Inteligencia artificial en la detección de caries dental en radiografías periapicales.

Abstract

Artificial intelligence (AI) has been advancing in dentistry, especially when detecting dental caries. Currently, a series of studies have indicated that AI models, particularly convolutional neural networks (CNN), are ahead of dental professionals. This work aims to determine the differences in the detection of dental caries by analyzing periapical radiographs between traditional methods and artificial intelligence in terms of accuracy, sensitivity, and specificity. This study was conducted through a systematic literature review with scientific databases, including Web of Science, PubMed, Cochrane Library, and IEEE Xplore. The results indicate that convolutional neural networks can significantly improve caries detection. However, there is a need for further research to establish whether it is the definitive tool for caries diagnosis. In conclusion, while artificial intelligence represents remarkable progress in dentistry, its widespread implementation requires addressing impediments, such as performance variability depending on the data type and images. Nevertheless, its ability to improve diagnostic accuracy and its relevance to clinical practice makes it a promising tool for advancing dental radiographic diagnosis. Keywords: Artificial intelligence, Dental caries, Periapical radiographs