Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study
Objectives: Approximal caries diagnosis in children is difficult, and artificial intelligence-based research in pediatric dentistry is scarce. To create a convolutional neural network (CNN)-based diagnostic system for the prompt and efficient identification of approximal caries in pediatric patient...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Medical Journals Sweden
2025-01-01
|
| Series: | Acta Odontologica Scandinavica |
| Subjects: | |
| Online Access: | https://medicaljournalssweden.se/actaodontologica/article/view/42599 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841557121927217152 |
|---|---|
| author | Zeynep Seyda Yavsan Hediye Orhan Enes Efe Emrehan Yavsan |
| author_facet | Zeynep Seyda Yavsan Hediye Orhan Enes Efe Emrehan Yavsan |
| author_sort | Zeynep Seyda Yavsan |
| collection | DOAJ |
| description |
Objectives: Approximal caries diagnosis in children is difficult, and artificial intelligence-based research in pediatric dentistry is scarce. To create a convolutional neural network (CNN)-based diagnostic system for the prompt and efficient identification of approximal caries in pediatric patients aged 5–12 years.
Materials and methods: Pediatric patients’ digital periapical radiographic images were collected to create a unique dataset. Various augmentation methods were used, and approximal caries in the augmented images were labeled by a pediatric dentist to minimize labeling errors. The dataset consisted of 830 data labeled for approximal caries on 415 images, which were divided into 80% training and 20% testing sets. After comparing 13 detection algorithms, including the latest YOLOv8, the most appropriate one was selected for the proposed system, which was then evaluated based on various performance metrics.
Results: The proposed detection system achieved a precision of 91.2%, an accuracy of 90.8%, a recall of 89.3%, and an F1 value of 90.24% after 300 iterations, utilizing a learning rate of 0.01.
Conclusion: Approximal caries has been successfully detected with the developed system. Future efforts will focus on augmenting the dataset and expanding the sample size to enhance the efficacy of the system.
|
| format | Article |
| id | doaj-art-62428d0d9a3f453989ccde264df3fe99 |
| institution | Kabale University |
| issn | 0001-6357 1502-3850 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | Medical Journals Sweden |
| record_format | Article |
| series | Acta Odontologica Scandinavica |
| spelling | doaj-art-62428d0d9a3f453989ccde264df3fe992025-01-06T16:55:15ZengMedical Journals SwedenActa Odontologica Scandinavica0001-63571502-38502025-01-018410.2340/aos.v84.42599Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot studyZeynep Seyda Yavsan0https://orcid.org/0000-0003-1275-0258Hediye Orhan1https://orcid.org/0000-0001-8760-914XEnes Efe2https://orcid.org/0000-0002-6136-6140Emrehan Yavsan3https://orcid.org/0000-0001-9521-4500Department of Pediatric Dentistry, Tekirdag Namik Kemal University, Tekirdag, TurkeyDepartment of Computer Engineering, Necmettin Erbakan University, Konya, TurkeyDepartment of Electrical and Electronics Engineering, Hitit University, Corum, TurkeyElectronic and Department of Electronics and Automation, Tekirdag Namik Kemal University, Tekirdag, Turkey Objectives: Approximal caries diagnosis in children is difficult, and artificial intelligence-based research in pediatric dentistry is scarce. To create a convolutional neural network (CNN)-based diagnostic system for the prompt and efficient identification of approximal caries in pediatric patients aged 5–12 years. Materials and methods: Pediatric patients’ digital periapical radiographic images were collected to create a unique dataset. Various augmentation methods were used, and approximal caries in the augmented images were labeled by a pediatric dentist to minimize labeling errors. The dataset consisted of 830 data labeled for approximal caries on 415 images, which were divided into 80% training and 20% testing sets. After comparing 13 detection algorithms, including the latest YOLOv8, the most appropriate one was selected for the proposed system, which was then evaluated based on various performance metrics. Results: The proposed detection system achieved a precision of 91.2%, an accuracy of 90.8%, a recall of 89.3%, and an F1 value of 90.24% after 300 iterations, utilizing a learning rate of 0.01. Conclusion: Approximal caries has been successfully detected with the developed system. Future efforts will focus on augmenting the dataset and expanding the sample size to enhance the efficacy of the system. https://medicaljournalssweden.se/actaodontologica/article/view/42599Artificial intelligencedental cariesmachine learningperiapical radiographypediatric dentistry |
| spellingShingle | Zeynep Seyda Yavsan Hediye Orhan Enes Efe Emrehan Yavsan Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study Acta Odontologica Scandinavica Artificial intelligence dental caries machine learning periapical radiography pediatric dentistry |
| title | Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study |
| title_full | Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study |
| title_fullStr | Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study |
| title_full_unstemmed | Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study |
| title_short | Diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs: A pilot study |
| title_sort | diagnosis of approximal caries in children with convolutional neural networks based detection algorithms on radiographs a pilot study |
| topic | Artificial intelligence dental caries machine learning periapical radiography pediatric dentistry |
| url | https://medicaljournalssweden.se/actaodontologica/article/view/42599 |
| work_keys_str_mv | AT zeynepseydayavsan diagnosisofapproximalcariesinchildrenwithconvolutionalneuralnetworksbaseddetectionalgorithmsonradiographsapilotstudy AT hediyeorhan diagnosisofapproximalcariesinchildrenwithconvolutionalneuralnetworksbaseddetectionalgorithmsonradiographsapilotstudy AT enesefe diagnosisofapproximalcariesinchildrenwithconvolutionalneuralnetworksbaseddetectionalgorithmsonradiographsapilotstudy AT emrehanyavsan diagnosisofapproximalcariesinchildrenwithconvolutionalneuralnetworksbaseddetectionalgorithmsonradiographsapilotstudy |