Literature DB >> 33405976

Deep-learning for predicting C-shaped canals in mandibular second molars on panoramic radiographs.

Su-Jin Jeon1, Jong-Pil Yun2, Han-Gyeol Yeom3, Woo-Sang Shin2,4, Jong-Hyun Lee2,4, Seung-Hyun Jeong2, Min-Seock Seo1.   

Abstract

OBJECTIVE: The aim of this study was to evaluate the use of a convolutional neural network (CNN) system for predicting C-shaped canals in mandibular second molars on panoramic radiographs.
METHODS: Panoramic and cone beam CT (CBCT) images obtained from June 2018 to May 2020 were screened and 1020 patients were selected. Our dataset of 2040 sound mandibular second molars comprised 887 C-shaped canals and 1153 non-C-shaped canals. To confirm the presence of a C-shaped canal, CBCT images were analyzed by a radiologist and set as the gold standard. A CNN-based deep-learning model for predicting C-shaped canals was built using Xception. The training and test sets were set to 80 to 20%, respectively. Diagnostic performance was evaluated using accuracy, sensitivity, specificity, and precision. Receiver-operating characteristics (ROC) curves were drawn, and the area under the curve (AUC) values were calculated. Further, gradient-weighted class activation maps (Grad-CAM) were generated to localize the anatomy that contributed to the predictions.
RESULTS: The accuracy, sensitivity, specificity, and precision of the CNN model were 95.1, 92.7, 97.0, and 95.9%, respectively. Grad-CAM analysis showed that the CNN model mainly identified root canal shapes converging into the apex to predict the C-shaped canals, while the root furcation was predominantly used for predicting the non-C-shaped canals.
CONCLUSIONS: The deep-learning system had significant accuracy in predicting C-shaped canals of mandibular second molars on panoramic radiographs.

Entities:  

Keywords:  C-shaped canal; Convolutional neural network; Deep learning; Diagnostic imaging; Panoramic radiograph

Mesh:

Year:  2021        PMID: 33405976      PMCID: PMC8231674          DOI: 10.1259/dmfr.20200513

Source DB:  PubMed          Journal:  Dentomaxillofac Radiol        ISSN: 0250-832X            Impact factor:   3.525


  31 in total

1.  Evaluation of periapical radiographs in the recognition of C-shaped mandibular second molars.

Authors:  T Lambrianidis; K Lyroudia; O Pandelidou; A Nicolaou
Journal:  Int Endod J       Date:  2001-09       Impact factor: 5.264

2.  Identification of C-shaped canal in mandibular second molars. Part I: radiographic and anatomical features revealed by intraradicular contrast medium.

Authors:  Wei Fan; Bing Fan; James L Gutmann; Gary S P Cheung
Journal:  J Endod       Date:  2007-07       Impact factor: 4.171

3.  Predicting the configuration of a C-shaped canal system from panoramic radiographs.

Authors:  Hwan-Jun Jung; Sam-Sun Lee; Kyung-Hoe Huh; Won-Jin Yi; Min-Suk Heo; Soon-Chul Choi
Journal:  Oral Surg Oral Med Oral Pathol Oral Radiol Endod       Date:  2010-01

4.  A deep-learning artificial intelligence system for assessment of root morphology of the mandibular first molar on panoramic radiography.

Authors:  Teruhiko Hiraiwa; Yoshiko Ariji; Motoki Fukuda; Yoshitaka Kise; Kazuhiko Nakata; Akitoshi Katsumata; Hiroshi Fujita; Eiichiro Ariji
Journal:  Dentomaxillofac Radiol       Date:  2018-11-09       Impact factor: 2.419

5.  Application of a fully deep convolutional neural network to the automation of tooth segmentation on panoramic radiographs.

Authors:  Jeong-Hee Lee; Sang-Sun Han; Young Hyun Kim; Chena Lee; Inhyeok Kim
Journal:  Oral Surg Oral Med Oral Pathol Oral Radiol       Date:  2019-11-15

Review 6.  C-shaped root canal systems: diagnosis, treatment, and restoration.

Authors:  C E Jerome
Journal:  Gen Dent       Date:  1994 Sep-Oct

7.  Evaluation of an artificial intelligence system for detecting vertical root fracture on panoramic radiography.

Authors:  Motoki Fukuda; Kyoko Inamoto; Naoki Shibata; Yoshiko Ariji; Yudai Yanashita; Shota Kutsuna; Kazuhiko Nakata; Akitoshi Katsumata; Hiroshi Fujita; Eiichiro Ariji
Journal:  Oral Radiol       Date:  2019-09-18       Impact factor: 1.852

8.  Automatic diagnosis for cysts and tumors of both jaws on panoramic radiographs using a deep convolution neural network.

Authors:  Odeuk Kwon; Tae-Hoon Yong; Se-Ryong Kang; Jo-Eun Kim; Kyung-Hoe Huh; Min-Suk Heo; Sam-Sun Lee; Soon-Chul Choi; Won-Jin Yi
Journal:  Dentomaxillofac Radiol       Date:  2020-07-03       Impact factor: 2.419

9.  Automated detection of third molars and mandibular nerve by deep learning.

Authors:  Shankeeth Vinayahalingam; Tong Xi; Stefaan Bergé; Thomas Maal; Guido de Jong
Journal:  Sci Rep       Date:  2019-06-21       Impact factor: 4.379

10.  Deep Learning for the Radiographic Detection of Periodontal Bone Loss.

Authors:  Joachim Krois; Thomas Ekert; Leonie Meinhold; Tatiana Golla; Basel Kharbot; Agnes Wittemeier; Christof Dörfer; Falk Schwendicke
Journal:  Sci Rep       Date:  2019-06-11       Impact factor: 4.379

View more
  3 in total

1.  Deep-learning approach for caries detection and segmentation on dental bitewing radiographs.

Authors:  Ibrahim Sevki Bayrakdar; Kaan Orhan; Serdar Akarsu; Özer Çelik; Samet Atasoy; Adem Pekince; Yasin Yasa; Elif Bilgir; Hande Sağlam; Ahmet Faruk Aslan; Alper Odabaş
Journal:  Oral Radiol       Date:  2021-11-22       Impact factor: 1.882

2.  Automatic segmentation of the temporomandibular joint disc on magnetic resonance images using a deep learning technique.

Authors:  Michihito Nozawa; Hirokazu Ito; Yoshiko Ariji; Motoki Fukuda; Chinami Igarashi; Masako Nishiyama; Nobumi Ogi; Akitoshi Katsumata; Kaoru Kobayashi; Eiichiro Ariji
Journal:  Dentomaxillofac Radiol       Date:  2021-08-04       Impact factor: 2.419

3.  A lightweight convolutional neural network model with receptive field block for C-shaped root canal detection in mandibular second molars.

Authors:  Lijuan Zhang; Feng Xu; Ying Li; Huimin Zhang; Ziyi Xi; Jie Xiang; Bin Wang
Journal:  Sci Rep       Date:  2022-10-17       Impact factor: 4.996

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.