CAJ | 학술논문

目的：通过图像融合方法结合解剖和功能医学图像以提供更多有用的信息并辅助医生诊断。方法利用稀疏表示能很好地反映图像特征的优势。首先，选取医院脑梗死和脑出血的CT和MRI的临床图像，采用双稀疏字典算法得到稀疏字典，再通过结合空间域信息的最大选择法作为融合规则对其进行融合，并与基于主成分分析（ principal component analysis ， PCA）和离散小波变换（ discrete wavelet transform， DWT）方法的图像融合结果在主观方面以及客观方面的QAB／F和Piella指标上进行比较。结果本文提出的方法所获得的融合图像主观评价优于另外两种方法。 QAB／F和Piella的均值分别为0．9139和0．7213，客观评价指标也优于另外两种方法。结论基于双稀疏字典的图像融合算法得到的融合图像更清晰，对比度更高，并且特征保留效果更好，有助于医生的诊断。
목적：통과도상융합방법결합해부화공능의학도상이제공경다유용적신식병보조의생진단。방법이용희소표시능흔호지반영도상특정적우세。수선，선취의원뇌경사화뇌출혈적CT화MRI적림상도상，채용쌍희소자전산법득도희소자전，재통과결합공간역신식적최대선택법작위융합규칙대기진행융합，병여기우주성분분석（ principal component analysis ， PCA）화리산소파변환（ discrete wavelet transform， DWT）방법적도상융합결과재주관방면이급객관방면적QAB／F화Piella지표상진행비교。결과본문제출적방법소획득적융합도상주관평개우우령외량충방법。 QAB／F화Piella적균치분별위0．9139화0．7213，객관평개지표야우우령외량충방법。결론기우쌍희소자전적도상융합산법득도적융합도상경청석，대비도경고，병차특정보류효과경호，유조우의생적진단。
Objective We use the method of image fusion combining anatomical and functional medical images to provide more useful information and to help the doctors in diagnosis .Methods Sparse representation can reflect the advantage of the image feature well .First, the CT and MRI images of cerebral infarction and cerebral hemorrhage from the hospital are selected , and the algorithm based on double sparse dictionary is used to obtain the sparse dictionary .Then the method of max selection with information of spatial domain as the fusion rule fuses the selected clinical images .Finally, the results of the proposed method are compared with the results of PCA method and DWT method in the subjective aspect and the objective aspect on the indices of QAB/F and Piella.Results Subjective evaluations of the fusion images obtained from the proposed method are better than the other two methods , and the mean values of QAB/F and Piella in the objective aspect are 0.9139 and 0.7213, which are superior to the other two methods .Conclusions The fusion images obtained from the proposed method based on sparse dictionary are clearer , with higher contrast , and have more features of source images , which is helpful in diagnosis .