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

Abstract

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.

arXiv comment8 pages, 5 figures, accepted by MICCAI 2018 Workshop: Deep Learning in Medical Image Analysis (DLMIA)

References in corpus (1)

• Translating and Segmenting Multimodal Medical Volumes with Cycle- and Shape-Consistency Generative Adversarial Network

Cited by in corpus (5)

• Generative Adversarial Network in Medical Imaging: A Review
• ResViT: Residual vision transformers for multi-modal medical image synthesis
• Which Contrast Does Matter? Towards a Deep Understanding of MR Contrast using Collaborative GAN
• Structurally aware bidirectional unpaired image to image translation between CT and MR
• Exploring constraints on CycleGAN-based CBCT enhancement for adaptive radiotherapy