Bidirectional cross-modality unsupervised domain adaptation using generative adversarial networks for cardiac image segmentation
Bidirectional cross-modality unsupervised domain adaptation using generative adversarial networks for cardiac image segmentation
复制标题
使用生成对抗网络进行心脏图像分割的双向跨模态无监督域适应
DOI：
10.1016/j.compbiomed.2021.104726
复制
发表时间：
2021-08-06
影响因子：
7.7
通讯作者：
Zhang, Yanning
中科院分区：
文献类型：
--
作者：
Cui, Hengfei;Chang Yuwen;Zhang, Yanning
背景资料：针对心脏图像分割问题，提出了一种基于生成对抗网络（GAN）的双向跨模态无监督域自适应（GBCUDA）框架，该框架能够有效地解决网络在适应目标域时分割性能下降的问题。方法：GBCUDA使用GAN进行图像对齐，应用对抗学习提取图像特征，并逐步增强提取特征的域不变性。共享编码器执行端到端学习任务，其中两个域之间的不同特征相互补充。自注意机制被纳入GAN网络，它可以根据所有特征位置的提示生成细节。此外，频谱归一化实现稳定的训练GAN，并引入知识蒸馏损失处理高级特征图，以更好地完成跨模式分割任务。结果如下：我们提出的无监督域自适应框架的有效性在多模态全心脏分割（MM-WHS）挑战2017数据集上进行了测试。所提出的方法是能够提高平均Dice从74.1%到81.5%的四个心脏子结构，并减少平均对称表面距离（ASD）从7.0到5.8在CT图像。对于MRI图像，我们提出的在CT图像上训练的框架给出了59.2%的平均Dice，并将平均ASD从5.7降低到4.9。结论：评估结果表明，我们的方法的有效性领域适应和优越性，目前国家的最先进的领域适应方法。
Background: A novel Generative Adversarial Networks (GAN) based bidirectional cross-modality unsupervised domain adaptation (GBCUDA) framework is developed for cardiac image segmentation, which can effectively tackle the problem of network's segmentation performance degradation when adapting to the target domain without ground truth labels. Method: GBCUDA uses GAN for image alignment, applies adversarial learning to extract image features, and gradually enhances the domain invariance of extracted features. The shared encoder performs an end-to-end learning task in which features that differ between the two domains complement each other. The selfattention mechanism is incorporated to the GAN network, which can generate details based on the prompts of all feature positions. Furthermore, spectrum normalization is implemented to stabilize the training of GAN, and knowledge distillation loss is introduced to process high-level feature-maps in order to better complete the crossmode segmentation task. Results: The effectiveness of our proposed unsupervised domain adaptation framework is tested over the MultiModality Whole Heart Segmentation (MM-WHS) Challenge 2017 dataset. The proposed method is able to improve the average Dice from 74.1% to 81.5% for the four cardiac substructures, and reduce the average symmetric surface distance (ASD) from 7.0 to 5.8 over CT images. For MRI images, our proposed framework trained on CT images gives the average Dice of 59.2% and reduces the average ASD from 5.7 to 4.9. Conclusions: The evaluation results demonstrate our method's effectiveness on domain adaptation and the superiority to the current state-of-the-art domain adaptation methods.