Deep Generative Networks for Heterogeneous Augmentation of Cranial Defects

TL;DR

This paper introduces three deep generative models to create synthetic skull data, enhancing dataset diversity for better segmentation and personalized cranial implant design.

Contribution

It proposes three volumetric deep generative models for augmenting cranial defect datasets, improving segmentation and implant design processes.

Findings

Synthetic skulls improve defect segmentation accuracy.

Generated data achieves a good balance between heterogeneity and realism.

Synthetic augmentation enhances personalized cranial implant design.

Abstract

The design of personalized cranial implants is a challenging and tremendous task that has become a hot topic in terms of process automation with the use of deep learning techniques. The main challenge is associated with the high diversity of possible cranial defects. The lack of appropriate data sources negatively influences the data-driven nature of deep learning algorithms. Hence, one of the possible solutions to overcome this problem is to rely on synthetic data. In this work, we propose three volumetric variations of deep generative models to augment the dataset by generating synthetic skulls, i.e. Wasserstein Generative Adversarial Network with Gradient Penalty (WGAN-GP), WGAN-GP hybrid with Variational Autoencoder pretraining (VAE/WGAN-GP) and Introspective Variational Autoencoder (IntroVAE). We show that it is possible to generate dozens of thousands of defective skulls with compatible defects that achieve a trade-off between defect heterogeneity and the realistic shape of the skull. We evaluate obtained synthetic data quantitatively by defect segmentation with the use of V-Net and qualitatively by their latent space exploration. We show that the synthetically generated skulls highly improve the segmentation process compared to using only the original unaugmented data. The generated skulls may improve the automatic design of personalized cranial implants for real medical cases.