Automated Detection, Localization, and Severity Assessment of Proximal Dental Caries from Bitewing Radiographs Using Deep Learning
<b>Background/Objectives</b>: Dental caries is a widespread chronic infection, affecting a large segment of the population. Proximal caries, in particular, present a distinct obstacle for early identification owing to their position, which hinders clinical inspection. Radiographic assess...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2025-04-01
|
| Series: | Diagnostics |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2075-4418/15/7/899 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850213132444631040 |
|---|---|
| author | Mashail Alsolamy Farrukh Nadeem Amr Ahmed Azhari Walaa Magdy Ahmed |
| author_facet | Mashail Alsolamy Farrukh Nadeem Amr Ahmed Azhari Walaa Magdy Ahmed |
| author_sort | Mashail Alsolamy |
| collection | DOAJ |
| description | <b>Background/Objectives</b>: Dental caries is a widespread chronic infection, affecting a large segment of the population. Proximal caries, in particular, present a distinct obstacle for early identification owing to their position, which hinders clinical inspection. Radiographic assessments, particularly bitewing images (BRs), are frequently utilized to detect these carious lesions. Nonetheless, misinterpretations may obstruct precise diagnosis. This paper presents a deep-learning-based system to improve the evaluation process by detecting proximal dental caries from BRs and classifying their severity in accordance with ICCMS<sup>TM</sup> guidelines. <b>Methods</b>: The system comprises three fundamental tasks: caries detection, tooth numbering, and describing caries location by identifying the tooth it belongs to and the surface, each built independently to enable reuse across many applications. We analyzed 1354 BRs annotated by a consultant of restorative dentistry to delineate the pertinent categories, concentrating on the detection and localization of caries tasks. A pre-trained YOLOv11-based instance segmentation model was employed, allocating 80% of the dataset for training, 10% for validation, and the remaining portion for evaluating the model on unseen data. <b>Results</b>: The system attained a precision of 0.844, recall of 0.864, F1-score of 0.851, and mAP of 0.888 for segmenting caries and classifying their severity, using an intersection over union (IoU) of 50% and a confidence threshold of 0.25. Concentrating on teeth that are entirely or three-quarters presented in BRs, the system attained 100% for identifying the affected teeth and surfaces. It achieved high sensitivity and accuracy in comparison to dentist evaluations. <b>Conclusions</b>: The results are encouraging, suggesting that the proposed system may effectively assist dentists in evaluating bitewing images, assessing lesion severity, and recommending suitable treatments. |
| format | Article |
| id | doaj-art-9c310848923a4b6da3e6df0248049194 |
| institution | OA Journals |
| issn | 2075-4418 |
| language | English |
| publishDate | 2025-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Diagnostics |
| spelling | doaj-art-9c310848923a4b6da3e6df02480491942025-08-20T02:09:11ZengMDPI AGDiagnostics2075-44182025-04-0115789910.3390/diagnostics15070899Automated Detection, Localization, and Severity Assessment of Proximal Dental Caries from Bitewing Radiographs Using Deep LearningMashail Alsolamy0Farrukh Nadeem1Amr Ahmed Azhari2Walaa Magdy Ahmed3Department of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 22233, Saudi ArabiaDepartment of Information Systems, Faculty of Computing and Information Technology, King Abdulaziz University, Jeddah 22233, Saudi ArabiaDepartment of Restorative Dentistry, Faculty of Dentistry, King Abdulaziz University, Jeddah 22233, Saudi ArabiaDepartment of Restorative Dentistry, Faculty of Dentistry, King Abdulaziz University, Jeddah 22233, Saudi Arabia<b>Background/Objectives</b>: Dental caries is a widespread chronic infection, affecting a large segment of the population. Proximal caries, in particular, present a distinct obstacle for early identification owing to their position, which hinders clinical inspection. Radiographic assessments, particularly bitewing images (BRs), are frequently utilized to detect these carious lesions. Nonetheless, misinterpretations may obstruct precise diagnosis. This paper presents a deep-learning-based system to improve the evaluation process by detecting proximal dental caries from BRs and classifying their severity in accordance with ICCMS<sup>TM</sup> guidelines. <b>Methods</b>: The system comprises three fundamental tasks: caries detection, tooth numbering, and describing caries location by identifying the tooth it belongs to and the surface, each built independently to enable reuse across many applications. We analyzed 1354 BRs annotated by a consultant of restorative dentistry to delineate the pertinent categories, concentrating on the detection and localization of caries tasks. A pre-trained YOLOv11-based instance segmentation model was employed, allocating 80% of the dataset for training, 10% for validation, and the remaining portion for evaluating the model on unseen data. <b>Results</b>: The system attained a precision of 0.844, recall of 0.864, F1-score of 0.851, and mAP of 0.888 for segmenting caries and classifying their severity, using an intersection over union (IoU) of 50% and a confidence threshold of 0.25. Concentrating on teeth that are entirely or three-quarters presented in BRs, the system attained 100% for identifying the affected teeth and surfaces. It achieved high sensitivity and accuracy in comparison to dentist evaluations. <b>Conclusions</b>: The results are encouraging, suggesting that the proposed system may effectively assist dentists in evaluating bitewing images, assessing lesion severity, and recommending suitable treatments.https://www.mdpi.com/2075-4418/15/7/899proximal cariesYOLO networkdiagnosisartificial intelligencebitewing radiographsinstance segmentation |
| spellingShingle | Mashail Alsolamy Farrukh Nadeem Amr Ahmed Azhari Walaa Magdy Ahmed Automated Detection, Localization, and Severity Assessment of Proximal Dental Caries from Bitewing Radiographs Using Deep Learning Diagnostics proximal caries YOLO network diagnosis artificial intelligence bitewing radiographs instance segmentation |
| title | Automated Detection, Localization, and Severity Assessment of Proximal Dental Caries from Bitewing Radiographs Using Deep Learning |
| title_full | Automated Detection, Localization, and Severity Assessment of Proximal Dental Caries from Bitewing Radiographs Using Deep Learning |
| title_fullStr | Automated Detection, Localization, and Severity Assessment of Proximal Dental Caries from Bitewing Radiographs Using Deep Learning |
| title_full_unstemmed | Automated Detection, Localization, and Severity Assessment of Proximal Dental Caries from Bitewing Radiographs Using Deep Learning |
| title_short | Automated Detection, Localization, and Severity Assessment of Proximal Dental Caries from Bitewing Radiographs Using Deep Learning |
| title_sort | automated detection localization and severity assessment of proximal dental caries from bitewing radiographs using deep learning |
| topic | proximal caries YOLO network diagnosis artificial intelligence bitewing radiographs instance segmentation |
| url | https://www.mdpi.com/2075-4418/15/7/899 |
| work_keys_str_mv | AT mashailalsolamy automateddetectionlocalizationandseverityassessmentofproximaldentalcariesfrombitewingradiographsusingdeeplearning AT farrukhnadeem automateddetectionlocalizationandseverityassessmentofproximaldentalcariesfrombitewingradiographsusingdeeplearning AT amrahmedazhari automateddetectionlocalizationandseverityassessmentofproximaldentalcariesfrombitewingradiographsusingdeeplearning AT walaamagdyahmed automateddetectionlocalizationandseverityassessmentofproximaldentalcariesfrombitewingradiographsusingdeeplearning |