WEAKLY SUPERVISED LEARNING OF PIECEWISE RIGID TRANSFORMATION FOR ORTHOGNATHIC SURGICAL RECONSTRUCTION OF DENTOFACIAL DEFORMITY

Abstract

We propose a data-driven surgical reconstruction algorithm under observation that the volumetric deformation of pre- and post-op dentofacial deformity volumes can be explained by a collection of rigidly movable pieces of the mandible and the maxilla. The decomposition of the deformable registration into piecewise rigid transformations regarding underlying hard pieces relaxes the supervision of dense voxel-wise correspondence. We design a novel piecewise rigid transformation constraint to enforce the semantic and meaningful correspondence of maxillofacial structures, avoiding bony structural distortions. The interpretable voxel-wise displacement fields account for morphology variations caused by orthognathic surgery and enable the prediction of the post-op craniofacial shapes. The experimental results showcase the effectiveness of the proposed approach on orthognathic surgical reconstruction of the clinically obtained cone-beam computed tomography with dentofacial deformity.