Toward Generating Synthetic CT Volumes using a 3D-Conditional Generative Adversarial Network

TL;DR

This paper introduces a 3D conditional GAN architecture capable of generating synthetic CT volumes from noisy or pixelated inputs, demonstrating promising results on COVID-19 datasets despite current GPU limitations.

Contribution

The paper presents a novel 3D cGAN model for generating full or partial synthetic CT scans, addressing the challenge of 3D medical image synthesis with a new architecture and evaluation on COVID-19 data.

Findings

Achieved PSNR up to 46.46 dB indicating high image quality

SSIM scores up to 1 showing structural similarity to real scans

Demonstrated effectiveness on denoising, depixelating, and autoencoding tasks

Abstract

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.