# Segmentation-Based Multi-Class Detection and Radiographic Charting of Periodontal and Restorative Conditions on Bitewing Radiographs Using Deep Learning

## TL;DR

This study uses deep learning to detect and segment multiple dental and periodontal conditions on bitewing radiographs with varying success across different classes.

## Contribution

A novel YOLOv8x-seg-based model is proposed for multi-class detection and segmentation of periodontal and restorative conditions on bitewing radiographs.

## Key findings

- The model achieved high precision and recall for alveolar bone loss detection.
- Lower performance was observed for low-frequency conditions like cervical marginal gaps and secondary caries.
- The model demonstrated acceptable segmentation performance with mAP@0.5 of 0.30.

## Abstract

Background/Objective: Bitewing radiographs are widely used for evaluating dental caries, restorations, and periodontal status due to their low radiation dose and high image quality. While artificial intelligence–based studies are common for other dental imaging modalities, multi-class diagnostic charting on bitewing radiographs remains limited. This study aimed to simultaneously detect eight periodontal and restorative parameters using a YOLOv8x-seg–based deep learning model and to assess its diagnostic performance. Materials and Methods: A total of 1197 digital bitewing radiographs were retrospectively analyzed and annotated by experts, resulting in 7860 labels across eight conditions. Periodontal conditions included alveolar bone loss, dental calculus, and furcation defects, while restorative and dental conditions comprised caries, cervical marginal gaps, open contacts, overhanging fillings, and secondary caries. The dataset was divided on a patient basis into training (80%), validation (10%), and test (10%) sets. The YOLOv8x-seg model was trained for 800 epochs with extensive data augmentation, and performance was evaluated using precision, recall, and F1-score, along with confusion matrices. Results: The model showed the highest accuracy in the alveolar bone loss class (precision: 0.84, recall: 0.93, F1: 0.88). While moderate performance was achieved for dental calculus (F1: 0.58) and caries (F1: 0.57) detection, lower scores were recorded in low-frequency classes such as cervical marginal gap (F1: 0.23), secondary caries (F1: 0.29), overhanging filling (F1: 0.35), furcation defect (F1: 0.40), and open contact (F1: 0.41). The overall segmentation performance achieved an mAP@0.5 of 0.30 and an mAP@0.5:0.95 of 0.10, indicating an acceptable performance level for segmentation-based multi-class models. Conclusions: The obtained findings demonstrate that the YOLOv8x-seg architecture can detect and segment periodontal conditions with high success and restorative parameters with moderate success in automation processes in bitewing radiographs. Accordingly, the model presents a methodologically feasible framework for the multiple and simultaneous radiographic evaluation of periodontal and restorative findings on bitewing radiographs, with performance varying across classes and lower sensitivity observed in low-frequency conditions.