Deep Learning for Predicting the Difficulty Level of Removing the Impacted Mandibular Third Molar
Background: Preoperative assessment of the impacted mandibular third molar (LM3) in a panoramic radiograph is important in surgical planning. The aim of this study was to develop and evaluate a computer-aided visualisation–based deep learning (DL) system using a panoramic radiograph to predict the d...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2025-02-01
|
| Series: | International Dental Journal |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S002065392400193X |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592772394123264 |
|---|---|
| author | Vorapat Trachoo Unchalisa Taetragool Ploypapas Pianchoopat Chatchapon Sukitporn-udom Narapathra Morakrant Kritsasith Warin |
| author_facet | Vorapat Trachoo Unchalisa Taetragool Ploypapas Pianchoopat Chatchapon Sukitporn-udom Narapathra Morakrant Kritsasith Warin |
| author_sort | Vorapat Trachoo |
| collection | DOAJ |
| description | Background: Preoperative assessment of the impacted mandibular third molar (LM3) in a panoramic radiograph is important in surgical planning. The aim of this study was to develop and evaluate a computer-aided visualisation–based deep learning (DL) system using a panoramic radiograph to predict the difficulty level of surgical removal of an impacted LM3. Methods: The study included 1367 LM3 images from 784 patients who presented from 2021–2023 to the University Dental Hospital; images were collected retrospectively. The difficulty level of surgically removing impacted LM3s was assessed via our newly developed DL system, which seamlessly integrated 3 distinct DL models. ResNet101V2 handled binary classification for identifying impacted LM3s in panoramic radiographs, RetinaNet detected the precise location of the impacted LM3, and Vision Transformer performed multiclass image classification to evaluate the difficulty levels of removing the detected impacted LM3. Results: The ResNet101V2 model achieved a classification accuracy of 0.8671. The RetinaNet model demonstrated exceptional detection performance, with a mean average precision of 0.9928. Additionally, the Vision Transformer model delivered an average accuracy of 0.7899 in predicting removal difficulty levels. Conclusions: The development of a 3-phase computer-aided visualisation–based DL system has yielded a very good performance in using panoramic radiographs to predict the difficulty level of surgically removing an impacted LM3. |
| format | Article |
| id | doaj-art-1d4a44c38577420dbedcccd45de64a4c |
| institution | Kabale University |
| issn | 0020-6539 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Dental Journal |
| spelling | doaj-art-1d4a44c38577420dbedcccd45de64a4c2025-01-21T04:12:42ZengElsevierInternational Dental Journal0020-65392025-02-01751144150Deep Learning for Predicting the Difficulty Level of Removing the Impacted Mandibular Third MolarVorapat Trachoo0Unchalisa Taetragool1Ploypapas Pianchoopat2Chatchapon Sukitporn-udom3Narapathra Morakrant4Kritsasith Warin5Faculty of Dentistry, Chulalongkorn University, Bangkok, ThailandDepartment of Computer Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok, ThailandDepartment of Computer Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok, ThailandDepartment of Computer Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok, ThailandDepartment of Computer Engineering, Faculty of Engineering, King Mongkut's University of Technology Thonburi, Bangkok, ThailandFaculty of Dentistry, Thammasat University, Pathum Thani, Thailand; Corresponding author. Faculty of Dentistry, Thammasat University, Pathum Thani, 12120 Thailand.Background: Preoperative assessment of the impacted mandibular third molar (LM3) in a panoramic radiograph is important in surgical planning. The aim of this study was to develop and evaluate a computer-aided visualisation–based deep learning (DL) system using a panoramic radiograph to predict the difficulty level of surgical removal of an impacted LM3. Methods: The study included 1367 LM3 images from 784 patients who presented from 2021–2023 to the University Dental Hospital; images were collected retrospectively. The difficulty level of surgically removing impacted LM3s was assessed via our newly developed DL system, which seamlessly integrated 3 distinct DL models. ResNet101V2 handled binary classification for identifying impacted LM3s in panoramic radiographs, RetinaNet detected the precise location of the impacted LM3, and Vision Transformer performed multiclass image classification to evaluate the difficulty levels of removing the detected impacted LM3. Results: The ResNet101V2 model achieved a classification accuracy of 0.8671. The RetinaNet model demonstrated exceptional detection performance, with a mean average precision of 0.9928. Additionally, the Vision Transformer model delivered an average accuracy of 0.7899 in predicting removal difficulty levels. Conclusions: The development of a 3-phase computer-aided visualisation–based DL system has yielded a very good performance in using panoramic radiographs to predict the difficulty level of surgically removing an impacted LM3.http://www.sciencedirect.com/science/article/pii/S002065392400193XImpacted toothThird molarPanoramic radiographArtificial intelligenceDeep learningNeural network |
| spellingShingle | Vorapat Trachoo Unchalisa Taetragool Ploypapas Pianchoopat Chatchapon Sukitporn-udom Narapathra Morakrant Kritsasith Warin Deep Learning for Predicting the Difficulty Level of Removing the Impacted Mandibular Third Molar International Dental Journal Impacted tooth Third molar Panoramic radiograph Artificial intelligence Deep learning Neural network |
| title | Deep Learning for Predicting the Difficulty Level of Removing the Impacted Mandibular Third Molar |
| title_full | Deep Learning for Predicting the Difficulty Level of Removing the Impacted Mandibular Third Molar |
| title_fullStr | Deep Learning for Predicting the Difficulty Level of Removing the Impacted Mandibular Third Molar |
| title_full_unstemmed | Deep Learning for Predicting the Difficulty Level of Removing the Impacted Mandibular Third Molar |
| title_short | Deep Learning for Predicting the Difficulty Level of Removing the Impacted Mandibular Third Molar |
| title_sort | deep learning for predicting the difficulty level of removing the impacted mandibular third molar |
| topic | Impacted tooth Third molar Panoramic radiograph Artificial intelligence Deep learning Neural network |
| url | http://www.sciencedirect.com/science/article/pii/S002065392400193X |
| work_keys_str_mv | AT vorapattrachoo deeplearningforpredictingthedifficultylevelofremovingtheimpactedmandibularthirdmolar AT unchalisataetragool deeplearningforpredictingthedifficultylevelofremovingtheimpactedmandibularthirdmolar AT ploypapaspianchoopat deeplearningforpredictingthedifficultylevelofremovingtheimpactedmandibularthirdmolar AT chatchaponsukitpornudom deeplearningforpredictingthedifficultylevelofremovingtheimpactedmandibularthirdmolar AT narapathramorakrant deeplearningforpredictingthedifficultylevelofremovingtheimpactedmandibularthirdmolar AT kritsasithwarin deeplearningforpredictingthedifficultylevelofremovingtheimpactedmandibularthirdmolar |