SlabGAN: a method for generating efficient 3D anisotropic medical volumes using generative adversarial networks

Jason L. Granstedt; Varun A. Kelkar; Weimin Zhou; Mark A. Anastasio

doi:10.1117/12.2581380

15 February 2021 SlabGAN: a method for generating efficient 3D anisotropic medical volumes using generative adversarial networks

Jason L. Granstedt, Varun A. Kelkar, Weimin Zhou, Mark A. Anastasio

Author Affiliations +

Proceedings Volume 11596, Medical Imaging 2021: Image Processing; 1159617 (2021) https://doi.org/10.1117/12.2581380
Event: SPIE Medical Imaging, 2021, Online Only

Abstract

Generative adversarial networks (GANs) have proven useful for several medical imaging tasks, including image reconstruction and stochastic object model generation. Thus far, most of the work with GANs has been constrained to twodimensional images. Considering that medical imaging data are often inherently three-dimensional (3D), a 3D GAN would be a more principled way to synthesize realistic volumes. Training a 3D GAN is both computationally and memory intensive. However, prior work has not considered the anisotropic nature of many medical imaging systems. In this paper, the SlabGAN is proposed to reduce the inefficiencies associated with training a 3D GAN. The SlabGAN uses the progressive GAN architecture extended to 3D, but removes the requirement of the three dimensions being equal sizes. This permits the generation of anisotropic 3D volumes with large x and y dimensions. The SlabGAN is trained on MRI brain images from the fastMRI dataset to generate images of dimension 256×256×16. The x and y dimensions of these images are comparable to previously published results while requiring significantly fewer computational resources to generate. The trained SlabGAN is applicable to tasks such as 3D medical image reconstruction and thin-slice MR super resolution.

Conference Presentation

Citation Download Citation

Jason L. Granstedt, Varun A. Kelkar, Weimin Zhou, and Mark A. Anastasio "SlabGAN: a method for generating efficient 3D anisotropic medical volumes using generative adversarial networks", Proc. SPIE 11596, Medical Imaging 2021: Image Processing, 1159617 (15 February 2021); https://doi.org/10.1117/12.2581380

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available