English

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

Image and Video Processing 2021-04-07 v1 Computer Vision and Pattern Recognition Machine Learning

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.

Keywords

Cite

@article{arxiv.2104.02060,
  title  = {Toward Generating Synthetic CT Volumes using a 3D-Conditional Generative Adversarial Network},
  author = {Jayalakshmi Mangalagiri and David Chapman and Aryya Gangopadhyay and Yaacov Yesha and Joshua Galita and Sumeet Menon and Yelena Yesha and Babak Saboury and Michael Morris and Phuong Nguyen},
  journal= {arXiv preprint arXiv:2104.02060},
  year   = {2021}
}

Comments

It is a short paper accepted in CSCI 2020 conference and is accepted to publication in the IEEE CPS proceedings

R2 v1 2026-06-24T00:51:49.269Z