Annotated intraoral image dataset for dental caries detection
Abstract This study introduces the first publicly available annotated intraoral image dataset for Artificial Intelligence (AI)-driven dental caries detection, addressing the lack of available datasets. It comprises 6,313 images collected from individuals aged 10 to 24 years in Mithi, Sindh, Pakistan...
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-07-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-025-05647-9 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1849767250321473536 |
|---|---|
| author | Syed Muhammad Faizan Ahmed Muhammad Huzaifa Ghori Aamna Khalid Ayesha Nooruddin Niha Adnan Abhishek Lal Fahad Umer |
| author_facet | Syed Muhammad Faizan Ahmed Muhammad Huzaifa Ghori Aamna Khalid Ayesha Nooruddin Niha Adnan Abhishek Lal Fahad Umer |
| author_sort | Syed Muhammad Faizan Ahmed |
| collection | DOAJ |
| description | Abstract This study introduces the first publicly available annotated intraoral image dataset for Artificial Intelligence (AI)-driven dental caries detection, addressing the lack of available datasets. It comprises 6,313 images collected from individuals aged 10 to 24 years in Mithi, Sindh, Pakistan, with annotations created using LabelMe software. These annotations were meticulously verified by experienced dentists and converted into multiple formats, including YOLO (You Only Look Once), PASCAL VOC (Pattern Analysis, Statistical Modeling, and Computational Learning Visual Object Classes), COCO (Common Objects in Context) for compatibility with diverse AI models. The dataset features images captured from various intraoral views, both with and without cheek retractors, offering detailed representation of mixed and permanent dentitions. Five AI models (YOLOv5s, YOLOv8s, YOLOv11, SSD-MobileNet-v2, and Faster R-CNN) were trained and evaluated, with YOLOv8s achieving the best performance (mAP = 0.841 @ 0.5 IoU). This work advances AI-based dental diagnostics and sets a benchmark for caries detection. Limitations include using a single mobile device for imaging. Future work should explore primary dentition and diverse imaging tools. |
| format | Article |
| id | doaj-art-d24a122e587b48f98f7b3faa75e20e3f |
| institution | DOAJ |
| issn | 2052-4463 |
| language | English |
| publishDate | 2025-07-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj-art-d24a122e587b48f98f7b3faa75e20e3f2025-08-20T03:04:17ZengNature PortfolioScientific Data2052-44632025-07-011211710.1038/s41597-025-05647-9Annotated intraoral image dataset for dental caries detectionSyed Muhammad Faizan Ahmed0Muhammad Huzaifa Ghori1Aamna Khalid2Ayesha Nooruddin3Niha Adnan4Abhishek Lal5Fahad Umer6Section of Dentistry, Department of Surgery, The Aga Khan UniversitySection of Dentistry, Department of Surgery, The Aga Khan UniversitySection of Dentistry, Department of Surgery, The Aga Khan UniversitySection of Dentistry, Department of Surgery, The Aga Khan UniversitySection of Dentistry, Department of Surgery, The Aga Khan UniversitySection of Gastroenterology, Department of Medicine. The Aga Khan UniversitySection of Dentistry, Department of Surgery, The Aga Khan UniversityAbstract This study introduces the first publicly available annotated intraoral image dataset for Artificial Intelligence (AI)-driven dental caries detection, addressing the lack of available datasets. It comprises 6,313 images collected from individuals aged 10 to 24 years in Mithi, Sindh, Pakistan, with annotations created using LabelMe software. These annotations were meticulously verified by experienced dentists and converted into multiple formats, including YOLO (You Only Look Once), PASCAL VOC (Pattern Analysis, Statistical Modeling, and Computational Learning Visual Object Classes), COCO (Common Objects in Context) for compatibility with diverse AI models. The dataset features images captured from various intraoral views, both with and without cheek retractors, offering detailed representation of mixed and permanent dentitions. Five AI models (YOLOv5s, YOLOv8s, YOLOv11, SSD-MobileNet-v2, and Faster R-CNN) were trained and evaluated, with YOLOv8s achieving the best performance (mAP = 0.841 @ 0.5 IoU). This work advances AI-based dental diagnostics and sets a benchmark for caries detection. Limitations include using a single mobile device for imaging. Future work should explore primary dentition and diverse imaging tools.https://doi.org/10.1038/s41597-025-05647-9 |
| spellingShingle | Syed Muhammad Faizan Ahmed Muhammad Huzaifa Ghori Aamna Khalid Ayesha Nooruddin Niha Adnan Abhishek Lal Fahad Umer Annotated intraoral image dataset for dental caries detection Scientific Data |
| title | Annotated intraoral image dataset for dental caries detection |
| title_full | Annotated intraoral image dataset for dental caries detection |
| title_fullStr | Annotated intraoral image dataset for dental caries detection |
| title_full_unstemmed | Annotated intraoral image dataset for dental caries detection |
| title_short | Annotated intraoral image dataset for dental caries detection |
| title_sort | annotated intraoral image dataset for dental caries detection |
| url | https://doi.org/10.1038/s41597-025-05647-9 |
| work_keys_str_mv | AT syedmuhammadfaizanahmed annotatedintraoralimagedatasetfordentalcariesdetection AT muhammadhuzaifaghori annotatedintraoralimagedatasetfordentalcariesdetection AT aamnakhalid annotatedintraoralimagedatasetfordentalcariesdetection AT ayeshanooruddin annotatedintraoralimagedatasetfordentalcariesdetection AT nihaadnan annotatedintraoralimagedatasetfordentalcariesdetection AT abhisheklal annotatedintraoralimagedatasetfordentalcariesdetection AT fahadumer annotatedintraoralimagedatasetfordentalcariesdetection |