Deep learning for chronological age and sex prediction from dental panoramic radiographs
Chronological age estimation and sex classification are two relevant tasks in a variety of clinical procedures, such as human identification or legal age determination. It is known that the oral cavity hosts anatomical structures that make it possible to estimate age and sex in a very accurate way, so numerous models have been developed to convert dry-bone or radiological measurements into an estimation of age or sex. However, the inherent subjectivity of the measurements or the time cost may hinder their application. To alleviate these problems, this PhD Thesis introduces three different automatic models for age and sex estimation on dental panoramic radiographs to assess the suitability not only of the whole X-ray image but also of specific structures such as the mandible and the teeth.
keywords: convolutional neural networks (CNNs), chronological age estimation, sex determination, panoramic dental images