Ea-GANs: Edge-Aware Generative Adversarial Networks for Cross-Modality MR Image Synthesis
Ea-GANs: Edge-Aware Generative Adversarial Networks for Cross-Modality MR Image Synthesis
复制标题
Ea-GAN：用于跨模态 MR 图像合成的边缘感知生成对抗网络
DOI：
10.1109/tmi.2019.2895894
复制
发表时间：
2019-07-01
影响因子：
10.6
通讯作者：
Bourgeat, Pierrick
中科院分区：
文献类型：
--
作者：
Yu, Biting;Zhou, Luping;Bourgeat, Pierrick
磁共振（MR）成像是一种广泛使用的医学成像协议，其可以被配置为提供人体组织之间的不同对比度。通过设置不同的扫描参数，每种MR成像模式都反映了被扫描身体部位的独特视觉特征，有利于后续多角度分析。为了充分利用多个成像模式的互补信息，跨模式MR图像合成近年来引起了越来越多的研究兴趣。然而，大多数现有的方法只关注最小化像素/体素的强度差异，而忽略了图像内容结构的纹理细节，这影响了合成图像的质量。在本文中，我们提出了用于跨模态MR图像合成的边缘感知生成对抗网络（Ea-GANs）。具体来说，我们整合边缘信息，它反映了图像内容的纹理结构，并描绘了图像中不同对象的边界，以减少这种差距。针对不同的学习策略，本文提出了两个框架，发生器诱导的Ea-GAN（gEa-GAN）和鉴别器诱导的Ea-GAN（dEa-GAN）。gEa-GAN通过其生成器合并边缘信息，而dEa-GAN进一步从生成器和边缘检测器两者中这样做，使得边缘相似性也被反向学习。此外，所提出的Ea-GAN是基于3D的，并利用分层特征来捕获上下文信息。实验结果表明，所提出的Ea-GAN，特别是dEa-GAN，在定性和定量测量方面优于多种最先进的跨模态MR图像合成方法。此外，dEa-GAN还显示出对立面，地图和城市景观基准数据集上的通用图像合成任务的良好通用性。
Magnetic resonance (MR) imaging is a widely used medical imaging protocol that can be configured to provide different contrasts between the tissues in human body. By setting different scanning parameters, each MR imaging modality reflects the unique visual characteristic of scanned body part, benefiting the subsequent analysis from multiple perspectives. To utilize the complementary information from multiple imaging modalities, cross-modality MR image synthesis has aroused increasing research interest recently. However, most existing methods only focus on minimizing pixel/voxel-wise intensity difference but ignore the textural details of image content structure, which affects the quality of synthesized images. In this paper, we propose edge-aware generative adversarial networks (Ea-GANs) for cross-modality MR image synthesis. Specifically, we integrate edge information, which reflects the textural structure of image content and depicts the boundaries of different objects in images, to reduce this gap. Corresponding to different learning strategies, two frameworks are proposed, i.e., a generator-induced Ea-GAN (gEa-GAN) and a discriminator-induced Ea-GAN (dEa-GAN). The gEa-GAN incorporates the edge information via its generator, while the dEa-GAN further does this from both the generator and the discriminator so that the edge similarity is also adversarially learned. In addition, the proposed Ea-GANs are 3D-based and utilize hierarchical features to capture contextual information. The experimental results demonstrate that the proposed Ea-GANs, especially the dEa-GAN, outperform multiple state-of-the-art methods for cross-modality MR image synthesis in both qualitative and quantitative measures. Moreover, the dEa-GAN also shows excellent generality to generic image synthesis tasks on benchmark datasets about facades, maps, and cityscapes.