Decision-Support for Restorative Dentistry: Hybrid Optimization Enhances Detection on Panoramic Radiographs

Abstract

Highlights: What are the main findings? A hybrid HGWO-PSO + SVM pipeline achieved the best five-class performance on panoramic radiographs (Accuracy 73.15%, macro-F1 0.728), outperforming a baseline CNN and conventional ML models. A patient-level 80/20 split and 5-fold CV showed stable results despite class imbalance; most errors occurred between radiopaque restorations (crowns vs. bridges). What are the implications of the main findings? Optimization-assisted feature selection can provide a more balanced and interpretable alternative to end-to-end DL on small, single-center datasets, supporting real-world deployment. The system is decision-supportive for restorative dentistry—helping standardize re-porting and triage—while larger, multi-center datasets and stronger DL baselines are needed for broader clinical adoption. Background/Objectives: Artificial intelligence (AI) has been increasingly used to support radiological assessment in dentistry. We benchmarked machine learning (ML), deep learning (DL), and a hybrid optimization-assisted approach for the automatic five-class image-level classification of dental restorations (filling, implant, root canal treatment, fixed partial denture/bridge, crown) on panoramic radiographs. Methods: We analyzed 353 anonymized panoramic images comprising 2137 labeled restorations, acquired on the same device. Images were cropped and enhanced (histogram equalization and CLAHE), and texture features were extracted with GLCM. A three-stage pipeline was evaluated: (i) GLCM-based features classified by conventional ML and a baseline DL model; (ii) Hybrid Grey Wolf–Particle Swarm Optimization (HGWO-PSO) for feature selection followed by SVM; and (iii) a CNN trained end-to-end on raw images. Performance was assessed with an 80/20 per-patient split and 5-fold cross-validation on the training set. While each panoramic radiograph may contain multiple restorations, in this study we modeled the task as single-label, image-level classification (dominant restoration type) due to pipeline constraints; this choice is discussed as a limitation and motivates multi-label, localization-based approaches in future work. The CNN baseline was implemented in TensorFlow 2.12 (CUDA 11.8/cuDNN 8.9) and trained with Adam (learning rate 1 × 10−4), with a batch size 32 and up to 50 epochs with early stopping (patience 5); data augmentation included horizontal flips, ±10° rotations, and ±15% brightness variation. A post hoc power analysis (G*Power 3.1; α = 0.05, β = 0.2) confirmed sufficient sample size (n = 353, power > 0.84). Results: The HGWO-PSO + SVM configuration achieved the highest accuracy (73.15%), with macro-precision/recall/F1 = 0.728, outperforming the CNN (68.52% accuracy) and traditional ML models (SVM 67.89%; DT 59.09%; RF 58.33%; K-NN 53.70%). Conclusions: On this single-center dataset, the hybrid optimization-assisted classifier moderately improved detection performance over the baseline CNN and conventional ML. Given the dataset size and class imbalance, the proposed system should be interpreted as a decision-supportive tool to assist dentists rather than a stand-alone diagnostic system. Future work will target larger, multi-center datasets and stronger DL baselines to enhance generalizability and clinical utility.