Evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographs
Abstract Determining the severity of dental crowding and the necessity of tooth extraction for orthodontic treatment planning are time-consuming processes and there are no firm criteria. Thus, automated assistance would be useful to clinicians. This study aimed to construct and evaluate artificial i...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2023-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-023-32514-7 |
| _version_ | 1797853891496247296 |
|---|---|
| author | Jiho Ryu Ye-Hyun Kim Tae-Woo Kim Seok-Ki Jung |
| author_facet | Jiho Ryu Ye-Hyun Kim Tae-Woo Kim Seok-Ki Jung |
| author_sort | Jiho Ryu |
| collection | DOAJ |
| description | Abstract Determining the severity of dental crowding and the necessity of tooth extraction for orthodontic treatment planning are time-consuming processes and there are no firm criteria. Thus, automated assistance would be useful to clinicians. This study aimed to construct and evaluate artificial intelligence (AI) systems to assist with such treatment planning. A total of 3,136 orthodontic occlusal photographs with annotations by two orthodontists were obtained. Four convolutional neural network (CNN) models, namely ResNet50, ResNet101, VGG16, and VGG19, were adopted for the AI process. Using the intraoral photographs as input, the crowding group and the necessity of tooth extraction were obtained. Arch length discrepancy analysis with AI-detected landmarks was used for crowding categorization. Various statistical and visual analyses were conducted to evaluate the performance. The maxillary and mandibular VGG19 models showed minimum mean errors of 0.84 mm and 1.06 mm for teeth landmark detection, respectively. Analysis of Cohen’s weighted kappa coefficient indicated that crowding categorization performance was best in VGG19 (0.73), decreasing in the order of VGG16, ResNet101, and ResNet50. For tooth extraction, the maxillary VGG19 model showed the highest accuracy (0.922) and AUC (0.961). By utilizing deep learning with orthodontic photographs, dental crowding categorization and diagnosis of orthodontic extraction were successfully determined. This suggests that AI can assist clinicians in the diagnosis and decision making of treatment plans. |
| first_indexed | 2024-04-09T19:57:03Z |
| format | Article |
| id | doaj.art-f86741c6b4a04cbc987bd51e93cf7c51 |
| institution | Directory Open Access Journal |
| issn | 2045-2322 |
| language | English |
| last_indexed | 2024-04-09T19:57:03Z |
| publishDate | 2023-03-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Reports |
| spelling | doaj.art-f86741c6b4a04cbc987bd51e93cf7c512023-04-03T05:25:13ZengNature PortfolioScientific Reports2045-23222023-03-0113111010.1038/s41598-023-32514-7Evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographsJiho Ryu0Ye-Hyun Kim1Tae-Woo Kim2Seok-Ki Jung3Department of Orthodontics, School of Dentistry, Dental Research Institute, Seoul National UniversityDepartment of Orthodontics, School of Dentistry, Dental Research Institute, Seoul National UniversityDepartment of Orthodontics, School of Dentistry, Dental Research Institute, Seoul National UniversityDepartment of Orthodontics, Korea University Guro HospitalAbstract Determining the severity of dental crowding and the necessity of tooth extraction for orthodontic treatment planning are time-consuming processes and there are no firm criteria. Thus, automated assistance would be useful to clinicians. This study aimed to construct and evaluate artificial intelligence (AI) systems to assist with such treatment planning. A total of 3,136 orthodontic occlusal photographs with annotations by two orthodontists were obtained. Four convolutional neural network (CNN) models, namely ResNet50, ResNet101, VGG16, and VGG19, were adopted for the AI process. Using the intraoral photographs as input, the crowding group and the necessity of tooth extraction were obtained. Arch length discrepancy analysis with AI-detected landmarks was used for crowding categorization. Various statistical and visual analyses were conducted to evaluate the performance. The maxillary and mandibular VGG19 models showed minimum mean errors of 0.84 mm and 1.06 mm for teeth landmark detection, respectively. Analysis of Cohen’s weighted kappa coefficient indicated that crowding categorization performance was best in VGG19 (0.73), decreasing in the order of VGG16, ResNet101, and ResNet50. For tooth extraction, the maxillary VGG19 model showed the highest accuracy (0.922) and AUC (0.961). By utilizing deep learning with orthodontic photographs, dental crowding categorization and diagnosis of orthodontic extraction were successfully determined. This suggests that AI can assist clinicians in the diagnosis and decision making of treatment plans.https://doi.org/10.1038/s41598-023-32514-7 |
| spellingShingle | Jiho Ryu Ye-Hyun Kim Tae-Woo Kim Seok-Ki Jung Evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographs Scientific Reports |
| title | Evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographs |
| title_full | Evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographs |
| title_fullStr | Evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographs |
| title_full_unstemmed | Evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographs |
| title_short | Evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographs |
| title_sort | evaluation of artificial intelligence model for crowding categorization and extraction diagnosis using intraoral photographs |
| url | https://doi.org/10.1038/s41598-023-32514-7 |
| work_keys_str_mv | AT jihoryu evaluationofartificialintelligencemodelforcrowdingcategorizationandextractiondiagnosisusingintraoralphotographs AT yehyunkim evaluationofartificialintelligencemodelforcrowdingcategorizationandextractiondiagnosisusingintraoralphotographs AT taewookim evaluationofartificialintelligencemodelforcrowdingcategorizationandextractiondiagnosisusingintraoralphotographs AT seokkijung evaluationofartificialintelligencemodelforcrowdingcategorizationandextractiondiagnosisusingintraoralphotographs |