3D-StyleGAN: A Style-Based Generative Adversarial Network for Generative Modeling of Three-Dimensional Medical Images
This work addresses the need for improved 3D medical image synthesis for real-world applications, though it is incremental as it adapts an existing 2D method to 3D.
The authors tackled the problem of generating three-dimensional medical images by extending StyleGAN2 to 3D, enabling synthesis of volumetric data such as brain MRIs with potential applications in image enhancement and disease modeling.
Image synthesis via Generative Adversarial Networks (GANs) of three-dimensional (3D) medical images has great potential that can be extended to many medical applications, such as, image enhancement and disease progression modeling. However, current GAN technologies for 3D medical image synthesis need to be significantly improved to be readily adapted to real-world medical problems. In this paper, we extend the state-of-the-art StyleGAN2 model, which natively works with two-dimensional images, to enable 3D image synthesis. In addition to the image synthesis, we investigate the controllability and interpretability of the 3D-StyleGAN via style vectors inherited form the original StyleGAN2 that are highly suitable for medical applications: (i) the latent space projection and reconstruction of unseen real images, and (ii) style mixing. We demonstrate the 3D-StyleGAN's performance and feasibility with ~12,000 three-dimensional full brain MR T1 images, although it can be applied to any 3D volumetric images. Furthermore, we explore different configurations of hyperparameters to investigate potential improvement of the image synthesis with larger networks. The codes and pre-trained networks are available online: https://github.com/sh4174/3DStyleGAN.