Akademik Veri Yönetim Sistemi
Children, cilt.12, sa.11, 2025 (SCI-Expanded, Scopus)
Highlights: What are the main findings? The transformer-based RT-DETR-X model achieved the highest diagnostic accuracy (mAP@0.5 = 0.43) in detecting and classifying furcation lesions on pediatric panoramic radiographs, outperforming both YOLOv12x and RT-DETR-L models. This study introduces an innovative integration of panoramic radiographic lesion classification with evidence-based treatment thresholds, directly linking lesion severity to root canal therapy or extraction decisions in pediatric dentistry. What are the implications of the main findings? The proposed AI framework provides standardized and reproducible diagnostic support for primary molar treatment planning, reducing inter-observer variability and clinical ambiguity. Lightweight architectures such as YOLOv12x can serve for rapid chairside triage, while transformer-based models like RT-DETR-X enable high-accuracy confirmatory analysis suitable for clinical decision support and resource-limited settings. Background/Aim: Furcation lesions in primary molars are critical in pediatric dentistry, often guiding treatment decisions between root canal therapy and extraction. This study introduces a deep learning-based clinical decision-support system that directly maps radiographic lesion characteristics to corresponding treatment recommendations—a novel contribution in the context of pediatric dental imaging, also represents the first integration of panoramic radiographic classification of primary molar furcation lesions with treatment planning in pediatric dentistry. Materials and Methods: A total of 387 anonymized panoramic radiographs from children aged 3–13 was labeled into five distinct bone lesion categories. Three object detection models (YOLOv12x, RT-DETR-L, and RT-DETR-X) were trained and evaluated using stratified train-validation-test splits. Diagnostic performance was assessed using precision, recall, mAP@0.5, and mAP@0.5–0.95. Additionally, qualitative accuracy was evaluated with expert-annotated samples. Results: Among the models, RT-DETR-X achieved the highest performance (mAP@0.5 = 0.434), representing modest but clinically promising diagnostic capability, despite the limitations of a relatively small, single-center dataset. Specifically, RT-DETR-X achieved the highest diagnostic accuracy (mAP@0.5 = 0.434, Recall = 0.483, Precision = 0.440), followed by YOLOv12x (mAP@0.5 = 0.397, Precision = 0.442) and RT-DETR-L (mAP@0.5 = 0.326). All models successfully identified lesion types and supported corresponding clinical decisions. The system reduced diagnostic ambiguity and showed promise in supporting clinicians with varying levels of experience. Conclusions: The proposed models have potential for standardizing diagnostic outcomes, especially in resource-limited settings and mobile clinical environments.