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.
翻译:磁共振(MR)和计算机透析(CT)图像是两种典型的医疗图像,它们为准确的临床诊断和治疗提供了相互补充的信息。然而,由于成本、辐射剂量和模式缺失等一些考虑,获取这两种图像可能受到限制。最近,医学图像合成引起了研究兴趣,以应对这一限制。在本文中,我们提出了一个双向学习模式,称为双向对比循环GAN(DC-cycopleGAN),以综合来自未受重视数据的医学图像。具体来说,在歧视者身上引入双重对比损失,通过利用源域样本作为负面样本,使合成图像远离源域,从而间接造成真实来源和合成图像之间的限制。此外,跨热带和结构相似指数(SSIM)被纳入了DC-cycourGAN(DC-cycleGANAANAANAANAAN),在BYCAGAGANANSANDGANDGAGANSAREGANANSANSLAGANANDGANAGANANANANANAGYGANANANANSLOLAGANGANGANGANANGANGANAGANAGANANDGYGYGANANDRAANANSLANSANANDGYGYGANAGAN ASANANDGYGANDGANANSLANDANDANSLANSLAGAGAGAGANSLANSLANSLANSLANSLANSLANSLANSLGNAGNAGAN SAGAN ASG ASGNAGNSLANSLANS NAGAN SAGNSLANSLANSLANSLANSLANSLANS SANSLANSLGYGYGYGYGYGYG SA SA SA SA SA SA SAG SAGANDANDANS SAG SAG SAG SAG SAG SAG SA SA SAG SAG SAG SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SA SAG