人工智能
计算机科学
图像配准
深度学习
计算机视觉
模式识别(心理学)
图像(数学)
地标
卷积神经网络
分割
医学影像学
作者
Qiming Fang,Xiao-Meng Gu,Jichao Yan,Jun Zhao,Qiang Li
出处
期刊:Nuclear Science Symposium and Medical Imaging Conference
日期:2019-10-01
被引量:4
标识
DOI:10.1109/nss/mic42101.2019.9059976
摘要
Image registration is a fundamental technique for many automatic medical image analysis tasks, but it can be time-consuming, especially for deformable three-dimensional image registration. In this paper we propose a fast unsupervised learning method for deformable image registration using a fully convolutional network (FCN). The network directly learns to estimate a dense displacement vector field (DVF) from a pair of input images. A spatial transform layer then uses the DVF to warp the moving image to the fixed image. Different from supervised learning based image registration methods, the network is trained by maximization of a similarity metric between the fixed image and the warped moving image. Thus training does not require supervised information such as manually annotated or synthetic ground truth. We evaluate the proposed model on publicly available datasets of inspiration-expiration chest CT image pairs. The results demonstrate that the accuracy of the model is comparable to that of the conventional image registration while executing orders of magnitude faster.
科研通智能强力驱动
Strongly Powered by AbleSci AI