Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system
Abstract Although panoramic radiography has a role in the examination of patients with cleft alveolus (CA), its appearances is sometimes difficult to interpret. The aims of this study were to develop a computer-aided diagnosis system for diagnosing the CA status on panoramic radiographs using a deep...
| Main Authors: | , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2021-08-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-021-95653-9 |
| _version_ | 1819202793437659136 |
|---|---|
| author | Chiaki Kuwada Yoshiko Ariji Yoshitaka Kise Takuma Funakoshi Motoki Fukuda Tsutomu Kuwada Kenichi Gotoh Eiichiro Ariji |
| author_facet | Chiaki Kuwada Yoshiko Ariji Yoshitaka Kise Takuma Funakoshi Motoki Fukuda Tsutomu Kuwada Kenichi Gotoh Eiichiro Ariji |
| author_sort | Chiaki Kuwada |
| collection | DOAJ |
| description | Abstract Although panoramic radiography has a role in the examination of patients with cleft alveolus (CA), its appearances is sometimes difficult to interpret. The aims of this study were to develop a computer-aided diagnosis system for diagnosing the CA status on panoramic radiographs using a deep learning object detection technique with and without normal data in the learning process, to verify its performance in comparison to human observers, and to clarify some characteristic appearances probably related to the performance. The panoramic radiographs of 383 CA patients with cleft palate (CA with CP) or without cleft palate (CA only) and 210 patients without CA (normal) were used to create two models on the DetectNet. The models 1 and 2 were developed based on the data without and with normal subjects, respectively, to detect the CAs and classify them into with or without CP. The model 2 reduced the false positive rate (1/30) compared to the model 1 (12/30). The overall accuracy of Model 2 was higher than Model 1 and human observers. The model created in this study appeared to have the potential to detect and classify CAs on panoramic radiographs, and might be useful to assist the human observers. |
| first_indexed | 2024-12-23T04:09:40Z |
| format | Article |
| id | doaj.art-a493db1ced3f4929b493e7338b127a10 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-12-23T04:09:40Z |
| publishDate | 2021-08-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-a493db1ced3f4929b493e7338b127a102022-12-21T18:00:33ZengNature PortfolioScientific Reports2045-23222021-08-0111111010.1038/s41598-021-95653-9Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning systemChiaki Kuwada0Yoshiko Ariji1Yoshitaka Kise2Takuma Funakoshi3Motoki Fukuda4Tsutomu Kuwada5Kenichi Gotoh6Eiichiro Ariji7Department of Oral and Maxillofacial Radiology, Aichi Gakuin University School of DentistryDepartment of Oral and Maxillofacial Radiology, Aichi Gakuin University School of DentistryDepartment of Oral and Maxillofacial Radiology, Aichi Gakuin University School of DentistryDepartment of Oral and Maxillofacial Radiology, Aichi Gakuin University School of DentistryDepartment of Oral and Maxillofacial Radiology, Aichi Gakuin University School of DentistryDivision of Radiological Technology, Dental Hospital, Aichi-Gakuin UniversityDivision of Radiological Technology, Dental Hospital, Aichi-Gakuin UniversityDepartment of Oral and Maxillofacial Radiology, Aichi Gakuin University School of DentistryAbstract Although panoramic radiography has a role in the examination of patients with cleft alveolus (CA), its appearances is sometimes difficult to interpret. The aims of this study were to develop a computer-aided diagnosis system for diagnosing the CA status on panoramic radiographs using a deep learning object detection technique with and without normal data in the learning process, to verify its performance in comparison to human observers, and to clarify some characteristic appearances probably related to the performance. The panoramic radiographs of 383 CA patients with cleft palate (CA with CP) or without cleft palate (CA only) and 210 patients without CA (normal) were used to create two models on the DetectNet. The models 1 and 2 were developed based on the data without and with normal subjects, respectively, to detect the CAs and classify them into with or without CP. The model 2 reduced the false positive rate (1/30) compared to the model 1 (12/30). The overall accuracy of Model 2 was higher than Model 1 and human observers. The model created in this study appeared to have the potential to detect and classify CAs on panoramic radiographs, and might be useful to assist the human observers.https://doi.org/10.1038/s41598-021-95653-9 |
| spellingShingle | Chiaki Kuwada Yoshiko Ariji Yoshitaka Kise Takuma Funakoshi Motoki Fukuda Tsutomu Kuwada Kenichi Gotoh Eiichiro Ariji Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system Scientific Reports |
| title | Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system |
| title_full | Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system |
| title_fullStr | Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system |
| title_full_unstemmed | Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system |
| title_short | Detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system |
| title_sort | detection and classification of unilateral cleft alveolus with and without cleft palate on panoramic radiographs using a deep learning system |
| url | https://doi.org/10.1038/s41598-021-95653-9 |
| work_keys_str_mv | AT chiakikuwada detectionandclassificationofunilateralcleftalveoluswithandwithoutcleftpalateonpanoramicradiographsusingadeeplearningsystem AT yoshikoariji detectionandclassificationofunilateralcleftalveoluswithandwithoutcleftpalateonpanoramicradiographsusingadeeplearningsystem AT yoshitakakise detectionandclassificationofunilateralcleftalveoluswithandwithoutcleftpalateonpanoramicradiographsusingadeeplearningsystem AT takumafunakoshi detectionandclassificationofunilateralcleftalveoluswithandwithoutcleftpalateonpanoramicradiographsusingadeeplearningsystem AT motokifukuda detectionandclassificationofunilateralcleftalveoluswithandwithoutcleftpalateonpanoramicradiographsusingadeeplearningsystem AT tsutomukuwada detectionandclassificationofunilateralcleftalveoluswithandwithoutcleftpalateonpanoramicradiographsusingadeeplearningsystem AT kenichigotoh detectionandclassificationofunilateralcleftalveoluswithandwithoutcleftpalateonpanoramicradiographsusingadeeplearningsystem AT eiichiroariji detectionandclassificationofunilateralcleftalveoluswithandwithoutcleftpalateonpanoramicradiographsusingadeeplearningsystem |