Related Experiment Video
Updated: Aug 5, 2026
Reliability of Artificial Intelligence-Based Cone Beam Computed Tomography Integration with Digital Dental Images
Published on: February 23, 2024
Cross-Vendor Robustness of a Hybrid Deep Learning Framework for Four-Stage Periodontitis Classification on Panoramic
Sang-Jeong Lee1, Su Yang2, Ji Yong Han3
1Department of Artificial Intelligence, Tech University of Korea, Siheung, 15073, Republic of Korea.
Objectives:
Although deep learning for periodontitis diagnosis on panoramic radiographs has advanced rapidly, most studies use single-vendor data and cross-vendor generalization is rarely evaluated. Therefore, we evaluate the cross-vendor robustness of a hybrid CNN-CAD framework for automated four-stage periodontitis classification.
Methods:
Five hundred panoramic radiographs were retrospectively collected from three vendors (Instrumentarium, n=400; Vatech, n=50; PointNix, n=50). The framework extends a previously published hybrid pipeline by adding a YOLO-based CNN for missing-teeth quantification, enabling four-stage classification according to the 2017 World Workshop criteria. Three dataset configurations were evaluated: pooled multi-vendor training and two leave-one-device-out (LODO) splits. We compared segmentation backbones (U-Net, Dense U-Net, SegNet, Mask R-CNN) and YOLO detector variants. Agreement with three oral and maxillofacial radiologists (3, 5 and 10 years of experience) was assessed using mean absolute difference (MAD), Pearson and intraclass correlation, Bland-Altman, and Passing-Bablok analyses.
Results:
Under pooled multi-vendor training, Mask R-CNN achieved Dice coefficients of 0.96, 0.92 and 0.94 for periodontal bone level, cemento-enamel junction level and teeth/implants respectively; CNNv4-tiny reached a mean AP of 0.86 for missing teeth. The MAD between automated and expert staging was 0.31, overall image-level ICC was 0.93 (95% CI 0.86-0.97; p<0.01), and Bland-Altman bias against the most experienced radiologist was 0.007. Under LODO, Dice coefficient dropped to 0.75-0.86 (all p<0.001 versus pooled), quantifying substantial vendor-induced domain shift.
Conclusions:
The hybrid framework achieves expert-level agreement under pooled multi-vendor training but degrades in held-out vendors, providing a quantitative reference for vendor-induced domain shift in panoramic radiograph AI and motivating vendor-aware training or domain adaptation in future clinical deployments.
Advances In Knowledge:
This work provides, to our knowledge, the first cross-vendor benchmark for deep-learning-based periodontitis staging on panoramic radiographs and quantifies vendor-induced domain shift directly addressing the external-validation gap recently identified in this journal.