Clinical Research Directory

Validating AI for Gender Prediction Using Morphometric Analysis of the Mandible

This retrospective validity study evaluates the accuracy of artificial intelligence (AI) in determining gender from mandibular morphometric linear measurements. The study utilizes pre-existing Cone Beam Computed Tomography (CBCT) scans of adult Egyptian dental patients. After automatic segmentation of the mandible from these scans, a radiologist will manually perform measurements from certain anatomical points. These measurements will be the reference standard for the AI models. A three-dimensional deep learning model will be developed to perform two tasks: 1. To identify the anatomical points and make the specified linear measurements from these points on the segmented mandibles 2. To accurately predict gender based on these measurements. (Main Objective) The primary objective of this study is to evaluate the accuracy of machine learning algorithms in gender identification from linear morphometric measurements of the mandible. The known gender from patient records will serve as the reference standard. This study will assess the reliability of AI as an objective tool for gender determination for forensic purposes.

Evaluation of Palatal Rugae-Based Identification After Maxillary Expansion Using Local Morphological Patch Analysis

This study investigates the reliability of palatal rugae-based identification following maxillary expansion procedures, including Miniscrew-Assisted Rapid Palatal Expansion (MARPE) and Surgically Assisted Rapid Maxillary Expansion (SARME). Because maxillary expansion alters the morphology of the palatal vault and the spatial relationship of the palatal rugae, conventional global alignment of the anterior palate may not provide stable post-treatment identification. The study evaluates a novel three-dimensional analysis approach based on separately segmented and independently aligned palatal ruga patches, with emphasis on preserving local morphological characteristics rather than global palatal configuration. Within-subject deviations before and after treatment will be compared with between-subject deviations to determine whether individual-specific ruga morphology remains distinguishable after expansion. Machine learning-based classification models using four independently aligned ruga patches will be developed to differentiate genuine matches from impostor comparisons. The primary analysis focuses on surgical expansion groups (MARPE and SARME) to assess whether pre-expansion scans can still be matched to post-expansion scans of the same individual. Secondary analyses will compare the performance of the ruga patch model with conventional anterior palate alignment and will simulate a mixed forensic database containing both treated and untreated individuals. The findings may provide evidence for the forensic applicability of palatal rugae identification after orthopedic and surgically assisted maxillary expansion procedures.