Unpaired Brain MR-to-CT Synthesis using a Structure-Constrained CycleGAN
This work addresses structural accuracy in medical image synthesis for brain imaging, though it is incremental as it builds on existing cycleGAN frameworks.
The paper tackled the problem of structural inconsistency in unpaired brain MR-to-CT synthesis using cycleGAN by introducing a structure-consistency loss and position-based training selection, resulting in improved performance that approximates paired data methods.
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.