Brain stroke lesion segmentation using consistent perception generative adversarial network
Brain stroke lesion segmentation using consistent perception generative adversarial network
复制标题
使用一致感知生成对抗网络进行脑中风病变分割
DOI：
10.1007/s00521-021-06816-8
复制
发表时间：
2022-03-06
影响因子：
6
通讯作者：
Lei, Baiying
中科院分区：
文献类型：
--
作者：
Wang, Shuqiang;Chen, Zhuo;Lei, Baiying
最先进的深度学习方法在分割任务中表现出令人印象深刻的性能。然而，这些方法的成功依赖于大量的人工标记的掩模，这些掩模的收集是昂贵且耗时的。在这项工作中，提出了一种新的一致感知生成对抗网络（CPGAN）用于半监督中风病变分割。所提出的CPGAN可以减少对完全标记样本的依赖。具体而言，相似性连接模块（SCM）的设计，以捕捉多尺度特征的信息。建议的SCM可以选择性地聚合功能在每个位置的加权和。此外，一致的感知策略被引入到所提出的模型，以提高脑卒中病变的预测效果的未标记的数据。此外，一个辅助网络的构建，以鼓励学习有意义的特征表示，往往被遗忘在训练阶段。利用辅助网络和神经网络共同判断分割结果是真实的还是虚假的。根据卒中后病变的解剖学描记（ATLAS）对CPGAN进行评价。实验结果表明，该网络具有上级分割性能。在半监督分割任务中，所提出的CPGAN仅使用五分之二的标记样本，优于使用全标记样本的一些方法。
The state-of-the-art deep learning methods have demonstrated impressive performance in segmentation tasks. However, the success of these methods depends on a large amount of manually labeled masks, which are expensive and time-consuming to be collected. In this work, a novel consistent perception generative adversarial network (CPGAN) is proposed for semi-supervised stroke lesion segmentation. The proposed CPGAN can reduce the reliance on fully labeled samples. Specifically, a similarity connection module (SCM) is designed to capture the information of multi-scale features. The proposed SCM can selectively aggregate the features at each position by a weighted sum. Moreover, a consistent perception strategy is introduced into the proposed model to enhance the effect of brain stroke lesion prediction for the unlabeled data. Furthermore, an assistant network is constructed to encourage the discriminator to learn meaningful feature representations which are often forgotten during training stage. The assistant network and the discriminator are employed to jointly decide whether the segmentation results are real or fake. The CPGAN was evaluated on the Anatomical Tracings of Lesions After Stroke (ATLAS). The experimental results demonstrate that the proposed network achieves superior segmentation performance. In semi-supervised segmentation task, the proposed CPGAN using only two-fifths of labeled samples outperforms some approaches using full labeled samples.