Paranasal sinus analysis based on deep learning and machine learning techniques: A comprehensive survey

Abstract

This survey provides an in-depth review of recent advancements in forensic anthropology through the application of imaging and modeling techniques for paranasal sinus structures. The focus is on exploring various studies that leverage the paranasal sinuses for the identification of individuals and demographic analysis, including age and gender estimation, especially when traditional methods such as fingerprint analysis, dental records, or DNA profiling are not feasible. Additionally, the survey aims to serve as a foundation for future work in similar analyses and segmentation tasks. These methods are especially useful in forensic contexts, such as those involving skeletonized remains where other anatomical structures are absent. The paper discusses several case studies, including the segmentation of paranasal sinuses as well as their classification for establishing biological profiles in diverse populations. The effectiveness of these 3D modeling approaches in predicting demographic characteristics such as sex, age, and ethnicity is also highlighted. Special emphasis is placed on the robustness and reliability of sinus morphology as both a forensic identifier and a tool for demographic inference.