Adnan Niha, Umer Fahad
Section of Operative Dentistry and Endodontics, Department of Surgery, Jenabai Hussainali Shariff (JHS) building, First Floor Dental clinics, Aga Khan University Hospital, Stadium Road, Karachi 74800, Pakistan.
Data Brief. 2024 Nov 23;57:111152. doi: 10.1016/j.dib.2024.111152. eCollection 2024 Dec.
With the digitization of radiographs, vast amounts of data have become accessible, enabling the curation and development of extensive datasets. Among radiographic modalities, Orthopantomograms (OPGs) are widely utilized in clinical practice. The integration of automated diagnostic processes into routine clinical practice holds great potential as an adjunct for dentists.Various OPG datasets exist, however their limitations affect the robustness of Artificial Intelligence (AI) models trained on them. This paper introduces an OPG dataset specifically designed for training AI algorithms in teeth segmentation and numbering tasks. A key feature of this dataset is its dual annotation, which allows for individual tooth segmentation by class, as well as numbering according to the Fédération Dentaire Internationale system.This dual-annotated dataset enhances the existing pool of OPG datasets and can be leveraged for further training of pre-trained algorithms or the development of new ones. Moreover, it offers researchers to carry out annotations tailored to their respective research objectives, thereby facilitating the development of AI models capable of addressing diverse diagnostic tasks.
随着X光片的数字化，大量数据变得可获取，这使得大规模数据集的管理和开发成为可能。在X光成像模态中，全景曲面断层片（OPG）在临床实践中被广泛应用。将自动化诊断流程整合到常规临床实践中，作为牙医的辅助手段具有巨大潜力。虽然存在各种OPG数据集，但其局限性影响了基于这些数据集训练的人工智能（AI）模型的稳健性。本文介绍了一个专门为牙齿分割和编号任务训练AI算法而设计的OPG数据集。该数据集的一个关键特性是其双重标注，它允许按类别对单个牙齿进行分割，并根据国际牙科联合会系统进行编号。这个双重标注的数据集丰富了现有的OPG数据集池，可用于进一步训练预训练算法或开发新算法。此外，它为研究人员提供了根据各自研究目标进行标注的机会，从而有助于开发能够处理各种诊断任务的AI模型。
