An Audit of Publicly Accessible Dental Imaging Datasets for Artificial Intelligence Applications

• Dr. Nazeera K. Halvani

  Department of Oral Biology, Lirona Dental Institute of Health Sciences, Muscat, Oman

  Author

• Dr. Emelio D. Travanik

  Faculty of Restorative Dentistry, Norbelia University School of Dental Medicine, Valletta, Malta

  Author

The integration of artificial intelligence (AI) into dentistry holds the promise of revolutionizing diagnostics, treatment planning, and patient care. However, the development of robust, equitable, and unbiased AI models is critically dependent on the availability of large, diverse, and meticulously documented datasets. This article provides a comprehensive systematic review of the current state of publicly available dental image datasets intended for AI research. We conducted an extensive search across academic databases, data repositories, and AI challenge platforms to identify and evaluate existing datasets. The evaluation was based on the FAIR (Findable, Accessible, Interoperable, and Reusable) guiding principles, metadata completeness, and current best practices for responsible data documentation. Our findings reveal a significant scarcity of high-quality, large-scale dental imaging datasets, particularly when compared to other medical fields like radiology and ophthalmology. The 16 unique datasets identified are predominantly from a few countries, feature a limited number of imaging modalities, and focus heavily on tooth segmentation tasks. Crucially, many existing datasets lack standardized metadata, clear licensing, comprehensive documentation, and transparent reporting of ethical approval, which severely limits their utility and hampers the development of generalizable AI models (1, 21). Furthermore, issues of poor data sharing compliance and the high potential for inherent demographic and technical biases within these datasets present significant challenges to the field (3, 7). This review highlights the urgent need for a concerted, global effort within the dental community to create, curate, and share high-quality, ethically sourced, and openly accessible datasets. Establishing robust data infrastructure and mandating adherence to data documentation standards, such as data cards and the Croissant format, are essential steps to accelerate innovation and ensure the trustworthy and equitable development of AI in dentistry (2, 10, 12).

• pdf

All articles published by The Parthenon Frontiers and its associated journals are distributed under the terms of the Creative Commons Attribution (CC BY 4.0) International License unless otherwise stated. 

Authors retain full copyright of their published work. By submitting their manuscript, authors agree to grant The Parthenon Frontiers a non-exclusive license to publish, archive, and distribute the article worldwide. Authors are free to:

• Share their article on personal websites, institutional repositories, or social media platforms.

• Reuse their content in future works, presentations, or educational materials, provided proper citation of the original publication.