Deep Learning for Periodontitis Diagnosis on Two Dimensional Dental Radiograph: A Systematic Review

Widiasri, Monica and Lomanto, Jordan (2026) Deep Learning for Periodontitis Diagnosis on Two Dimensional Dental Radiograph: A Systematic Review. Jurnal INFOTEL, 17 (4). pp. 892-919. ISSN p-ISSN: 2085-3688, e-ISSN: 2460-0997

PDF rev paper Infotel - Deep Learning for Periodontitis Diagnosis on Two Dimensional Dental Radiograph A Systematic Review.pdf Download (2MB)

Abstract

Periodontitis is an inflammatory disease that affects the supporting structures of the teeth and is a major contributor to tooth loss. Traditional diagnosis through clinical examination and manual interpretation of two-dimensional (2D) dental radiographs is prone to variability and subjectivity. The emergence of deep learning (DL) has improved the way medical images are analyzed, including dental radiography. This study systematically reviews the existing literature that uses DL approaches for the diagnosis of periodontitis using two-dimensional (2D) dental radiographic images and evaluates their diagnostic performance compared to clinical evaluations. A systematic literature review (SLR) was conducted following the PRISMA 2020 protocol and guided by the PICO (Populations, Interventions, Comparisons, Outcomes) framework. Five major databases (Scopus, PubMed, Semantic Scholar, Web of Science, and ScienceDirect) were searched for relevant studies published between 2016 and 2025. A total of 27 studies (in 29 reports) were included based on eligibility criteria, covering classification, segmentation, or detection tasks using panoramic, periapical, or bitewing radiographs. Most DL models achieved excellent performance with classification accuracies often exceeding 80% and segmentation Dice coefficients greater than 0.88. Although some models outperformed clinicians, external validation and real-world deployment remain limited. In conclusion, this review shows the feasibility of DL approaches in the diagnosis of automated periodontitis using 2D radiographs, although challenges and limitations remain in standardization, robust validation, and integration into clinical workflows.

Item Type:	Article
Uncontrolled Keywords:	Systematic Review, Deep Learning, Periodontitis Diagnosis, 2D Dental Radio- graph, Computer Vision
Subjects:	Q Science > QA Mathematics > QA75 Electronic computers. Computer science
Divisions:	Faculty of Engineering > Department of Informatic
Depositing User:	Monica Widiasri 61151
Date Deposited:	04 Feb 2026 03:11
Last Modified:	04 Feb 2026 03:11
URI:	http://repository.ubaya.ac.id/id/eprint/50235

Actions (login required)

View Item