AI and Radiomics: A Systematic Literature Review Exploring the Potential of Texture Analysis in Early Caries Diagnosis

This paper presents a systematic literature review that explores the potential of integrating artificial intelligence and radiomics for the early detection of dental caries. Dental caries, a prevalent global health issue, often goes undetected in its early stages using traditional diagnostic methods such as visual-tactile examination and conventional radiographic imaging. These approaches may fail to consistently identify incipient lesions, leading to delayed treatment and progression of the disease. The integration of artificial intelligence and radiomics, which involves extracting quantitative features from medical images, presents a promising solution for enhancing early caries detection. Radiomics leverages texture analysis techniques to identify subtle changes within dental radiographs that are often imperceptible to the human eye. When combined with AI models, particularly convolutional neural networks, these systems can develop predictive algorithms that detect and characterize early-stage carious lesions with improved accuracy. This literature review explores the potential of AI-radiomic approaches in revolutionizing dental diagnostics by addressing limitations of traditional methods and providing a roadmap for clinical integration. We also discuss the challenges in implementing these technologies, such as data availability, methodological rigor, and ethical considerations, emphasizing the need for robust validation and interdisciplinary collaboration to achieve seamless integration and improved patient outcomes.