Abstract
The most common imaging methods used in dentistry are X-ray imaging and RGB color photography. However, both imaging methods provide only a limited amount of information on the wavelength-dependent optical properties of the hard and soft tissues in the mouth. Spectral imaging, on the other hand, provides significantly more information on the medically relevant dental and oral features (e.g. caries, calculus, and gingivitis). Due to this, we constructed a spectral imaging setup and acquired 316 oral and dental reflectance spectral images, 215 of which are annotated by medical experts, of 30 human test subjects. Spectral images of the subjects’ faces and other areas of interest were captured, along with other medically relevant information (e.g., pulse and blood pressure). We collected these oral, dental, and face spectral images, their annotations and metadata into a publicly available database that we describe in this paper. This oral and dental spectral image database (ODSI-DB) provides a vast amount of data that can be used for developing, e.g., pattern recognition and machine vision applications for dentistry.
Highlights
The majority of dental and oral imaging is performed by X-ray-based techniques or by digital photography
Digital photography is more suitable for soft tissue and avoids these risks while still providing useful diagnostic information, even of hard tissue
Since this text-based annotation format is relatively inconvenient for practical use, the oral and dental spectral image dataset contains annotations as bi-level mask images saved in multi-page Tiff files
Summary
The majority of dental and oral imaging is performed by X-ray-based techniques or by digital photography. Digital photography is more suitable for soft tissue and avoids these risks while still providing useful diagnostic information, even of hard tissue ( this is limited to surface features). The additional information provided by spectral imaging enables new data analysis and visualization methods compared to grayscale or color images. Spectral images can be used to design systems that enhance the visibility of a targeted feature, for example, by applying different weights on the bands while computing a color image representation [7], or by optimizing contrast to produce optimal optical filters [8,9]. Examples of the few public medical spectral image datasets include images of brain [15,16] and retinal [17] tissue These publicly available image sets require contacting the authors for access. The database is available online at the following address: https://sites.uef.fi/spectral/odsi-db/
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
