生物医学工程研究2018，Vol.37Issue(1)：71-76,6.DOI:10.19529/j.cnki.1672-6278.2018.01.15
一种改进的条件方差和医学图像配准
An improved medical image registration method based on the sum of conditional variance
摘要
Abstract
Multi-modality medical image registration is the key step for the fusion of image information provided by different med-ical imaging modalities.The sum of conditional variance(SCV)is considered to be a state-of-the-art similarity measure for regis-tering multi-modality images.However,the main drawback of the SCV is that it uses only quantized information to calculate the joint histogram.To overcome this limitation,we proposed a new interpolator function for the joint histogram of SCV to improve the perform-ance.We applied our method to multi-modality medical image registration, comparing with the normalized mutual information (NMI),cross cumulative residual entropy(CCRE),and the original SCV.The results show that the proposed method can register im-ages with different geometric transformation or strong noises.Compared with NMI,CCRE and SCV,the proposed method has improved the success rate and robustness.关键词
图像配准/条件方差和/PV插值/归一化互信息/交叉累积剩余熵Key words
Image registration/Sum of conditional variance/PV interpolator/Normalized mutual information/Cross cumulative residual entropy分类
医药卫生引用本文复制引用
相艳,桂鹏,王硕,许春荣,邵党国,刘利军,汤守国..一种改进的条件方差和医学图像配准[J].生物医学工程研究,2018,37(1):71-76,6.基金项目
国家自然科学基金资助项目(81560296) （81560296）
云南省教育厅科学研究基金资助项目(2015Y070). （2015Y070）
