Skull Shape Reconstruction Using Cascaded Convolutional Networks

Cranial implant design, Anatomical reconstruction, 3D shape completion, Convolutional neural networks, Generative adversarial networks

Designing a cranial implant to restore the protective and aesthetic function of the patient's skull is a challenging process that requires a substantial amount of manual work, even for an experienced clinician. While computer-assisted approaches with various levels of required user interaction exist to aid this process, they are usually only validated on either a single type of simple synthetic defect or a very limited sample of real defects. The work presented in this paper aims to address two challenges: (i) design a fully automatic 3D shape reconstruction method that can address diverse shapes of real skull defects in various stages of healing and (ii) to provide an open dataset for optimization and validation of anatomical reconstruction methods on a set of synthetically broken skull shapes.
We propose an application of the multi-scale cascade architecture of convolutional neural networks to the reconstruction task. Such an architecture is able to tackle the issue of trade-off between the output resolution and the receptive field of the model imposed by GPU memory limitations. Furthermore, we experiment with both generative and discriminative models and study their behavior during the task of anatomical reconstruction.
The proposed method achieves an average surface error of 0.59 for our synthetic test dataset with as low as 0.48 for unilateral defects of parietal and temporal bone, matching state-of-the-art performance while being completely automatic. We also show that the model trained on our synthetic dataset is able to reconstruct real patient defects.