Faizan Ahmed Syed Muhammad, Ghori Muhammad Huzaifa, Khalid Aamna, Nooruddin Ayesha, Adnan Niha, Lal Abhishek, Umer Fahad
Section of Dentistry, Department of Surgery, The Aga Khan University, Karachi, Pakistan.
Section of Gastroenterology, Department of Medicine. The Aga Khan University, Karachi, Pakistan.
Sci Data. 2025 Jul 25;12(1):1297. doi: 10.1038/s41597-025-05647-9.
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.
本研究推出了首个公开可用的用于人工智能（AI）驱动的龋齿检测的带注释口腔内图像数据集，以解决可用数据集匮乏的问题。该数据集包含从巴基斯坦信德省米蒂市10至24岁个体收集的6313张图像，其注释使用LabelMe软件创建。这些注释经过经验丰富的牙医精心验证，并转换为多种格式，包括YOLO（You Only Look Once）、PASCAL VOC（模式分析、统计建模和计算学习视觉对象类）、COCO（上下文常见对象），以与各种AI模型兼容。该数据集的特点是包含从各种口腔内视图拍摄的图像，有使用颊部牵开器的和未使用颊部牵开器的，提供了混合牙列和恒牙列的详细表征。对五个AI模型（YOLOv5s、YOLOv8s、YOLOv11、SSD-MobileNet-v2和Faster R-CNN）进行了训练和评估，其中YOLOv8s表现最佳（平均精度均值mAP = 0.841 @ 0.5交并比IoU）。这项工作推动了基于AI的牙科诊断，并为龋齿检测设定了基准。局限性包括使用单一移动设备进行成像。未来的工作应探索乳牙列和多样的成像工具。
