MS-Net: Multi-Site Network for Improving Prostate Segmentation With Heterogeneous MRI Data
MS-Net: Multi-Site Network for Improving Prostate Segmentation With Heterogeneous MRI Data
复制标题
MS-Net：利用异构 MRI 数据改善前列腺分割的多站点网络
DOI：
10.1109/tmi.2020.2974574
复制
发表时间：
2020-09-01
影响因子：
10.6
通讯作者：
Heng, Pheng Ann
中科院分区：
文献类型：
--
作者：
Liu, Quande;Dou, Qi;Heng, Pheng Ann
磁共振成像中的前列腺自动分割是计算机辅助诊断的迫切需求。最近，各种深度学习方法在这项任务中取得了显著进展，通常依赖于大量的训练数据。由于医学图像的稀缺性，重要的是有效地聚合来自多个站点的数据以进行鲁棒的模型训练，以缓解单站点样本的不足。然而，由于扫描仪和成像协议的差异，来自不同站点的前列腺MRI呈现异质性，这对聚合多站点数据用于网络训练的有效方法提出了挑战。在本文中，我们提出了一种新的多站点网络（MS-Net），通过学习鲁棒的表示，利用多个数据源来改善前列腺分割。为了补偿不同MRI数据集的站点间异质性，我们在网络骨干中开发了特定于域的批量归一化层，使网络能够分别估计统计数据并为每个站点执行特征归一化。考虑到从多个数据集中获取共享知识的困难，提出了一种新的学习范式，即，多站点引导的知识转移，提出了增强核提取更多的通用表示从多站点数据。在三个异构前列腺MRI数据集上进行的大量实验表明，我们的MS-Net在所有数据集上的性能都得到了一致的提高，并且在多站点学习方面优于最先进的方法。
Automated prostate segmentation in MRI is highly demanded for computer-assisted diagnosis. Recently, a variety of deep learning methods have achieved remarkable progress in this task, usually relying on large amounts of training data. Due to the nature of scarcity for medical images, it is important to effectively aggregate data from multiple sites for robust model training, to alleviate the insufficiency of single-site samples. However, the prostate MRIs from different sites present heterogeneity due to the differences in scanners and imaging protocols, raising challenges for effective ways of aggregating multi-site data for network training. In this paper, we propose a novel multi-site network (MS-Net) for improving prostate segmentation by learning robust representations, leveraging multiple sources of data. To compensate for the inter-site heterogeneity of different MRI datasets, we develop Domain-Specific Batch Normalization layers in the network backbone, enabling the network to estimate statistics and perform feature normalization for each site separately. Considering the difficulty of capturing the shared knowledge from multiple datasets, a novel learning paradigm, i.e., Multi-site-guided Knowledge Transfer, is proposed to enhance the kernels to extract more generic representations from multi-site data. Extensive experiments on three heterogeneous prostate MRI datasets demonstrate that our MS-Net improves the performance across all datasets consistently, and outperforms state-of-the-art methods for multi-site learning.