Uncertainty-based Active Learning by Bayesian U-Net for Multi-label Cone-Beam CT Segmentation

This study assessed the efficacy of Active Learning (AL) strategies training AI models for accurate multi-label segmentation and detection of periapical lesions in cone-beam CTs (CBCTs) using a limited dataset.

Source: Journal of Endodontics - November 16, 2023 Category: Dentistry Authors: Jiayu Huang, Nazbanoo Farpour, Bingjian J. Yang, Muralidhar Mupparapu, Fleming Lure, Jing Li, Hao Yan, Frank C. Setzer Tags: Basic Research-Technology Source Type: research