There is an increasing call for radiation dose tracking from medical examinations and patient-specific dose management has become a great concern. Especially, since the computed tomography (CT) can lead to a significant amount of patient dose, fast and accurate CT dose estimation has become an important issue. For the purpose of real-time scan-protocol optimization and patient-specific dose management in cone-beam CT (CBCT), we introduce a hybrid approach that estimates the absorbed dose distributions in reconstructed images. The proposed method employs a numerical algorithm for the estimation of primary dose distributions and a deep learning technique for the estimation of secondary ones. The validation of the proposed method is performed by comparative analysis with the Monte Carlo (MC) and conventional model-based dose reconstruction methods for typical dentoalveolar CBCT protocols which consider the simple cylindrical water and anthropomorphic head phantoms as a patient. To verify each stage of the proposed method, we have developed the list-mode MC methodology for CT dose reconstructions and applied it to dental CBCT to analyze the dose distributions in terms of local primary and remote secondary doses. The proposed method shows good agreement with the MC method and consumes a significantly lower computational cost. While the direct MC simulation takes several hours for estimating an absorbed energy map for a complete CBCT scan, the proposed method can generate an absorbed dose map from a CT image in few seconds. The patient-dose benefits in CBCT due to the width-truncated detector geometry and the beam-intensity modulation are also investigated for a wide range of parameters. The dose benefit with the width-truncated geometry linearly increases as the detector-offset width is decreased. Considering both patient dose and voxel noise, the gain from the modulation techniques is marginal compared to the conventional uniform power scanning. This study will be useful for the development of dental CBCT imaging techniques in terms of patient-specific dose.