A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI) Part 2: Analysis of the Position of the Hyoid Bone on Panoramic Radiographs
Background: Oral frailty is associated with systemic frailty. The vertical position of the hyoid bone is important when considering the risk of dysphagia. However, dentists usually do not focus on this position. Purpose: To create an AI model for detection of the position of the vertical hyoid bone....
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-10-01
|
| Series: | Eng |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2673-4117/4/4/145 |
| _version_ | 1797381283642343424 |
|---|---|
| author | Yukiko Matsuda Emi Ito Migiwa Kuroda Kazuyuki Araki Wataru Nakada Yoshihiko Hayakawa |
| author_facet | Yukiko Matsuda Emi Ito Migiwa Kuroda Kazuyuki Araki Wataru Nakada Yoshihiko Hayakawa |
| author_sort | Yukiko Matsuda |
| collection | DOAJ |
| description | Background: Oral frailty is associated with systemic frailty. The vertical position of the hyoid bone is important when considering the risk of dysphagia. However, dentists usually do not focus on this position. Purpose: To create an AI model for detection of the position of the vertical hyoid bone. Methods: In this study, 1830 hyoid bone images from 915 panoramic radiographs were used for AI learning. The position of the hyoid bone was classified into six types (Types 0, 1, 2, 3, 4, and 5) based on the same criteria as in our previous study. Plan 1 learned all types. In Plan 2, the five types other than Type 0 were learned. To reduce the number of groupings, three classes were formed using combinations of two types in each class. Plan 3 was used for learning all three classes, and Plan 4 was used for learning the two classes other than Class A (Types 0 and 1). Precision, recall, f-values, accuracy, and areas under the precision–recall curves (PR-AUCs) were calculated and comparatively evaluated. Results: Plan 4 showed the highest accuracy and PR-AUC values, of 0.93 and 0.97, respectively. Conclusions: By reducing the number of classes and not learning cases in which the anatomical structure was partially invisible, the vertical hyoid bone was correctly detected. |
| first_indexed | 2024-03-08T20:49:12Z |
| format | Article |
| id | doaj.art-d45d1c3e7b444cb48002202681802dc0 |
| institution | Directory Open Access Journal |
| issn | 2673-4117 |
| language | English |
| last_indexed | 2024-03-08T20:49:12Z |
| publishDate | 2023-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Eng |
| spelling | doaj.art-d45d1c3e7b444cb48002202681802dc02023-12-22T14:06:14ZengMDPI AGEng2673-41172023-10-01442542255210.3390/eng4040145A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI) Part 2: Analysis of the Position of the Hyoid Bone on Panoramic RadiographsYukiko Matsuda0Emi Ito1Migiwa Kuroda2Kazuyuki Araki3Wataru Nakada4Yoshihiko Hayakawa5Division of Radiology, Department of Oral Diagnostic Sciences, Showa University School of Dentistry, 2-1-1 Kitasenzoku, Ohta-ku, Tokyo 145-8515, JapanDivision of Radiology, Department of Oral Diagnostic Sciences, Showa University School of Dentistry, 2-1-1 Kitasenzoku, Ohta-ku, Tokyo 145-8515, JapanDivision of Radiology, Department of Oral Diagnostic Sciences, Showa University School of Dentistry, 2-1-1 Kitasenzoku, Ohta-ku, Tokyo 145-8515, JapanDivision of Radiology, Department of Oral Diagnostic Sciences, Showa University School of Dentistry, 2-1-1 Kitasenzoku, Ohta-ku, Tokyo 145-8515, JapanDepartment of Engineering on Intelligent Machines & Biomechanics, School of Regional Innovation & Social Design Engineering, Faculty of Engineering, Kitami Institute of Technology, 165 Koencho, Kitami 090-8507, Hokkaido, JapanDepartment of Engineering on Intelligent Machines & Biomechanics, School of Regional Innovation & Social Design Engineering, Faculty of Engineering, Kitami Institute of Technology, 165 Koencho, Kitami 090-8507, Hokkaido, JapanBackground: Oral frailty is associated with systemic frailty. The vertical position of the hyoid bone is important when considering the risk of dysphagia. However, dentists usually do not focus on this position. Purpose: To create an AI model for detection of the position of the vertical hyoid bone. Methods: In this study, 1830 hyoid bone images from 915 panoramic radiographs were used for AI learning. The position of the hyoid bone was classified into six types (Types 0, 1, 2, 3, 4, and 5) based on the same criteria as in our previous study. Plan 1 learned all types. In Plan 2, the five types other than Type 0 were learned. To reduce the number of groupings, three classes were formed using combinations of two types in each class. Plan 3 was used for learning all three classes, and Plan 4 was used for learning the two classes other than Class A (Types 0 and 1). Precision, recall, f-values, accuracy, and areas under the precision–recall curves (PR-AUCs) were calculated and comparatively evaluated. Results: Plan 4 showed the highest accuracy and PR-AUC values, of 0.93 and 0.97, respectively. Conclusions: By reducing the number of classes and not learning cases in which the anatomical structure was partially invisible, the vertical hyoid bone was correctly detected.https://www.mdpi.com/2673-4117/4/4/145AI modeldysphagiapanoramic radiographvertical hyoid bone position |
| spellingShingle | Yukiko Matsuda Emi Ito Migiwa Kuroda Kazuyuki Araki Wataru Nakada Yoshihiko Hayakawa A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI) Part 2: Analysis of the Position of the Hyoid Bone on Panoramic Radiographs Eng AI model dysphagia panoramic radiograph vertical hyoid bone position |
| title | A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI) Part 2: Analysis of the Position of the Hyoid Bone on Panoramic Radiographs |
| title_full | A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI) Part 2: Analysis of the Position of the Hyoid Bone on Panoramic Radiographs |
| title_fullStr | A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI) Part 2: Analysis of the Position of the Hyoid Bone on Panoramic Radiographs |
| title_full_unstemmed | A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI) Part 2: Analysis of the Position of the Hyoid Bone on Panoramic Radiographs |
| title_short | A Basic Study for Predicting Dysphagia in Panoramic X-ray Images Using Artificial Intelligence (AI) Part 2: Analysis of the Position of the Hyoid Bone on Panoramic Radiographs |
| title_sort | basic study for predicting dysphagia in panoramic x ray images using artificial intelligence ai part 2 analysis of the position of the hyoid bone on panoramic radiographs |
| topic | AI model dysphagia panoramic radiograph vertical hyoid bone position |
| url | https://www.mdpi.com/2673-4117/4/4/145 |
| work_keys_str_mv | AT yukikomatsuda abasicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT emiito abasicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT migiwakuroda abasicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT kazuyukiaraki abasicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT watarunakada abasicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT yoshihikohayakawa abasicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT yukikomatsuda basicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT emiito basicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT migiwakuroda basicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT kazuyukiaraki basicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT watarunakada basicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs AT yoshihikohayakawa basicstudyforpredictingdysphagiainpanoramicxrayimagesusingartificialintelligenceaipart2analysisofthepositionofthehyoidboneonpanoramicradiographs |