Generation of Artificial CT Images using Patch-based Conditional Generative Adversarial Networks

TL;DR

This paper introduces a patch-based conditional GAN method for generating high-quality artificial CT images, aiding medical image analysis where data scarcity is a challenge.

Contribution

It proposes a novel GAN architecture using segmentation masks as conditions for improved CT image generation, validated on whole heart CT images.

Findings

Generated images are of high quality and suitable for medical analysis.

The method effectively captures the structure of heart subregions.

Potential to enhance training datasets for medical diagnostics.

Abstract

Deep learning has a great potential to alleviate diagnosis and prognosis for various clinical procedures. However, the lack of a sufficient number of medical images is the most common obstacle in conducting image-based analysis using deep learning. Due to the annotations scarcity, semi-supervised techniques in the automatic medical analysis are getting high attention. Artificial data augmentation and generation techniques such as generative adversarial networks (GANs) may help overcome this obstacle. In this work, we present an image generation approach that uses generative adversarial networks with a conditional discriminator where segmentation masks are used as conditions for image generation. We validate the feasibility of GAN-enhanced medical image generation on whole heart computed tomography (CT) images and its seven substructures, namely: left ventricle, right ventricle, left atrium, right atrium, myocardium, pulmonary arteries, and aorta. Obtained results demonstrate the suitability of the proposed adversarial approach for the accurate generation of high-quality CT images. The presented method shows great potential to facilitate further research in the domain of artificial medical image generation.