Indian Journal of Forensic Odontology

Artificial Intelligence (AI) has emerged as a transformative tool in forensic odontology, enhancing the accuracy and efficiency of human identification processes. This systematic review examines the applications of AI in forensic odontology, focusing on its role in dental age estimation, sex determination, bite mark analysis, and human identification through dental records. A comprehensive literature search was conducted across PubMed and Scopus databases, covering studies published from January 2010 to February 2025. A total of 18 relevant articles were included in this review. The findings indicate that AI, particularly through machine learning (ML) and deep learning (DL) algorithms, significantly improves the precision and objectivity of forensic dental analyses. Despite these advancements, challenges such as data privacy, ethical considerations, and the need for large, diverse datasets persist. Future research should address these issues to fully integrate AI into routine forensic odontology practice.

Introduction: Forensic odontology relies on craniofacial features for identification when traditional methods fail. The maxillary sinus, with its variable dimensions, offers potential for profiling, yet its link to facial profiles remains under explored. This study aims to assess whether CBCT-derived maxillary sinus dimensional ratios can reliably distinguish frontal and lateral facial profile types in a living population. Methodology:This cross-sectional study enrolled 50 adults (18–60 years) at Kothiwal Dental College, Moradabad, with no craniofacial trauma or sinus pathology. Standardized frontal and lateral photographs categorized profiles (Oval, Square, Round; Convex, Straight, Concave) using anthropometric guidelines. CBCT scans measured bilateral sinus height, width, and depth, calculating ratios (H/W, H/D, W/D, left-right asymmetry). Two blinded observers assessed data, with reliability confirmed by ICC (>0.75). Spearman’s correlation, Kruskal-Wallis, and linear discriminant analysis evaluated associations, using SPSS with p<0.05 significance. Results: Analysis revealed significant gender differences in the Height-to-Width (H/W) ratio (males: 1.95±0.21, females: 1.82±0.24, p=0.033). Frontal profiles showed significant variations in H/W (oval: 1.98±0.43, p=0.047), H/D (round: 1.12±0.36, p=0.001), and W/D (round: 0.56±0.12, p=0.008). Side profiles exhibited significant differences in H/W (straight: 2.05±0.58, p=0.041), H/D (concave: 1.15±0.26, p=0.018), and W/D (concave: 0.58±0.18, p=0.021), suggesting sinus ratios as potential profile markers. Conclusion: Maxillary sinus ratios, particularly H/W, correlate with gender and facial profiles, enhancing forensic identification. CBCT provides a precise tool, though larger, diverse samples are needed to validate findings and address limitations like post-mortem applicability, advancing individualized profiling in forensic odontology.

Bite mark analysis is one of the fundamental characteristic of forensic odontology, aiding in the identification of perpetrators in crimes. Computer-assisted methods have emerged as a promising tool in bite mark analysis, offering improved accuracy and efficiency. This article aims to review the reliability of computerassisted methods for bite mark analysis. This review underscores the potential of computer-assisted methods in bite mark analysis, while emphasizing the need for further research to establish their reliability and validity. Ultimately, this review aims to inform forensic practitioners, researchers, and policymakers about the current state of computer-assisted bite mark analysis and its potential applications in forensic science.