Unsupervised Learning for Cross-Domain Medical Image Synthesis Using Deformation Invariant Cycle Consistency Networks

• Published in: Simulation and Synthesis in Medical Imaging Vol. 11037; pp. 52 - 60
• Main Authors: Wang, Chengjia, Macnaught, Gillian, Papanastasiou, Giorgos, MacGillivray, Tom, Newby, David
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 01.01.2018; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: Deep learning; GAN; Synthesis; Unsupervised learning
• ISBN: 3030005356; 9783030005351
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-00536-8_6

Recently, the cycle-consistent generative adversarial networks (CycleGAN) has been widely used for synthesis of multi-domain medical images. The domain-specific nonlinear deformations captured by CycleGAN make the synthesized images difficult to be used for some applications, for example, generating pseudo-CT for PET-MR attenuation correction. This paper presents a deformation-invariant CycleGAN (DicycleGAN) method using deformable convolutional layers and new cycle-consistency losses. Its robustness dealing with data that suffer from domain-specific nonlinear deformations has been evaluated through comparison experiments performed on a multi-sequence brain MR dataset and a multi-modality abdominal dataset. Our method has displayed its ability to generate synthesized data that is aligned with the source while maintaining a proper quality of signal compared to CycleGAN-generated data. The proposed model also obtained comparable performance with CycleGAN when data from the source and target domains are alignable through simple affine transformations.