Unpaired Brain MR-to-CT Synthesis Using a Structure-Constrained CycleGAN

• Published in: Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support Vol. 11045; pp. 174 - 182
• Main Authors: Yang, Heran, Sun, Jian, Carass, Aaron, Zhao, Can, Lee, Junghoon, Xu, Zongben, Prince, Jerry
• Format: Book Chapter
• Language: English
• Published: Switzerland Springer International Publishing AG 2018; Springer International Publishing
• Series: Lecture Notes in Computer Science
• Subjects: CycleGAN; Deep learning; MIND; MR-to-CT synthesis
• ISBN: 3030008886; 9783030008888
• ISSN: 0302-9743; 1611-3349
• DOI: 10.1007/978-3-030-00889-5_20

The cycleGAN is becoming an influential method in medical image synthesis. However, due to a lack of direct constraints between input and synthetic images, the cycleGAN cannot guarantee structural consistency between these two images, and such consistency is of extreme importance in medical imaging. To overcome this, we propose a structure-constrained cycleGAN for brain MR-to-CT synthesis using unpaired data that defines an extra structure-consistency loss based on the modality independent neighborhood descriptor to constrain structural consistency. Additionally, we use a position-based selection strategy for selecting training images instead of a completely random selection scheme. Experimental results on synthesizing CT images from brain MR images demonstrate that our method is better than the conventional cycleGAN and approximates the cycleGAN trained with paired data.