{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,22]],"date-time":"2026-09-22T03:20:18Z","timestamp":1790047218450,"version":"4.0.1"},"reference-count":37,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T00:00:00Z","timestamp":1733356800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"funder":[{"name":"Suzhou \u201cMedical Health Science and Technology Innovation\u201d Project","award":["SKY2022030"],"award-info":[{"award-number":["SKY2022030"]}]},{"name":"Suzhou \u201cMedical Health Science and Technology Innovation\u201d Project","award":["SKY2022030"],"award-info":[{"award-number":["SKY2022030"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>This study aimed to develop a deep learning system for the detection of three-rooted mandibular first molars (MFMs) on panoramic radiographs and to assess its diagnostic performance. Panoramic radiographs, together with cone beam computed tomographic (CBCT) images of the same subjects, were retrospectively collected from 730 patients, encompassing a total of 1444 MFMs (367 teeth were three-rooted and the remaining 1077 teeth were two-rooted). Five convolutional neural network (CNN) models (ResNet-101 and \u2212\u200950, DenseNet-201, MobileNet-v3 and Inception-v3) were employed to classify three- and two-rooted MFMs on the panoramic radiographs. The diagnostic performance of each model was evaluated using standard metrics, including accuracy, sensitivity, specificity, precision, negative predictive value,\u00a0and F1 score. Receiver operating characteristic (ROC) curve analyses were performed, with the CBCT examination taken as the gold standard.<\/jats:p>\n                  <jats:p>\n                    Among the five CNN models evaluated, ResNet-101 demonstrated superior diagnostic performance, and the AUC value attained was 0.907, significantly higher than that of all other models (all\n                    <jats:italic>P<\/jats:italic>\n                    \u2009&lt;\u20090.01). The accuracy, sensitivity, and specificity were 87.5%, 83.6%, and 88.9%, respectively. DenseNet-201, however, showed the lowest diagnostic performance among the five models (all\n                    <jats:italic>P<\/jats:italic>\n                    \u2009&lt;\u20090.01), with an AUC value of 0.701 and an accuracy of 73.2%. Overall, the performance of the CNNs diminished when using image patches containing only the distal half of MFMs, with AUC values ranging between 0.680 and 0.800. In contrast, the diagnostic performance of the two clinicians was poorer, with AUC values of only 0.680 and 0.632, respectively. In conclusion, the CNN-based deep learning system exhibited a high level of accuracy in the detection of three-rooted MFMs on panoramic radiographs.\n                  <\/jats:p>","DOI":"10.1038\/s41598-024-82378-8","type":"journal-article","created":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T12:15:13Z","timestamp":1733400913000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Detection of three-rooted mandibular first molars on panoramic radiographs using deep learning"],"prefix":"10.1038","volume":"14","author":[{"given":"Long","family":"Jin","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyuan","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bingbing","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zezheng","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panpan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongchun","family":"Gu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,12,5]]},"reference":[{"key":"82378_CR1","doi-asserted-by":"publisher","first-page":"1308","DOI":"10.1016\/j.joen.2023.06.011","volume":"49","author":"FP Hatipo\u011flu","year":"2023","unstructured":"Hatipo\u011flu, F. P. et al. Assessment of the prevalence of Radix Entomolaris and distolingual canal in mandibular first molars in 15 countries: A multinational cross-sectional study with meta-analysis. J. Endod. 49, 1308\u20131318 (2023).","journal-title":"J. Endod"},{"key":"82378_CR2","doi-asserted-by":"publisher","first-page":"990","DOI":"10.1016\/j.joen.2010.02.030","volume":"36","author":"Y Gu","year":"2010","unstructured":"Gu, Y. et al. Root canal morphology of permanent three-rooted mandibular first molars\u2013part I: Pulp floor and root canal system. J. Endod. 36, 990\u2013994 (2010).","journal-title":"J. Endod"},{"key":"82378_CR3","doi-asserted-by":"publisher","first-page":"1341","DOI":"10.1016\/j.joen.2010.04.025","volume":"36","author":"Y Gu","year":"2010","unstructured":"Gu, Y., Lu, Q., Wang, P. & Ni, L. Root canal morphology of permanent three-rooted mandibular first molars: Part II\u2013measurement of root canal curvatures. J. Endod. 36, 1341\u20131346 (2010).","journal-title":"J. Endod"},{"key":"82378_CR4","doi-asserted-by":"publisher","first-page":"329","DOI":"10.1186\/s12903-022-02378-w","volume":"22","author":"C Jiang","year":"2022","unstructured":"Jiang, C. et al. Investigation of three-rooted deciduous mandibular second molars in a Chinese population using cone-beam computed tomography. BMC Oral Health. 22, 329 (2022).","journal-title":"BMC Oral Health"},{"key":"82378_CR5","doi-asserted-by":"publisher","first-page":"503","DOI":"10.1016\/j.joen.2008.12.013","volume":"35","author":"MG Tu","year":"2009","unstructured":"Tu, M. G. et al. Detection of permanent three-rooted mandibular first molars by cone-beam computed tomography imaging in Taiwanese individuals. J. Endod. 35, 503\u2013507 (2009).","journal-title":"J. Endod"},{"key":"82378_CR6","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1186\/s12903-020-01218-z","volume":"20","author":"X Qiao","year":"2020","unstructured":"Qiao, X. et al. Prevalence of middle mesial canal and radix entomolaris of mandibular first permanent molars in a western Chinese population: An in vivo cone-beam computed tomographic study. BMC Oral Health. 20, 224 (2020).","journal-title":"BMC Oral Health"},{"key":"82378_CR7","doi-asserted-by":"publisher","first-page":"1096","DOI":"10.1016\/j.joen.2018.04.001","volume":"44","author":"JNR Martins","year":"2018","unstructured":"Martins, J. N. R., Gu, Y., Marques, D., Francisco, H. & Caram\u00eas, J. Differences on the root and root canal morphologies between Asian and caucasian ethnic groups analyzed by cone beam computed tomography. J. Endod. 44, 1096\u20131104 (2018).","journal-title":"J. Endod"},{"key":"82378_CR8","doi-asserted-by":"publisher","first-page":"656","DOI":"10.1186\/s12903-023-03376-2","volume":"23","author":"B Bai","year":"2023","unstructured":"Bai, B. et al. Ex vivo detection of mandibular incisors\u2019 root canal morphology using CBCT with 4 different voxel sizes and micro-computed tomography. BMC Oral Health. 23, 656 (2023).","journal-title":"BMC Oral Health"},{"key":"82378_CR9","first-page":"20190138","volume":"49","author":"D Sandler","year":"2020","unstructured":"Sandler, D. & O\u2019Neill, P. Deep learning in dental image analysis: A review. Dentomaxillofac Radiol. 49, 20190138 (2020).","journal-title":"Dentomaxillofac Radiol."},{"key":"82378_CR10","doi-asserted-by":"publisher","first-page":"104581","DOI":"10.1016\/j.jdent.2023.104581","volume":"135","author":"J Ver Berne","year":"2023","unstructured":"Ver Berne, J., Saadi, S. B., Politis, C., &           Jacobs. R. A deep learning approach for radiological detection and classification of radicular cysts and periapical granulomas. J. Dent. 135, 104581 (2023).","journal-title":"J. Dent."},{"key":"82378_CR11","doi-asserted-by":"publisher","first-page":"12609","DOI":"10.1038\/s41598-021-92121-2","volume":"11","author":"S Vinayahalingam","year":"2021","unstructured":"Vinayahalingam, S. et al. Classification of caries in third molars on panoramic radiographs using deep learning. Sci. Rep. 11, 12609 (2021).","journal-title":"Sci. Rep."},{"key":"82378_CR12","doi-asserted-by":"publisher","first-page":"20180218","DOI":"10.1259\/dmfr.20180218","volume":"48","author":"T Hiraiwa","year":"2019","unstructured":"Hiraiwa, T. et al. A deep-learning artificial intelligence system for assessment of root morphology of the mandibular first molar on panoramic radiography. Dentomaxillofac Radiol. 48, 20180218 (2019).","journal-title":"Dentomaxillofac Radiol."},{"key":"82378_CR13","doi-asserted-by":"publisher","first-page":"914","DOI":"10.1016\/j.joen.2022.04.007","volume":"48","author":"S Yang","year":"2022","unstructured":"Yang, S. et al. Development and validation of a visually explainable deep learning model for classification of C-shaped canals of the mandibular second molars in periapical and panoramic dental radiographs. J. Endod. 48, 914\u2013921 (2022).","journal-title":"J. Endod"},{"key":"82378_CR14","doi-asserted-by":"publisher","first-page":"17373","DOI":"10.1038\/s41598-022-20411-4","volume":"12","author":"L Zhang","year":"2022","unstructured":"Zhang, L. et al. A lightweight convolutional neural network model with receptive field block for C-shaped root canal detection in mandibular second molars. Sci. Rep. 12, 17373 (2022).","journal-title":"Sci. Rep."},{"key":"82378_CR15","doi-asserted-by":"publisher","first-page":"20200513","DOI":"10.1259\/dmfr.20200513","volume":"50","author":"SJ Jeon","year":"2021","unstructured":"Jeon, S. J. et al. Deep-learning for predicting C-shaped canals in mandibular second molars on panoramic radiographs. Dentomaxillofac Radiol. 50, 20200513 (2021).","journal-title":"Dentomaxillofac Radiol."},{"key":"82378_CR16","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. et al. A survey on deep learning in medical image analysis. Med. Image Anal. 42, 60\u201388 (2017).","journal-title":"Med. Image Anal."},{"key":"82378_CR17","first-page":"96","volume":"5","author":"K Moutselos","year":"2019","unstructured":"Moutselos, K., Michopoulou, S. & Tziafas, D. Automated classification of dental images using deep learning. J. Imaging. 5, 96 (2019).","journal-title":"J. Imaging"},{"key":"82378_CR18","doi-asserted-by":"publisher","first-page":"106","DOI":"10.1016\/j.jdent.2018.07.015","volume":"77","author":"JH Lee","year":"2018","unstructured":"Lee, J. H., Kim, D. H., Jeong, S. N. & Choi, S. H. Detection and diagnosis of dental caries using a deep learning-based convolutional neural network algorithm. J. Dent. 77, 106\u2013111 (2018).","journal-title":"J. Dent."},{"key":"82378_CR19","doi-asserted-by":"publisher","first-page":"337","DOI":"10.1007\/s11282-019-00409-x","volume":"36","author":"M Fukuda","year":"2020","unstructured":"Fukuda, M. et al. Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiography. Oral Radiol. 36, 337\u2013343 (2020).","journal-title":"Oral Radiol."},{"key":"82378_CR20","doi-asserted-by":"publisher","first-page":"680","DOI":"10.1111\/iej.13265","volume":"53","author":"K Orhan","year":"2020","unstructured":"Orhan, K., Bayrakdar, I. S., Ezhov, M., Kravtsov, A. & \u00d6zy\u00fcrek, T. Evaluation of artificial intelligence for detecting periapical pathosis on cone-beam computed tomography scans. Int. Endod J. 53, 680\u2013689 (2020).","journal-title":"Int. Endod J."},{"key":"82378_CR21","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1016\/j.joen.2022.12.007","volume":"49","author":"S Sadr","year":"2022","unstructured":"Sadr, S. et al. Deep learning for detection of periapical radiolucent lesions: a systematic review and meta-analysis of diagnostic test accuracy. J. Endod. 49, 248\u2013261e3 (2022).","journal-title":"J. Endod"},{"key":"82378_CR22","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1186\/s12903-022-02436-3","volume":"22","author":"G Alotaibi","year":"2022","unstructured":"Alotaibi, G. et al. Artificial intelligence (AI) diagnostic tools: Utilizing a convolutional neural network (CNN) to assess periodontal bone level radiographically-a retrospective study. BMC Oral Health. 22, 399 (2022).","journal-title":"BMC Oral Health"},{"key":"82378_CR23","doi-asserted-by":"crossref","unstructured":"Ariji, Y. et al. Two-step deep learning models for detection and identification of the manufacturers and types of dental implants on panoramic radiographs. Odontology (2024).","DOI":"10.1007\/s10266-024-00989-z"},{"key":"82378_CR24","doi-asserted-by":"publisher","first-page":"436","DOI":"10.1038\/nature14539","volume":"521","author":"Y LeCun","year":"2015","unstructured":"LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436\u2013444 (2015).","journal-title":"Nature"},{"key":"82378_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Deep residual learning for image recognition. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 770\u2013778 (2016).","DOI":"10.1109\/CVPR.2016.90"},{"key":"82378_CR26","doi-asserted-by":"publisher","first-page":"95","DOI":"10.3390\/computers12050095","volume":"12","author":"P Podder","year":"2023","unstructured":"Podder, P. et al. Rethinking densely connected convolutional networks for diagnosing infectious diseases. Computers 12, 95 (2023).","journal-title":"Computers"},{"key":"82378_CR27","unstructured":"Howard, A. et al. Searching for MobileNetV3. arXiv preprint arXiv:1905.02244 (2019)."},{"key":"82378_CR28","doi-asserted-by":"crossref","unstructured":"Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J. & Wojna, Z. Rethinking the Inception architecture for computer vision. arXiv Preprint arXiv :151200567 (2015).","DOI":"10.1109\/CVPR.2016.308"},{"key":"82378_CR29","doi-asserted-by":"publisher","first-page":"27","DOI":"10.1631\/FITEE.1700808","volume":"19","author":"Q Zhang","year":"2018","unstructured":"Zhang, Q. & Zhu, S. C. Visual interpretability for deep learning: A survey. Front. Inf. Technol. Electron. Eng. 19, 27\u201339 (2018).","journal-title":"Front. Inf. Technol. Electron. Eng."},{"key":"82378_CR30","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1007\/s11263-019-01228-7","volume":"128","author":"RR Selvaraju","year":"2020","unstructured":"Selvaraju, R. R. et al. Grad-CAM: visual explanations from deep networks via gradient-based localization. Int. J. Comput. Vis. 128, 336\u2013359 (2020).","journal-title":"Int. J. Comput. Vis."},{"key":"82378_CR31","first-page":"1834","volume":"37","author":"Z Zhang","year":"2018","unstructured":"Zhang, Z., Xie, Y., Xing, F., McGough, M. & Yang, L. MDNet: a semantically and visually interpretable medical image diagnosis network. IEEE Trans. Med. Imaging. 37, 1834\u20131843 (2018).","journal-title":"IEEE Trans. Med. Imaging"},{"key":"82378_CR32","doi-asserted-by":"publisher","first-page":"789","DOI":"10.1111\/j.1365-2591.2004.00870.x","volume":"37","author":"RJ De Moor","year":"2004","unstructured":"De Moor, R. J., Deroose, C. A. & Calberson, F. L. The radix entomolaris in mandibular first molars: An endodontic challenge. Int. Endod J. 37, 789\u2013799 (2004).","journal-title":"Int. Endod J."},{"key":"82378_CR33","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1038\/sj.bdj.4805710","volume":"159","author":"RT Walker","year":"1985","unstructured":"Walker, R. T. & Quackenbush, L. E. Three-root lower first permanent molars in Hong-Kong Chinese. Br. Dent. J. 159, 298\u2013299 (1985).","journal-title":"Br. Dent. J."},{"key":"82378_CR34","doi-asserted-by":"publisher","first-page":"1163","DOI":"10.1016\/j.joen.2007.07.020","volume":"33","author":"MG Tu","year":"2007","unstructured":"Tu, M. G. et al. Prevalence of three-rooted mandibular first molars among Taiwanese individuals. J. Endod. 33, 1163\u20131166 (2007).","journal-title":"J. Endod"},{"key":"82378_CR35","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1177\/00220345211020265","volume":"101","author":"F Schwendicke","year":"2022","unstructured":"Schwendicke, F. & Krois, J. Data dentistry: how data are changing clinical care and research. J. Dent. Res. 101, 21\u201329 (2022).","journal-title":"J. Dent. Res."},{"key":"82378_CR36","first-page":"012055","volume":"1482","author":"B Aubakirova","year":"2020","unstructured":"Aubakirova, B., Lee, S. J., Kim, Y. H. & Kim, S. H. Weaknesses and limitations of Grad-CAM in deep learning. J. Phys. Conf. Ser. 1482, 012055 (2020).","journal-title":"J. Phys. Conf. Ser."},{"key":"82378_CR37","doi-asserted-by":"publisher","first-page":"1037","DOI":"10.1167\/9.8.1037","volume":"9","author":"L Fei-Fei","year":"2010","unstructured":"Fei-Fei, L., Deng, J., Li, K. & ImageNet Constructing a large-scale image database. J. Vis. 9, 1037 (2010).","journal-title":"J. Vis."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-82378-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-82378-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-82378-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,5]],"date-time":"2024-12-05T13:09:10Z","timestamp":1733404150000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-024-82378-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,5]]},"references-count":37,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["82378"],"URL":"https:\/\/doi.org\/10.1038\/s41598-024-82378-8","relation":{},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,5]]},"assertion":[{"value":"15 August 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 December 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"5 December 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}},{"value":"Approval for this study was obtained from the Institutional Ethics Committee (IEC) for Human Research (Issuing Number: KY2022-089-01). Due to the retrospective nature of the study, the IEC of Suzhou Ninth People\u2019s Hospital waived the need of obtaining informed consent. The study was performed in accordance with the Declaration of Helsinki.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}}],"article-number":"30392"}}