Impacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistance
Abstract Background Assessing the difficulty of impacted lower third molar (ILTM) surgical extraction is crucial for predicting postoperative complications and estimating procedure duration. The aim of this study was to evaluate the effectiveness of a convolutional neural network (CNN) in determinin...
Saved in:
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
BMC
2025-01-01
|
| Series: | BMC Oral Health |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s12903-025-05425-4 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832571220519813120 |
|---|---|
| author | Paniti Achararit Chawan Manaspon Chavin Jongwannasiri Promphakkon Kulthanaamondhita Chumpot Itthichaisri Soranun Chantarangsu Thanaphum Osathanon Ekarat Phattarataratip Kraisorn Sappayatosok |
| author_facet | Paniti Achararit Chawan Manaspon Chavin Jongwannasiri Promphakkon Kulthanaamondhita Chumpot Itthichaisri Soranun Chantarangsu Thanaphum Osathanon Ekarat Phattarataratip Kraisorn Sappayatosok |
| author_sort | Paniti Achararit |
| collection | DOAJ |
| description | Abstract Background Assessing the difficulty of impacted lower third molar (ILTM) surgical extraction is crucial for predicting postoperative complications and estimating procedure duration. The aim of this study was to evaluate the effectiveness of a convolutional neural network (CNN) in determining the angulation, position, classification and difficulty index (DI) of ILTM. Additionally, we compared these parameters and the time required for interpretation among deep learning (DL) models, sixth-year dental students (DSs), and general dental practitioners (GPs) with and without CNN assistance. Materials and Methods The dataset included cropped panoramic radiographs of 1200 ILTMs. The parameters examined were ILTM angulation, class, and position. The radiographs were randomly split into test datasets, while the remaining images were utilized for training and validation. Data augmentation techniques were applied. Another set of radiographs was used to compare the accuracy between human experts and the top-performing CNN. This dataset was also given to DSs and GPs. The participants were instructed to classify the parameters of the ILTMs both with and without the aid of the best-performing CNN model. The results, as well as the Pederson DI and time taken for both groups with and without CNN assistance, were statistically analyzed. Results All the selected CNN models successfully classified ILTM angulation, class, and position. Within the DS and GP groups, the accuracy and kappa scores were significantly greater when CNN assistance was used. Among the groups, performance tests without CNN assistance revealed no significant differences in any category. However, compared with DSs, GPs took significantly less time for the class and total time, a trend that persisted when CNN assistance was used. With the CNN, the GPs achieved significantly higher accuracy and kappa scores for class classification than the DSs did (p = 0.035 and 0.010). Conversely, the DS group, with the CNN, exhibited higher accuracy and kappa scores for position classification than did the GP group (p < 0.001). Conclusion The CNN can achieve accuracies ranging from 87 to 96% for ILTM classification. With the assistance of the CNN, both DSs and GPs exhibited significantly higher accuracy in ILTM classification. Additionally, compared with DSs with and without CNN assistance, GPs took significantly less time to inspect the class and overall. |
| format | Article |
| id | doaj-art-24f7c384cfa647129ef263fe52e8f40a |
| institution | Kabale University |
| issn | 1472-6831 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | BMC |
| record_format | Article |
| series | BMC Oral Health |
| spelling | doaj-art-24f7c384cfa647129ef263fe52e8f40a2025-02-02T12:45:12ZengBMCBMC Oral Health1472-68312025-01-0125111410.1186/s12903-025-05425-4Impacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistancePaniti Achararit0Chawan Manaspon1Chavin Jongwannasiri2Promphakkon Kulthanaamondhita3Chumpot Itthichaisri4Soranun Chantarangsu5Thanaphum Osathanon6Ekarat Phattarataratip7Kraisorn Sappayatosok8Princess Srisavangavadhana Faculty of Medicine, Chulabhorn Royal AcademyBiomedical Engineering Institute, Chiang Mai UniversityPrincess Srisavangavadhana Faculty of Medicine, Chulabhorn Royal AcademyBangkok Hospital Dental Center Holistic Care and Dental Implant, Bangkok HospitalBangkok Hospital Dental Center Holistic Care and Dental Implant, Bangkok HospitalDepartment of Oral Pathology, Faculty of Dentistry, Chulalongkorn UniversityCenter of Excellence for Dental Stem Cell Biology, Department of Anatomy, Faculty of Dentistry, Chulalongkorn UniversityDepartment of Oral Pathology, Faculty of Dentistry, Chulalongkorn UniversityBangkok Hospital Dental Center Holistic Care and Dental Implant, Bangkok HospitalAbstract Background Assessing the difficulty of impacted lower third molar (ILTM) surgical extraction is crucial for predicting postoperative complications and estimating procedure duration. The aim of this study was to evaluate the effectiveness of a convolutional neural network (CNN) in determining the angulation, position, classification and difficulty index (DI) of ILTM. Additionally, we compared these parameters and the time required for interpretation among deep learning (DL) models, sixth-year dental students (DSs), and general dental practitioners (GPs) with and without CNN assistance. Materials and Methods The dataset included cropped panoramic radiographs of 1200 ILTMs. The parameters examined were ILTM angulation, class, and position. The radiographs were randomly split into test datasets, while the remaining images were utilized for training and validation. Data augmentation techniques were applied. Another set of radiographs was used to compare the accuracy between human experts and the top-performing CNN. This dataset was also given to DSs and GPs. The participants were instructed to classify the parameters of the ILTMs both with and without the aid of the best-performing CNN model. The results, as well as the Pederson DI and time taken for both groups with and without CNN assistance, were statistically analyzed. Results All the selected CNN models successfully classified ILTM angulation, class, and position. Within the DS and GP groups, the accuracy and kappa scores were significantly greater when CNN assistance was used. Among the groups, performance tests without CNN assistance revealed no significant differences in any category. However, compared with DSs, GPs took significantly less time for the class and total time, a trend that persisted when CNN assistance was used. With the CNN, the GPs achieved significantly higher accuracy and kappa scores for class classification than the DSs did (p = 0.035 and 0.010). Conversely, the DS group, with the CNN, exhibited higher accuracy and kappa scores for position classification than did the GP group (p < 0.001). Conclusion The CNN can achieve accuracies ranging from 87 to 96% for ILTM classification. With the assistance of the CNN, both DSs and GPs exhibited significantly higher accuracy in ILTM classification. Additionally, compared with DSs with and without CNN assistance, GPs took significantly less time to inspect the class and overall.https://doi.org/10.1186/s12903-025-05425-4Impacted toothArtificial intelligenceDeep learningConvolutional neural networkPederson difficulty index |
| spellingShingle | Paniti Achararit Chawan Manaspon Chavin Jongwannasiri Promphakkon Kulthanaamondhita Chumpot Itthichaisri Soranun Chantarangsu Thanaphum Osathanon Ekarat Phattarataratip Kraisorn Sappayatosok Impacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistance BMC Oral Health Impacted tooth Artificial intelligence Deep learning Convolutional neural network Pederson difficulty index |
| title | Impacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistance |
| title_full | Impacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistance |
| title_fullStr | Impacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistance |
| title_full_unstemmed | Impacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistance |
| title_short | Impacted lower third molar classification and difficulty index assessment: comparisons among dental students, general practitioners and deep learning model assistance |
| title_sort | impacted lower third molar classification and difficulty index assessment comparisons among dental students general practitioners and deep learning model assistance |
| topic | Impacted tooth Artificial intelligence Deep learning Convolutional neural network Pederson difficulty index |
| url | https://doi.org/10.1186/s12903-025-05425-4 |
| work_keys_str_mv | AT panitiachararit impactedlowerthirdmolarclassificationanddifficultyindexassessmentcomparisonsamongdentalstudentsgeneralpractitionersanddeeplearningmodelassistance AT chawanmanaspon impactedlowerthirdmolarclassificationanddifficultyindexassessmentcomparisonsamongdentalstudentsgeneralpractitionersanddeeplearningmodelassistance AT chavinjongwannasiri impactedlowerthirdmolarclassificationanddifficultyindexassessmentcomparisonsamongdentalstudentsgeneralpractitionersanddeeplearningmodelassistance AT promphakkonkulthanaamondhita impactedlowerthirdmolarclassificationanddifficultyindexassessmentcomparisonsamongdentalstudentsgeneralpractitionersanddeeplearningmodelassistance AT chumpotitthichaisri impactedlowerthirdmolarclassificationanddifficultyindexassessmentcomparisonsamongdentalstudentsgeneralpractitionersanddeeplearningmodelassistance AT soranunchantarangsu impactedlowerthirdmolarclassificationanddifficultyindexassessmentcomparisonsamongdentalstudentsgeneralpractitionersanddeeplearningmodelassistance AT thanaphumosathanon impactedlowerthirdmolarclassificationanddifficultyindexassessmentcomparisonsamongdentalstudentsgeneralpractitionersanddeeplearningmodelassistance AT ekaratphattarataratip impactedlowerthirdmolarclassificationanddifficultyindexassessmentcomparisonsamongdentalstudentsgeneralpractitionersanddeeplearningmodelassistance AT kraisornsappayatosok impactedlowerthirdmolarclassificationanddifficultyindexassessmentcomparisonsamongdentalstudentsgeneralpractitionersanddeeplearningmodelassistance |