ImplantFormer: Vision Transformer based Implant Position Regression Using Dental CBCT Data
This work addresses the need for objective and automated implant positioning in dental prosthetics, which is incremental as it applies a transformer-based method to a specific medical domain.
The paper tackles the problem of subjective implant position design in dentistry by proposing ImplantFormer, a vision transformer-based network that automatically predicts implant positions from dental CBCT data, achieving superior performance over existing methods in experiments using five-fold cross-validation.
Implant prosthesis is the most appropriate treatment for dentition defect or dentition loss, which usually involves a surgical guide design process to decide the implant position. However, such design heavily relies on the subjective experiences of dentists. In this paper, a transformer-based Implant Position Regression Network, ImplantFormer, is proposed to automatically predict the implant position based on the oral CBCT data. We creatively propose to predict the implant position using the 2D axial view of the tooth crown area and fit a centerline of the implant to obtain the actual implant position at the tooth root. Convolutional stem and decoder are designed to coarsely extract image features before the operation of patch embedding and integrate multi-level feature maps for robust prediction, respectively. As both long-range relationship and local features are involved, our approach can better represent global information and achieves better location performance. Extensive experiments on a dental implant dataset through five-fold cross-validation demonstrated that the proposed ImplantFormer achieves superior performance than existing methods.