Artificial Intelligence and Machine Learning in Modern Prosthodontics: A Comprehensive Review of Automated Design, Margin Line Extraction, and Radiographic Implant Identification

Artificial intelligence; machine learning; prosthodontics; deep learning; convolutional neural networks; generative adversarial networks.

Dildora Nabiyeva1
Doctor of Medical Sciences (DSc),
Professor. Department of Faculty and
Hospital Therapy No. 1, Rheumatology
and Occupational Pathology
Tashkent State Medical University
Tashkent, Uzbekistan
E-mail: dil_nab@mail.ru
ORCID: https://orcid.org/0000-0002-78791522

Musashaykhov Umidjon Khusanovich2
DSc, Head of the Department of
Propaedeutics of Internal Diseases at the
Andijan State Medical Institute.
Andijan, Uzbekistan
E-mail: musashayxov1989@mail.ru
ORCID: https://orcid.org/0000-0002-16199101

Orifjon Abdumalikovich Aripov3
DSc, professor.Head of the Department at
the Center for the Development of
Professional Qualifications of Medical
Workers, Uzbekistan
E-mail: orifjon-aripov75@mail.ru
ORCID: https://orcid.org/0009-0000-64724604

Nodir Kuziev4
Doctor of Philosophy (PhD) in philosophy.
Associate Professor, Department of
History and Source Studies of Islam,
Philosophy, Bukhara State University
E-mail: n.a.kuziyev@buxdu.uz
ORCID: https://orcid.org/0009-0001-55879759

Shirinova Madina Bonu Gulomjon kizi5
Assistant at the department of Therapeutic
dentistry Samarkand State Medical
University. Samarkand, Uzbekistan
E-mail: Mjiyanova00@mail.ru
ORCID: https://orcid.org/0009-0000-97254215

Allayeva Aziza Nasridinovna6
Bukhara State Medical Institute, Assistant
at the Department of Anatomy and Clinical
Anatomy (OSTA). Bukhara, Uzbekistan
E-mail: aziza.allayeva@bsmi.uz
ORCID: https://orcid.org/0009-0004-26615078

Received-23-05-2026
Revised-25-06-2026
Accepted-29-06-2026

European Journal of Prosthodontics and Restorative Dentistry (2026) 34 (04s), 512-521

Artificial Intelligence and Machine Learning in Modern Prosthodontics: A Comprehensive Review of Automated Design, Margin Line Extraction, and Radiographic Implant Identification

This review examines the expanding role of artificial intelligence (AI) and machine learning (ML) in contemporary prosthodontics, with particular emphasis on automated prosthodontic design, margin line detection, and radiographic implant identification. A systematic search of PubMed, Scopus, Web of Science, and ScienceDirect identified 68 peer-reviewed studies published between 2018 and 2025. The findings indicate that deep learning models, including convolutional neural networks (CNNs), U-Net architectures, generative adversarial networks (GANs), YOLO, and DETR, significantly improve clinical efficiency and diagnostic precision. GANbased systems reduced crown design time by up to 75% while maintaining acceptable marginal adaptation. AI-assisted margin line extraction achieved high accuracy with IoU values above 91%, whereas implant identification models demonstrated mAP scores exceeding 96%. Despite promising outcomes, challenges remain regarding dataset standardization, clinical validation, interoperability, regulatory compliance, and data privacy. Overall, AI-driven technologies demonstrate substantial potential to optimize prosthodontic workflows, enhance treatment planning, and improve patient-centered clinical outcomes.

••••••••••••••••••••••••••••••• ejprd.org - Published by Riset Publication Services LLC

EJPRD

Copyright ©2026 by Riset Publication Services LLC