Blog
A generative adversarial inpainting network to enhance prediction of periodontal clinical attachment level
This study addresses a key challenge in periodontal diagnostics: accurately estimating the clinical attachment level (CAL) from intraoral radiographs. Although deep learning models can predict CAL, bitewing radiographs have a limited field of view, preventing CNNs from analyzing anatomical structures that lie outside the captured region. To overcome this limitation, the authors developed a generative adversarial inpainting network using partial convolutions to reconstruct missing anatomy and provide additional contextual information for CAL prediction. A large retrospective dataset was used, including 80,326 images for training, 12,901 for validation, and 10,687 for direct comparison between inpainted and non-inpainted methods. Statistical analyses (MBE, MAE, Dunn’s pairwise test) demonstrated that the inpainting approach significantly improved prediction performance. The MAE decreased from 1.50 mm to 1.04 mm, and all pairwise comparisons confirmed superior accuracy for the inpainted models. The study concludes that GAN-based inpainting enhances CAL prediction from bitewing and periapical radiographs and achieves accuracy within the clinically acceptable 1 mm threshold. Clinically, this work highlights how AI can compensate for inherent radiographic limitations, offering more reliable assessments even when anatomy falls outside the imaging field.
Artificial intelligence; Deep learning; GAN; Inpainting; Periodontal disease
Year: 2022
Modality: Bitewing; Periapical
Dataset: 80,326 train / 12,901 val / 10,687 test
Network Architecture: GAN
Metrics: MAE, MBE, Dunn test
AP Qty: 3
Supervisor: No information
Experience: 11, 22, 38 years
Expertise: Periodontist; General dentists
Tool/System: No information
ML Task: Classification and Object Detection
**Objective:**Determine if GAN-based inpainting improves CAL prediction..
GAN-based inpainting enhances CAL prediction, staying within ±1 mm clinical standards.