Reliability of Artificial Intelligence Using Cone Beam Computed Tomography (CBCT) Images in Maxillofacial Region – A Systematic Review and Meta Analysis

Abstract

BACKGROUND: Artificial Intelligence (AI) has the ability to process huge datasets, disclose human essence computationally, and perform like humans as technology advances. The applications of machine learning and artificial intelligence has become popular within the last decade.

AIM: The present study aimed to investigate the performance of AI using cone-beam computed tomography (CBCT) images

MATERIALS AND METHOD: Studies using application of Cone beam computed tomography to develop or implement AI models were sought by searching electronic databases including PubMed, Google scholar, Scopus in the field of Dental and maxillofacial Radiology. The customized assessment criteria based on PRISMA guidelines and COCHRANE assessment tool were adapted for quality analysis of the studies included.

RESULT: All the studies were methodologically acceptable with low risk of bias due to two step selection process. Most studies focused on AI applications for an automated localization of cephalometric landmarks, classification/segmentation of maxillofacial cysts and/or tumors, and identification of periodontitis/periapical disease. The performance of AI models varies among different algorithms.

CONCLUSION: The application of AI for detection and segmentation using CBCT images is comparable to services offered by trained dentists and can potentially expedite and enhance the interpretive process. Implementing AI into clinical dentistry can analyse a large number of CBCT studies and flag the ones with significant findings, thus increasing efficiency.