Enhanced artificial intelligence-based diagnosis using CBCT with internal denoising: Clinical validation for discrimination of fungal ball, sinusitis, and normal cases in the maxillary sinus

Kyungsu Kim, Chae Yeon Lim, Joong Bo Shin, Myung Jin Chung, Yong Gi Jung

Abstract: Highlights•Compared with the current CBCT-based AI computer-aided diagnostic (CAD) technology, our CBCT CAD system improves the diagnostic performance by additionally considering a noise-removing process for the first time.•We demonstrate the clinical efficacy of our CBCT CAD system by comparing it with multiple otolaryngologists.•We validate the noise reduction function through a comparison of actual CBCT and matching CT, suggesting that our method can be helpful not only for simple diagnosis but also for the interpretation of AI results.