@Article{Suski2025,
journal="Journal of Stomatology",
issn="0011-4553",
volume="78",
number="3",
year="2025",
title="Machine learning in dental photography",
abstract="Dental photography has evolved from a simple documentation tool to a key component in modern clinical and diagnostic workflows, enhancing diagnostic precision, treatment planning, and patient communication. Recent advancements in artificial intelligence (AI) and machine learning (ML) hold potential to further revolutionize dental photography, particularly through automated image analysis. This review aimed to explore the application of ML in dental photography across various dental specialties, assessing its role in diagnostics, treatment planning, and workflow optimization.   A literature review was conducted using PubMed database, focusing on articles from 2014 to 2024 related to ML in dental photography. Based on inclusion criteria, of the initial 51 results, 23 studies were considered, including reviews, systematic reviews, and original research, all English-written papers.   ML applications in dental photography span numerous fields, such as conservative and restorative dentistry, orthodontics, and oral medicine. ML models, particularly convolutional neural networks, demonstrated high accuracy in caries detection, orthodontic diagnostics, and oral pathology identification from dental images. Notable advan­cements included automated plaque assessment, diagnostic support for caries and periodontal conditions, and landmark identification in orthodontic imaging. However, challenges, such as data quality, image variability, and the need for extensive datasets, still remain. ML-driven analysis of dental photography offers promising bene­fits for enhancing diagnostic workflows, particularly in remote or resource-limited settings. While substantial progress has been made, further refinement and dataset expansion are essential for broader clinical adoption.",
author="Suski, Piotr
and Tokarczuk, Oskar Dominik
and Smala, Kamila
and Wiśniowski, Maksymilian
and Szalewski, Leszek",
pages="236--243",
doi="10.5114/jos.2025.154386",
url="http://dx.doi.org/10.5114/jos.2025.154386"
}