Journal of Biomedicine and Practice – Biomeditsina va amaliyot jurnali 11-том 3-нөмір (2026)
ENHANCING THE EFFICIENCY OF MULTIMODAL REGISTRATION OF CBCT AND INTRAORAL SCANS BASED ON ARTIFICIAL INTELLIGENCE
ИСМОИЛОВ Ахроржон Анваржон оглы, САНАКУЛОВ Джамшед Облобердиевич
Аңдатпа
This study aims to evaluate the efficiency of artificial intelligence (AI)-based multimodal registration of cone-beam computed tomography (CBCT) and intraoral scan (IOS) data within the framework of advancing digital technologies in dentistry. In modern implantology, high-precision diagnostics and the development of individualized treatment plans rely heavily on three-dimensional (3D) models. CBCT provides detailed information on bone structures, while IOS accurately captures dental surfaces and soft tissues. The integration of these two imaging modalities significantly improves the quality of clinical decision-making. The study analyzed CBCT and IOS datasets from 23 patients. Registration was performed using three different approaches: manual registration (MR), semi-automatic registration (SR), and AI-based automatic registration (AR). Evaluation metrics included registration time, median surface deviation (MSD), and root mean square error (RMS). The results demonstrated a significant advantage of the AI-based method. The AR approach reduced registration time by more than tenfold and improved accuracy metrics (MSD ≈ 0.04 mm). This approach minimizes human-related errors and enhances the reproducibility of results. In conclusion, AI-based multimodal registration systems exhibit high efficiency in dentistry and play a crucial role in optimizing implantological planning.
искусственный интеллект, CBCT, интраоральное сканирование, мультимодальная регистрация, 3D-моделирование, имплантология, цифровая стоматологияartificial intelligence, CBCT, intraoral scanning, multimodal registration, 3D modeling, implantology, digital dentistrySun’iy intellekt, CBCT, intraoral skan, multimodal registratsiya, 3D modellashtirish, implantologiya, raqamli stomatologiya
Метадеректер дереккөзі: журналдың OAI-PMH архиві · Sindex толық мәтінді сақтамайды, дереккөзге сілтеме береді.