Deep Learning Architecture to Infer Kennedy Classification of Partially Edentulous Arches Using Object Detection Techniques and Piecewise Annotations
Objectives: Dental health is integral to overall well-being, with early detection of issues critical for prevention. This research work focuses on utilizing artificial intelligence and deep learning–based object detection techniques for automated detection of common dental issues in orthopantomograp...
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/S0020653924015910 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832592822565339136 |
|---|---|
| author | Zohaib Khurshid, MRes, FDTFEd, FHEA Maria Waqas, PhD Shehzad Hasan, PhD Shakeel Kazmi, PhD Muhammad Faheemuddin, FCPS |
| author_facet | Zohaib Khurshid, MRes, FDTFEd, FHEA Maria Waqas, PhD Shehzad Hasan, PhD Shakeel Kazmi, PhD Muhammad Faheemuddin, FCPS |
| author_sort | Zohaib Khurshid, MRes, FDTFEd, FHEA |
| collection | DOAJ |
| description | Objectives: Dental health is integral to overall well-being, with early detection of issues critical for prevention. This research work focuses on utilizing artificial intelligence and deep learning–based object detection techniques for automated detection of common dental issues in orthopantomography x-ray images, including broken roots, periodontally compromised teeth, and the Kennedy classification of partially edentulous arches. Methods: An orthopantomography dataset has been used to train several models employing various object detection architectures, hyperparameters, and training techniques. The performance of these models was evaluated to select the one with the highest accuracy. This selected model was subsequently deployed for further testing and validation on unseen data to assess its real-world performance and potential for clinical application. Results: The proposed model not only facilitates the classification of the Kennedy classification but also offers detailed information about the arch (maxillary or mandibular) and specifies the affected side of the arch (right or left). It can diagnose multiple dental issues simultaneously within an image, enhancing diagnostic capabilities for dental practitioners. Conclusions: Despite a small dataset, satisfactory results were achieved through tailored hyperparameters and a piecewise annotation scheme. |
| format | Article |
| id | doaj-art-e52b0e0c3b6d4eb3b04838c3ca1c2c34 |
| institution | Kabale University |
| issn | 0020-6539 |
| language | English |
| publishDate | 2025-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | International Dental Journal |
| spelling | doaj-art-e52b0e0c3b6d4eb3b04838c3ca1c2c342025-01-21T04:12:47ZengElsevierInternational Dental Journal0020-65392025-02-01751223235Deep Learning Architecture to Infer Kennedy Classification of Partially Edentulous Arches Using Object Detection Techniques and Piecewise AnnotationsZohaib Khurshid, MRes, FDTFEd, FHEA0Maria Waqas, PhD1Shehzad Hasan, PhD2Shakeel Kazmi, PhD3Muhammad Faheemuddin, FCPS4Department of Prosthodontics and Dental Implantology, College of Dentistry, King Faisal University, Al-Ahsa, KSA; Center of Excellence for Regenerative Dentistry, Department of Anatomy, Faculty of Dentistry, Chulalongkorn University, Bangkok, Thailand; Corresponding author. Department of Prosthodontics and Dental Implantology, King Faisal University, Al-Ahsa, 31982, KSA.Department of Computer and Information Systems Engineering, NED University of Engineering and Technology, Karachi, PakistanDepartment of Computer and Information Systems Engineering, NED University of Engineering and Technology, Karachi, PakistanDepartment of Oral Biology, College of Dentistry, Shaheed Zulfiqar Ali Bhutto Medical University Islamabad, PakistanDepartment of Prosthodontics and Dental Implantology, College of Dentistry, King Faisal University, Al-Ahsa, KSAObjectives: Dental health is integral to overall well-being, with early detection of issues critical for prevention. This research work focuses on utilizing artificial intelligence and deep learning–based object detection techniques for automated detection of common dental issues in orthopantomography x-ray images, including broken roots, periodontally compromised teeth, and the Kennedy classification of partially edentulous arches. Methods: An orthopantomography dataset has been used to train several models employing various object detection architectures, hyperparameters, and training techniques. The performance of these models was evaluated to select the one with the highest accuracy. This selected model was subsequently deployed for further testing and validation on unseen data to assess its real-world performance and potential for clinical application. Results: The proposed model not only facilitates the classification of the Kennedy classification but also offers detailed information about the arch (maxillary or mandibular) and specifies the affected side of the arch (right or left). It can diagnose multiple dental issues simultaneously within an image, enhancing diagnostic capabilities for dental practitioners. Conclusions: Despite a small dataset, satisfactory results were achieved through tailored hyperparameters and a piecewise annotation scheme.http://www.sciencedirect.com/science/article/pii/S0020653924015910Kennedy classificationbroken rootperiodontally compromised toothdeep learningobject detection and localizationYou Only Look Once (YOLO) |
| spellingShingle | Zohaib Khurshid, MRes, FDTFEd, FHEA Maria Waqas, PhD Shehzad Hasan, PhD Shakeel Kazmi, PhD Muhammad Faheemuddin, FCPS Deep Learning Architecture to Infer Kennedy Classification of Partially Edentulous Arches Using Object Detection Techniques and Piecewise Annotations International Dental Journal Kennedy classification broken root periodontally compromised tooth deep learning object detection and localization You Only Look Once (YOLO) |
| title | Deep Learning Architecture to Infer Kennedy Classification of Partially Edentulous Arches Using Object Detection Techniques and Piecewise Annotations |
| title_full | Deep Learning Architecture to Infer Kennedy Classification of Partially Edentulous Arches Using Object Detection Techniques and Piecewise Annotations |
| title_fullStr | Deep Learning Architecture to Infer Kennedy Classification of Partially Edentulous Arches Using Object Detection Techniques and Piecewise Annotations |
| title_full_unstemmed | Deep Learning Architecture to Infer Kennedy Classification of Partially Edentulous Arches Using Object Detection Techniques and Piecewise Annotations |
| title_short | Deep Learning Architecture to Infer Kennedy Classification of Partially Edentulous Arches Using Object Detection Techniques and Piecewise Annotations |
| title_sort | deep learning architecture to infer kennedy classification of partially edentulous arches using object detection techniques and piecewise annotations |
| topic | Kennedy classification broken root periodontally compromised tooth deep learning object detection and localization You Only Look Once (YOLO) |
| url | http://www.sciencedirect.com/science/article/pii/S0020653924015910 |
| work_keys_str_mv | AT zohaibkhurshidmresfdtfedfhea deeplearningarchitecturetoinferkennedyclassificationofpartiallyedentulousarchesusingobjectdetectiontechniquesandpiecewiseannotations AT mariawaqasphd deeplearningarchitecturetoinferkennedyclassificationofpartiallyedentulousarchesusingobjectdetectiontechniquesandpiecewiseannotations AT shehzadhasanphd deeplearningarchitecturetoinferkennedyclassificationofpartiallyedentulousarchesusingobjectdetectiontechniquesandpiecewiseannotations AT shakeelkazmiphd deeplearningarchitecturetoinferkennedyclassificationofpartiallyedentulousarchesusingobjectdetectiontechniquesandpiecewiseannotations AT muhammadfaheemuddinfcps deeplearningarchitecturetoinferkennedyclassificationofpartiallyedentulousarchesusingobjectdetectiontechniquesandpiecewiseannotations |