2024 Guidelines for Reporting Diagnostic Accuracy Studies in Endodontics: A Consensus\u2010Based Development","volume":"57","author":"Nagendrababu V.","year":"2024","journal-title":"International Endodontic Journal"},{"issue":"7","key":"e_1_2_12_24_1","doi-asserted-by":"crossref","first-page":"583","DOI":"10.1111\/j.1365-2591.2011.01872.x","article-title":"A Prospective Study of the Factors Affecting Outcomes of Nonsurgical Root Canal Treatment: Part 1: Periapical Health","volume":"44","author":"Ng Y. L.","year":"2011","journal-title":"International Endodontic Journal"},{"key":"e_1_2_12_25_1","doi-asserted-by":"publisher","DOI":"10.1111\/iej.70065"},{"issue":"12","key":"e_1_2_12_26_1","doi-asserted-by":"crossref","first-page":"1675","DOI":"10.1111\/iej.13187","article-title":"European Society of Endodontology Position Statement: Use of Cone Beam Computed Tomography in Endodontics","volume":"52","author":"Patel S.","year":"2019","journal-title":"International Endodontic Journal"},{"issue":"10","key":"e_1_2_12_27_1","doi-asserted-by":"crossref","first-page":"818","DOI":"10.1111\/j.1365-2591.2007.01299.x","article-title":"The Potential Applications of Cone Beam Computed Tomography in the Management of Endodontic Problems","volume":"40","author":"Patel S.","year":"2007","journal-title":"International Endodontic Journal"},{"issue":"1","key":"e_1_2_12_28_1","doi-asserted-by":"crossref","first-page":"4001","DOI":"10.1038\/s41598-023-31099-5","article-title":"Image Quality for Visualization of Cracks and Fine Endodontic Structures Using 10 CBCT Devices With Various Scanning Protocols and Artefact Conditions","volume":"13","author":"Pinto J. C.","year":"2023","journal-title":"Scientific Reports"},{"issue":"2","key":"e_1_2_12_29_1","doi-asserted-by":"crossref","first-page":"77","DOI":"10.1016\/S0099-2399(97)80250-6","article-title":"Cyclic Fatigue Testing of Nickel\u2010Titanium Endodontic Instruments","volume":"23","author":"Pruett J. P.","year":"1997","journal-title":"Journal of Endodontics"},{"key":"e_1_2_12_30_1","doi-asserted-by":"crossref","first-page":"e928758","DOI":"10.12659\/MSM.928758","article-title":"Analysis of Root Canal Curvature and Root Canal Morphology of Maxillary Posterior Teeth in Guizhou, China","volume":"27","author":"Qiao X.","year":"2021","journal-title":"Medical Science Monitor: International Medical Journal of Experimental and Clinical Research"},{"issue":"3","key":"e_1_2_12_31_1","doi-asserted-by":"crossref","first-page":"57","DOI":"10.4103\/2321-4619.168733","article-title":"A Brief Review of the Methods Used to Determine the Curvature of Root Canals","volume":"3","author":"Rashid H.","year":"2015","journal-title":"Journal of Restorative Dentistry"},{"key":"e_1_2_12_32_1","doi-asserted-by":"crossref","first-page":"271","DOI":"10.1016\/0030-4220(71)90230-1","article-title":"A Comparison of Canal Preparations in Straight and Curved Root Canals","volume":"32","author":"Schneider S. W.","year":"1971","journal-title":"Oral Surgery, Oral Medicine, and Oral Pathology"},{"key":"e_1_2_12_33_1","doi-asserted-by":"crossref","first-page":"769","DOI":"10.1177\/0022034520915714","article-title":"Artificial Intelligence in Dentistry: Chances and Challenges","volume":"99","author":"Schwendicke F.","year":"2020","journal-title":"Journal of Dental Research"},{"key":"e_1_2_12_34_1","doi-asserted-by":"crossref","first-page":"650","DOI":"10.1007\/s00784-024-06009-2","article-title":"AI\u2010Driven Segmentation of the Pulp Cavity System in Mandibular Molars on CBCT Images Using Convolutional Neural Networks","volume":"28","author":"Slim M. L.","year":"2024","journal-title":"Clinical Oral Investigations"},{"issue":"1","key":"e_1_2_12_35_1","doi-asserted-by":"crossref","first-page":"16","DOI":"10.1111\/j.1747-4477.2006.00003.x","article-title":"Determination of Root Canal Curvatures Before and After Canal Preparation (Part II): A Method Based on Numeric Calculus","volume":"32","author":"Sonntag D.","year":"2006","journal-title":"Australian Endodontic Journal"},{"issue":"1","key":"e_1_2_12_36_1","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1016\/j.joen.2025.09.008","article-title":"AAE and AAOMR Joint Position Statement: Use of Cone\u2010Beam Computed Tomography in Endodontics 2025 Update","volume":"52","author":"Sousa Melo S. L.","year":"2026","journal-title":"Journal of Endodontics"},{"issue":"4","key":"e_1_2_12_37_1","doi-asserted-by":"crossref","first-page":"508","DOI":"10.1016\/j.oooo.2015.07.033","article-title":"AAE and AAOMR Joint Position Statement: Use of Cone Beam Computed Tomography in Endodontics 2015 Update","volume":"120","author":"Special Committee to Revise the Joint AAE\/AAOMR Position Statement on use of CBCT in Endodontics","year":"2015","journal-title":"Oral Surgery, Oral Medicine, Oral Pathology and Oral Radiology"},{"issue":"4","key":"e_1_2_12_38_1","doi-asserted-by":"crossref","first-page":"e240300","DOI":"10.1148\/ryai.240300","article-title":"Checklist for Artificial Intelligence in Medical Imaging (CLAIM): 2024 Update","volume":"6","author":"Tejani A. S.","year":"2024","journal-title":"Radiology. Artificial Intelligence"},{"issue":"1","key":"e_1_2_12_39_1","doi-asserted-by":"crossref","first-page":"449","DOI":"10.1186\/s12903-021-01822-7","article-title":"Prevalence of Complex Root Canal Morphology in the Mandibular First and Second Premolars in Thai Population: CBCT Analysis","volume":"21","author":"Thanaruengrong P.","year":"2021","journal-title":"BMC Oral Health"},{"key":"e_1_2_12_40_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2512.02867"},{"key":"e_1_2_12_41_1","first-page":"256","volume-title":"Endodontic Therapy","author":"Weine F. S.","year":"1982"},{"key":"e_1_2_12_42_1","first-page":"118","article-title":"Reliability of Two Methods on Measuring Root Canal Curvature","volume":"3","author":"Zhu Y.","year":"2003","journal-title":"International Chinese Journal of Dentistry"}],"container-title":["International Endodontic Journal"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/iej.70281","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/iej.70281","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/iej.70281","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,28]],"date-time":"2026-09-28T09:43:32Z","timestamp":1790588612000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/iej.70281"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,28]]},"references-count":41,"alternative-id":["10.1111\/iej.70281"],"URL":"https:\/\/doi.org\/10.1111\/iej.70281","archive":["Portico"],"relation":{},"ISSN":["0143-2885","1365-2591"],"issn-type":[{"value":"0143-2885","type":"print"},{"value":"1365-2591","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,28]]},"assertion":[{"value":"2026-03-25","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-17","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2026-09-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"iej.70281"}}