Multi-Modality Generative Adversarial Networks with Tumor Consistency Loss for Brain MR Image Synthesis
This work addresses a domain-specific challenge in medical imaging by enabling more efficient synthesis of brain MR images, though it is incremental as it builds on existing GAN frameworks.
The paper tackles the problem of synthesizing multiple missing MR image modalities from a single input to reduce clinical costs, achieving better image quality than baseline methods and improving tumor segmentation accuracy.
Magnetic Resonance (MR) images of different modalities can provide complementary information for clinical diagnosis, but whole modalities are often costly to access. Most existing methods only focus on synthesizing missing images between two modalities, which limits their robustness and efficiency when multiple modalities are missing. To address this problem, we propose a multi-modality generative adversarial network (MGAN) to synthesize three high-quality MR modalities (FLAIR, T1 and T1ce) from one MR modality T2 simultaneously. The experimental results show that the quality of the synthesized images by our proposed methods is better than the one synthesized by the baseline model, pix2pix. Besides, for MR brain image synthesis, it is important to preserve the critical tumor information in the generated modalities, so we further introduce a multi-modality tumor consistency loss to MGAN, called TC-MGAN. We use the synthesized modalities by TC-MGAN to boost the tumor segmentation accuracy, and the results demonstrate its effectiveness.