Deep learning in the diagnosis of maxillary sinus diseases: A systematic review.

ABSTRACT

OBJECTIVES: To assess the performance of deep learning (DL) in the detection, classification, and segmentation of maxillary sinus diseases. MATERIALS AND METHODS: An electronic search was conducted by two reviewers on databases including PubMed, Scopus, Cochrane, and IEEE. All English papers published no later than February 7, 2024, were evaluated. Studies related to DL for diagnosing maxillary sinus diseases were also searched in journals manually. RESULTS: 14 of 1167 studies were eligible according to the inclusion criteria. All studies trained DL models based on radiographic images. Six studies applied to detection tasks, one focused on classification, two segmented lesions, and five studies made a combination of 2 types of DL models. The accuracy of the DL algorithms ranged from 75.7% to 99.7%, and the area under curves (AUC) varied between 0.7 and 0.997. CONCLUSION: DL can accurately deal with the tasks of diagnosing maxillary sinus diseases. Students, residents, and dentists could be assisted by DL algorithms to diagnose and make rational decisions on implant treatment related to maxillary sinuses.