Sample-Adaptive GANs: Linking Global and Local Mappings for Cross-Modality MR Image Synthesis
Sample-Adaptive GANs: Linking Global and Local Mappings for Cross-Modality MR Image Synthesis
复制标题
样本自适应 GAN：链接全局和局部映射以进行跨模态 MR 图像合成
DOI：
10.1109/tmi.2020.2969630
复制
发表时间：
2020-01
影响因子：
10.6
通讯作者：
Pierrick Bourgeat
中科院分区：
文献类型：
--
作者：
Biting Yu;Luping Zhou;Lei Wang;Yinghuan Shi;Jurgen Fripp;Pierrick Bourgeat
生成对抗网络（GAN）已被广泛用于跨模态医学图像合成。现有的GAN模型通常逆向学习从源模态到目标模态的全局样本空间映射，然后不加区别地将该映射应用于整个空间中的所有样本进行预测。然而，由于与医学图像合成的复杂性质相反的训练样本的稀缺性，学习对所有样本“最优”的单个全局样本空间映射是非常具有挑战性的，如果不是难以处理的话。为了解决这个问题，本文提出了样本自适应GAN模型，它不仅满足源模态和目标模态之间的全局样本空间映射，而且还探索每个给定样本周围的局部空间以提取其唯一特征。具体来说，所提出的样本自适应GAN将整个学习模型分解为两条合作路径。基线路径通过像往常一样拟合所有训练样本以进行全局样本空间映射来学习公共GAN模型。新的样本自适应路径还通过学习每个样本与其相邻训练样本的关系并使用这些训练样本的目标模态特征作为合成的辅助信息来对每个样本进行建模。通过这种样本自适应路径的增强，所提出的样本自适应GAN能够灵活地调整自己以适应不同的样本，从而优化合成性能。我们的模型已经在来自两个公共数据集的三个跨模态MR图像合成任务上进行了验证，并且它们的性能明显优于最先进的方法。此外，实验还表明，我们的样本自适应策略可以用来改善各种骨干GAN模型。它补充了现有的GAN模型，并可以在需要时随时集成。
Generative adversarial network (GAN) has been widely explored for cross-modality medical image synthesis. The existing GAN models usually adversarially learn a global sample space mapping from the source-modality to the target-modality and then indiscriminately apply this mapping to all samples in the whole space for prediction. However, due to the scarcity of training samples in contrast to the complicated nature of medical image synthesis, learning a single global sample space mapping that is “optimal” to all samples is very challenging, if not intractable. To address this issue, this paper proposes sample-adaptive GAN models, which not only cater for the global sample space mapping between the source- and the target-modalities but also explore the local space around each given sample to extract its unique characteristic. Specifically, the proposed sample-adaptive GANs decompose the entire learning model into two cooperative paths. The baseline path learns a common GAN model by fitting all the training samples as usual for the global sample space mapping. The new sample-adaptive path additionally models each sample by learning its relationship with its neighboring training samples and using the target-modality features of these training samples as auxiliary information for synthesis. Enhanced by this sample-adaptive path, the proposed sample-adaptive GANs are able to flexibly adjust themselves to different samples, and therefore optimize the synthesis performance. Our models have been verified on three cross-modality MR image synthesis tasks from two public datasets, and they significantly outperform the state-of-the-art methods in comparison. Moreover, the experiment also indicates that our sample-adaptive strategy could be utilized to improve various backbone GAN models. It complements the existing GANs models and can be readily integrated when needed.
登录
查看更多内容
DOI：
10.1109/tip.2014.2387019
发表时间：
2015-02
期刊：
IEEE transactions on image processing : a publication of the IEEE Signal Processing Society
影响因子：
--
作者：
Woo J;Stone M;Prince JL
通讯作者：
Prince JL
影响因子：
10.9
作者：
Jog, Amod;Carass, Aaron;Roy, Snehashis;Pham, Dzung L.;Prince, Jerry L.
通讯作者：
Prince, Jerry L.
影响因子：
0.2
作者：
Comendant Ion
通讯作者：
Comendant Ion
Ea-GAN：用于跨模态 MR 图像合成的边缘感知生成对抗网络
影响因子：
10.6
作者：
Yu, Biting;Zhou, Luping;Bourgeat, Pierrick
通讯作者：
Bourgeat, Pierrick
影响因子：
10.6
作者：
Huynh T;Gao Y;Kang J;Wang L;Zhang P;Lian J;Shen D;Alzheimer's Disease Neuroimaging Initiative
通讯作者：
Alzheimer's Disease Neuroimaging Initiative