An overlap invariant entropy measure of 3D medical image alignment
An overlap invariant entropy measure of 3D medical image alignment
复制标题
DOI：
10.1016/s0031-3203(98)00091-0
复制
发表时间：
1999-01-01
影响因子：
8
通讯作者：
Hawkes, DJ
中科院分区：
文献类型：
--
作者：
Studholme, C;Hill, DLG;Hawkes, DJ
本文关注的是基于熵的自动3D多模态医学图像配准标准的发展。在这种应用中，未对准相对于成像视场可能较大，重叠统计的不变性是重要的考虑因素。目前熵的措施进行审查，并提出了一个规范化的措施，这是简单的边际熵和联合熵的总和之比。使用一个简单的图像模型和实验的临床图像数据的变化重叠对当前的熵的措施和这种归一化的措施进行比较。结果表明，归一化熵测量提供了显着改善的行为在一定范围内的成像领域的看法。(C)1999年模式识别学会。由爱思唯尔科技有限公司出版。保留所有权利。
This paper is concerned with the development of entropy-based registration criteria for automated 3D multi-modality medical image alignment. In this application where misalignment can be large with respect to the imaged field of view, invariance to overlap statistics is an important consideration. Current entropy measures are reviewed and a normalised measure is proposed which is simply the ratio of the sum of the marginal entropies and the joint entropy. The effect of changing overlap on current entropy measures and this normalised measure are compared using a simple image model and experiments on clinical image data. Results indicate that the normalised entropy measure provides significantly improved behaviour over a range of imaged fields of view. (C) 1999 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.