论文标题

MS-NET:用于通过异质MRI数据改善前列腺分割的多站点网络

MS-Net: Multi-Site Network for Improving Prostate Segmentation with Heterogeneous MRI Data

论文作者

Liu, Quande, Dou, Qi, Yu, Lequan, Heng, Pheng Ann

论文摘要

高度要求在MRI中进行自动前列腺分段以进行计算机辅助诊断。最近,通常依靠大量的培训数据,各种深度学习方法在这项任务中取得了显着进步。由于医学图像的稀缺性质,重要的是要有效地从多个站点汇总数据以进行健壮的模型训练,以减轻单位点样品的不足。但是,由于扫描仪和成像协议的差异,来自不同站点的前列腺MRI出现异质性,从而为有效的方式汇总了多站点数据以进行网络培训的有效方法。在本文中,我们提出了一个新型的多站点网络(MS-NET),用于通过学习稳健表示,利用多个数据源来改善前列腺分割。为了补偿不同MRI数据集的现场异质性,我们在网络骨干网中开发了特定于域的批准层,从而使网络能够估算每个站点的统计信息并对每个站点进行特征归一化。考虑到从多个数据集中捕获共享知识的困难,提出了一种新颖的学习范式,即多站点指导的知识转移,以增强内核以从多站点数据中提取更多通用表示。对三个异质前列腺MRI数据集进行的广泛实验表明,我们的MS-NET始终提高所有数据集的性能,并且优于多站点学习的最先进方法。

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.

扫码加入交流群

加入微信交流群

微信交流群二维码

扫码加入学术交流群,获取更多资源