DC-cycleGAN: Bidirectional CT-to-MR Synthesis from Unpaired Data

TL;DR

This paper introduces DC-cycleGAN, a bidirectional model for unpaired CT and MR image synthesis that uses dual contrast loss and structural metrics to improve image quality, outperforming existing methods.

Contribution

The paper proposes a novel dual contrast cycleGAN model with a dual contrast loss and structural considerations for improved unpaired medical image synthesis.

Findings

DC-cycleGAN produces promising synthesis results.

Outperforms other cycleGAN-based methods.

Effective in unpaired CT-MR image translation.

Abstract

Magnetic resonance (MR) and computer tomography (CT) images are two typical types of medical images that provide mutually-complementary information for accurate clinical diagnosis and treatment. However, obtaining both images may be limited due to some considerations such as cost, radiation dose and modality missing. Recently, medical image synthesis has aroused gaining research interest to cope with this limitation. In this paper, we propose a bidirectional learning model, denoted as dual contrast cycleGAN (DC-cycleGAN), to synthesize medical images from unpaired data. Specifically, a dual contrast loss is introduced into the discriminators to indirectly build constraints between real source and synthetic images by taking advantage of samples from the source domain as negative samples and enforce the synthetic images to fall far away from the source domain. In addition, cross-entropy and structural similarity index (SSIM) are integrated into the DC-cycleGAN in order to consider both the luminance and structure of samples when synthesizing images. The experimental results indicate that DC-cycleGAN is able to produce promising results as compared with other cycleGAN-based medical image synthesis methods such as cycleGAN, RegGAN, DualGAN, and NiceGAN. The code will be available at https://github.com/JiayuanWang-JW/DC-cycleGAN.