Toward Generating Synthetic CT Volumes using a 3D-Conditional Generative Adversarial Network
This addresses the challenge of creating realistic medical imaging data for applications like training or augmentation, though it is incremental as it builds on existing GAN methods with specific adaptations for 3D CT data.
The paper tackles the problem of generating synthetic 3D CT volumes from noisy or pixelated inputs using a novel conditional GAN architecture, achieving PSNR values from 12.53 to 46.46 dB and SSIM from 0.89 to 1 on COVID-19 CT datasets.
We present a novel conditional Generative Adversarial Network (cGAN) architecture that is capable of generating 3D Computed Tomography scans in voxels from noisy and/or pixelated approximations and with the potential to generate full synthetic 3D scan volumes. We believe conditional cGAN to be a tractable approach to generate 3D CT volumes, even though the problem of generating full resolution deep fakes is presently impractical due to GPU memory limitations. We present results for autoencoder, denoising, and depixelating tasks which are trained and tested on two novel COVID19 CT datasets. Our evaluation metrics, Peak Signal to Noise ratio (PSNR) range from 12.53 - 46.46 dB, and the Structural Similarity index ( SSIM) range from 0.89 to 1.