Generative adversarial networks (GANs) have shown remarkable success in generating realistic images and are increasingly used in medical imaging for image-to-image translation tasks. However, GANs tend to suffer from a frequency bias towards low frequencies, which can lead to the removal of important structures in the generated images. To address this issue, we propose a novel frequency-aware image-to-image translation framework based on the supervised RegGAN approach, which we call fRegGAN. The framework employs a K-space loss to regularize the frequency content of the generated images and incorporates well-known properties of MRI K-space geometry to guide the network training process. By combine our method with the RegGAN approach, we can mitigate the effect of training with misaligned data and frequency bias at the same time. We evaluate our method on the public BraTS dataset and outperform the baseline methods in terms of both quantitative and qualitative metrics when synthesizing T2-weighted from T1-weighted MR images. Detailed ablation studies are provided to understand the effect of each modification on the final performance. The proposed method is a step towards improving the performance of image-to-image translation and synthesis in the medical domain and shows promise for other applications in the field of image processing and generation.
翻译:生成对抗网络 (GAN) 在生成逼真图像方面显示出了极大的成功,并且越来越多地在医学成像中用于图像到图像的翻译任务。然而,GAN 往往会受到低频偏差的影响,这可能导致在生成的图像中移除重要的结构。为了解决这个问题,我们提出了一种新的基于监督 RegGAN 方法的频率感知图像到图像翻译框架,称为 fRegGAN。该框架采用 K 空间损失来规范生成图像的频率内容,并结合MRI K 空间几何的公认性质来指导网络训练过程。将我们的方法与 RegGAN 方法相结合,我们可以同时缓解训练误差数据和频率偏差的影响。我们在公共 BraTS 数据集上评估了我们的方法,并在从 T1 加权 MR 图像合成 T2 加权 MR 图像方面,以定量和定性指标方面均优于基线方法。提供了详细的消融研究以了解每个修改对最终性能的影响。所提出的方法是改进医学领域图像到图像翻译和合成性能的一步,并对图像处理和生成领域的其他应用具有潜力。