AI-Powered Multi-Label Dental Disease Detection from Panoramic Radiographs A YOLO-Based Review and Future Directions

DOI

10.2991/978-94-6239-756-9_13How to use a DOI?

Keywords

Panoramic radiography; Dental AI; YOLO; multi-label disease detection; tooth-level localization; FDI tooth numbering; deep learning; clinical data integration; dental imaging analytics; diagnostic automation

Abstract

The panoramic radiographs offer a synoptic view of the dentoalveolar anatomy but is cumbersome to analyze reliably in the presence of concurrent caries, loss of periodontal bone and impactions. By utilizing modern deeply learned object detectors (YOLO-family) that have become commoditized, the review challenges this technology to identify multiple diseases at once, give attributions of individual teeth, and combine automated object detection with patient covariates like age, oral hygiene, and medical history. YOLO models have been found to perform high-fidelity localization of teeth and lesions empirically and with high speed, compared to segmentation paradigms such as U-Net and Mask R-CNN that are highly accurate but have a very high computational latency, which limits their applications to real-time deployment. The initial multimodal frameworks that combine imaging with patient metadata are characterized by significant increases in diagnostic accuracy as well as predictive power. Nevertheless, significant challenges remain to be overcome most notably due to the lack of large well-marked datasets, the lack of automated FDI-based tooth indexing schemes, and insufficient architectural studies in the field of multi-pathology detection in a single panorama. Overall, the synthesis highlights the fact that YOLO-based pipelines are best poised to enable the use of dental radiographic interpretation, provided that standardized datasets and fine multi-label frameworks are created, and the smooth integration of clinical metadata into individual diagnostic intelligence is facilitated. The review distinctly outlines the new paradigm of YOLO in panoramic radiography in the integrated multi-label dental disease analytics.

Copyright

© 2026 The Author(s)

Open Access

Open Access This chapter is licensed under the terms of the Creative Commons Attribution-NonCommercial 4.0 International License (http://creativecommons.org/licenses/by-nc/4.0/), which permits any noncommercial use, sharing, adaptation, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons license and indicate if changes were made.

Download article (PDF)

TY  - CONF
AU  - Aradhana S. Thorat
AU  - Archana Chaudhari
PY  - 2026
DA  - 2026/08/31
TI  - AI-Powered Multi-Label Dental Disease Detection from Panoramic Radiographs A YOLO-Based Review and Future Directions
BT  - Proceedings of the Conference on Bioengineering for Global Health (SYMRESEARCH 2.0 2025)
PB  - Atlantis Press
SP  - 172
EP  - 182
SN  - 2468-5747
UR  - https://doi.org/10.2991/978-94-6239-756-9_13
DO  - 10.2991/978-94-6239-756-9_13
ID  - Thorat2026
ER  -