Deep Learning-based Facial Appearance Simulation Driven by Surgically Planned Craniomaxillofacial Bony Movement

TL;DR

This paper introduces ACMT-Net, a deep learning model that accurately simulates facial appearance changes after jaw surgery by modeling soft tissue and bone movement correspondence, offering a faster alternative to traditional FEM methods.

Contribution

The paper presents ACMT-Net, a novel deep learning approach that incorporates attentive correspondence to improve accuracy in facial change simulation post-surgery.

Findings

Achieves comparable accuracy to FEM-based methods

Significantly reduces computational time

Effective on patients with jaw deformity

Abstract

Simulating facial appearance change following bony movement is a critical step in orthognathic surgical planning for patients with jaw deformities. Conventional biomechanics-based methods such as the finite-element method (FEM) are labor intensive and computationally inefficient. Deep learning-based approaches can be promising alternatives due to their high computational efficiency and strong modeling capability. However, the existing deep learning-based method ignores the physical correspondence between facial soft tissue and bony segments and thus is significantly less accurate compared to FEM. In this work, we propose an Attentive Correspondence assisted Movement Transformation network (ACMT-Net) to estimate the facial appearance by transforming the bony movement to facial soft tissue through a point-to-point attentive correspondence matrix. Experimental results on patients with jaw deformity show that our proposed method can achieve comparable facial change prediction accuracy compared with the state-of-the-art FEM-based approach with significantly improved computational efficiency.