Medical Image Fusion Based on Wavelet Transform and Independent Component Analysis

By analyzing the characters of CT medical image, this paper proposes a novel method for this particular image fusion, which is using discrete wavelet transform and independent component analysis. Firstly, each of CT images were decomposed by 2-D discrete wavelet transform. Then independent component analysis were used to analyse the wavelet coefficients in different level for acquiring independent component. At last, we use wavelet reconstruction to synthesize one CT medical image which could contain more integrated accurate detail information of different soft tissue such as muscles and blood vessels. By contrast, the efficiency of our method is better than weighted average, laplacian pyramid method in medical image fusion field.