AI-Based Early Detection of Enamel Hypomineralization Patterns in Primary Dentition Using Texture Analytics

Abstract

Enamel hypomineralization in primary dentition is a prevalent condition that can lead to increased dental sensitivity, decay, and aesthetic concerns if not detected early. Traditional diagnostic methods rely on clinical examination, which may be subjective and prone to delayed detection. This study proposes an AI-based framework for early detection of enamel hypomineralization patterns using texture analytics on intraoral images. High-resolution images of primary teeth were processed to extract texture features such as Gray-Level Co-occurrence Matrix (GLCM) and Local Binary Patterns (LBP), which were then analyzed using machine learning models to identify characteristic hypomineralization patterns. The proposed approach demonstrated high accuracy and sensitivity in distinguishing affected enamel from healthy tissue, highlighting the potential of AI-assisted diagnostics to support pediatric dental care. Early, non-invasive detection of enamel hypomineralization can improve preventive strategies and reduce the risk of long-term dental complications.