arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1802.04692cs.CV
收藏

BIRNet:使用双监督全卷积网络的脑图像配准

BIRNet: Brain Image Registration Using Dual-Supervised Fully Convolutional Networks

University of North Carolina at Chapel Hill(北卡罗来纳大学教堂山分校);Northwestern Polytechnical University(西北工业大学);Korea University(高丽大学)

Jingfan Fan, Xiaohuan Cao, Pew-Thian Yap, Dinggang Shen

摘要:

在本文中,我们提出了一种通过预测图像外观变形来进行图像配准的深度学习方法。由于获得用于训练的地面真实变形场可能具有挑战性,因此我们设计了一个受双重指导的完全卷积网络:(1)使用现有配准方法获得的变形场进行粗指导;(2)使用图像相似性进行细指导。后一种指导有助于避免过度依赖训练变形场的监督,这可能是不准确的。为了进行有效的训练,我们进一步改进了深度卷积网络,包括间隙填充、分层丢失和多源策略。在多种数据集上的实验表明,与现有方法相比,该方法具有良好的配准精度和效率。

英文摘要:

In this paper, we propose a deep learning approach for image registration by predicting deformation from image appearance. Since obtaining ground-truth deformation fields for training can be challenging, we design a fully convolutional network that is subject to dual-guidance: (1) Coarse guidance using deformation fields obtained by an existing registration method; and (2) Fine guidance using image similarity. The latter guidance helps avoid overly relying on the supervision from the training deformation fields, which could be inaccurate. For effective training, we further improve the deep convolutional network with gap filling, hierarchical loss, and multi-source strategies. Experiments on a variety of datasets show promising registration accuracy and efficiency compared with state-of-the-art methods.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑