An improved medical image registration method based on the sum of conditional variance
XIANG Yan
GUI Peng
WANG Shuo
XU Chunrong
SHAO Dangguo
LIU Lijun
TANG Shouguo
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.
Keywords：Image registrationSum of conditional variancePV interpolatorNormalized mutual informationCross cumulative residual entropy
Publication Date：2018-01-01
Online Publishing Date：2026-09-11(First online date of this platform, not the publication date of the document)
Pages：6( 71-76 )