Efficient tooth gingival margin line reconstruction via adversarial learning

Abstract

Gingival margin morphology plays an important role in the functional and aesthetic restoration of denture. However, this is a challenging task, mainly because there are great differences in the gingival margin morphology between different individuals and different dental positions. To address this problem, we present a deep adversarial network-driven gingival margin line reconstruction (GMLR) framework to automatically obtain the personalized gingival contour for a partially edentulous patient. Specifically, we first establish the training database by a visual distance-based orthogonal projection method to realize the bidirectional reversible mapping between three-dimensional gingival model and two-dimensional depth representation. Then, the GMLR network consists of a dual generator model and a two-scale discriminator model to avoid the loss of the gingival contour details. The proposed generator uses the global-to-local scheme to reconstruct clear gingival contour images in an end-to-end manner, while two-scale discriminator aims to guide the generator to produce a globally consistent gingival contour result with finer details. In addition, a comprehensive loss function is presented to combine gingival contour details, structure and perceptual features. Finally, we propose to reconstruct the personalized gingival line by the polygon-based node insertion and the feature line reconstruction method via the tangent constraint. Experimental results demonstrate that, under the same conditions, the proposed method outperforms recent advances on the real-world dental database. Importantly, the reconstructed missing GMLs are basically harmonious with the adjacent teeth and have enough anatomical morphology.