Deep Learning for Detecting Periapical Bone Rarefaction in Panoramic Radiographs: A Systematic Review and Critical Assessment.
Authors
Affiliations (8)
Affiliations (8)
- DDS, MsD Student, Departments of Dental Radiology and Imaging and Endodontics, Faculty of Dentistry, University of Fortaleza, Fortaleza, Ceará, Brazil.
- DDS, MsD Student, Department of Stomatology, Faculty of Dentistry, University of Fortaleza, Fortaleza, Ceará, Brazil.
- DDS, MsD Student, Department of Operative Dentistry and Dental Materials, Faculty of Dentistry, University of Fortaleza, Fortaleza, Ceará, Brazil.
- Undergraduate, Faculty of Dentistry, University of Fortaleza, Fortaleza, Ceará, Brazil.
- MSc, Center for Technological Sciences, University of Fortaleza, Fortaleza, Ceará, Brazil.
- MSc, Laboratory of Image Processing and Computer Simulation (LAPISCO), Federal Institute of Education, Science and Technology of Ceará, Fortaleza Campus, Fortaleza, Ceará, Brazil.
- DDS, MSc, PhD, Departments of Dental Radiology and Imaging and Stomatology, Faculty of Dentistry, University of Fortaleza, Fortaleza, Ceará, Brazil.
- DDS, MsD, PhD, Department of Endodontics, Faculty of Dentistry, University of Fortaleza, Fortaleza, Ceará, Brazil.
Abstract
To evaluate deep learning (DL)-based models for detecting periapical bone rarefaction (PBRs) in panoramic radiographs (PRs), analyzing their feasibility and performance in dental practice. A search was conducted across seven databases and partial grey literature up to November 15, 2024, using Medical Subject Headings and entry terms related to DL, PBRs, and PRs. Studies assessing DL-based models for detecting and classifying PBRs in conventional PRs were included, while those using non-PR imaging or focusing solely on non-PBR lesions were excluded. Two independent reviewers performed screening, data extraction, and quality assessment using the Quality Assessment of Diagnostic Accuracy Studies-2 tool, with conflicts resolved by a third reviewer. Twelve studies met the inclusion criteria, mostly from Asia (58.3%). The risk of bias was moderate in 10 studies (83.3%) and high in 2 (16.7%). DL models showed moderate to high performance in PBR detection (sensitivity: 26-100%; specificity: 51-100%), with U-NET and YOLO being the most used algorithms. Only one study (8.3%) distinguished Periapical Granuloma from Periapical Cysts, revealing a classification gap. Key challenges included limited generalization due to small datasets, anatomical superimpositions in PRs, and variability in reported metrics, compromising models comparison. This review underscores that DL-based has the potential to become a valuable tool in dental image diagnostics, but it cannot yet be considered a definitive practice. Multicenter collaboration is needed to diversify data and democratize those tools. Standardized performance reporting is critical for fair comparability between different models.