Literature DB >> 33547985

Differential diagnosis of ameloblastoma and odontogenic keratocyst by machine learning of panoramic radiographs.

Zijia Liu1, Jiannan Liu2, Guangtao Zhai3, Jing Han4, Zijie Zhou2, Qiaoyu Zhang2, Hao Wu5.   

Abstract

PURPOSE: The differentiation of the ameloblastoma and odontogenic keratocyst directly affects the formulation of surgical plans, while the results of differential diagnosis by imaging alone are not satisfactory. This paper aimed to propose an algorithm based on convolutional neural networks (CNN) structure to significantly improve the classification accuracy of these two tumors.
METHODS: A total of 420 digital panoramic radiographs provided by 401 patients were acquired from the Shanghai Ninth People's Hospital. Each of them was cropped to a patch as a region of interest by radiologists. Furthermore, inverse logarithm transformation and histogram equalization were employed to increase the contrast of the region of interest (ROI). To alleviate overfitting, random rotation and flip transform as data augmentation algorithms were adopted to the training dataset. We provided a CNN structure based on a transfer learning algorithm, which consists of two branches in parallel. The output of the network is a two-dimensional vector representing the predicted scores of ameloblastoma and odontogenic keratocyst, respectively.
RESULTS: The proposed network achieved an accuracy of 90.36% (AUC = 0.946), while sensitivity and specificity were 92.88% and 87.80%, respectively. Two other networks named VGG-19 and ResNet-50 and a network trained from scratch were also used in the experiment, which achieved accuracy of 80.72%, 78.31%, and 69.88%, respectively.
CONCLUSIONS: We proposed an algorithm that significantly improves the differential diagnosis accuracy of ameloblastoma and odontogenic keratocyst and has the utility to provide a reliable recommendation to the oral maxillofacial specialists before surgery.

Entities:  

Keywords:  Ameloblastoma; Deep learning; Machine learning; Odontogenic keratocyst

Mesh:

Year:  2021        PMID: 33547985      PMCID: PMC7946691          DOI: 10.1007/s11548-021-02309-0

Source DB:  PubMed          Journal:  Int J Comput Assist Radiol Surg        ISSN: 1861-6410            Impact factor:   2.924


  20 in total

1.  Dynamic multislice helical CT of ameloblastoma and odontogenic keratocyst: correlation between contrast enhancement and angiogenesis.

Authors:  Katsuhiko Hayashi; Mitsuhiro Tozaki; Masashi Sugisaki; Nahoko Yoshida; Kunihiko Fukuda; Haruyasu Tanabe
Journal:  J Comput Assist Tomogr       Date:  2002 Nov-Dec       Impact factor: 1.826

2.  Update from the 4th Edition of the World Health Organization Classification of Head and Neck Tumours: Odontogenic and Maxillofacial Bone Tumors.

Authors:  John M Wright; Marilena Vered
Journal:  Head Neck Pathol       Date:  2017-02-28

3.  Discriminating solitary cysts from soft tissue lesions in mammography using a pretrained deep convolutional neural network.

Authors:  Thijs Kooi; Bram van Ginneken; Nico Karssemeijer; Ard den Heeten
Journal:  Med Phys       Date:  2017-03       Impact factor: 4.071

4.  Imaging features contributing to the diagnosis of ameloblastomas and keratocystic odontogenic tumours: logistic regression analysis.

Authors:  Y Ariji; M Morita; A Katsumata; Y Sugita; M Naitoh; M Goto; M Izumi; Y Kise; K Shimozato; K Kurita; H Maeda; E Ariji
Journal:  Dentomaxillofac Radiol       Date:  2011-03       Impact factor: 2.419

5.  Deep learning object detection of maxillary cyst-like lesions on panoramic radiographs: preliminary study.

Authors:  Hirofumi Watanabe; Yoshiko Ariji; Motoki Fukuda; Chiaki Kuwada; Yoshitaka Kise; Michihito Nozawa; Yoshihiko Sugita; Eiichiro Ariji
Journal:  Oral Radiol       Date:  2020-09-19       Impact factor: 1.852

6.  Cystic lesions of the maxillomandibular region: MR imaging distinction of odontogenic keratocysts and ameloblastomas from other cysts.

Authors:  M Minami; T Kaneda; K Ozawa; H Yamamoto; Y Itai; M Ozawa; K Yoshikawa; Y Sasaki
Journal:  AJR Am J Roentgenol       Date:  1996-04       Impact factor: 3.959

Review 7.  Establishing the natural history and growth rate of ameloblastoma with implications for management: systematic review and meta-analysis.

Authors:  Michael P Chae; Nicolas R Smoll; David J Hunter-Smith; Warren Matthew Rozen
Journal:  PLoS One       Date:  2015-02-23       Impact factor: 3.240

8.  Diffusion-Weighted MR Imaging of Unicystic Odontogenic Tumors for Differentiation of Unicystic Ameloblastomas from Keratocystic Odontogenic Tumors.

Authors:  Yifeng Han; Xindong Fan; Lixin Su; Zhenfeng Wang
Journal:  Korean J Radiol       Date:  2018-01-02       Impact factor: 3.500

Review 9.  Odontogenic Keratocyst: Developing a Protocol for Surgical Intervention.

Authors:  Rajesh Ashok Kshirsagar; Rajat Chandrashekhar Bhende; Pratik Hemantkumar Raut; Vrushika Mahajan; Vishal Jugalkishor Tapadiya; Vikram Singh
Journal:  Ann Maxillofac Surg       Date:  2019 Jan-Jun

10.  Deep Learning for Automated Detection of Cyst and Tumors of the Jaw in Panoramic Radiographs.

Authors:  Hyunwoo Yang; Eun Jo; Hyung Jun Kim; In-Ho Cha; Young-Soo Jung; Woong Nam; Jun-Young Kim; Jin-Kyu Kim; Yoon Hyeon Kim; Tae Gyeong Oh; Sang-Sun Han; Hwiyoung Kim; Dongwook Kim
Journal:  J Clin Med       Date:  2020-06-12       Impact factor: 4.241

View more
  3 in total

1.  Radiolucent Lesions of the Jaws: An Attempted Demonstration of the Use of Co-Word Analysis to List Main Similar Pathologies.

Authors:  Andy Wai Kan Yeung
Journal:  Int J Environ Res Public Health       Date:  2022-02-09       Impact factor: 3.390

2.  Improved Diagnostic Accuracy of Ameloblastoma and Odontogenic Keratocyst on Cone-Beam CT by Artificial Intelligence.

Authors:  Zi-Kang Chai; Liang Mao; Hua Chen; Ting-Guan Sun; Xue-Meng Shen; Juan Liu; Zhi-Jun Sun
Journal:  Front Oncol       Date:  2022-01-27       Impact factor: 6.244

Review 3.  Artificial Intelligence in Dentistry-Narrative Review.

Authors:  Agata Ossowska; Aida Kusiak; Dariusz Świetlik
Journal:  Int J Environ Res Public Health       Date:  2022-03-15       Impact factor: 3.390

  3 in total

北京卡尤迪生物科技股份有限公司 © 2022-2023.