A hybrid approach for Medical Image Fusion Based on Wavelet Transform and Principal Component Analysis

This paper presents a hybrid approach for medical image fusion based on the Discrete Wavelet Transform (DWT) and Principal Component Analysis (PCA). The main idea of the approach is to select between two fusion methods; DWT and PCA based on the local variance estimated at each position in the fusion results. Simulation results on multi-modality images are presented in this paper. The two modalities adopted are Magnetic Resonance (MR) images and Computed Tomography (CT) images. Evaluation metrics such as entropy, edge intensity, contrast, and average gradient have been adopted for performance evaluation of the proposed method. The obtained results confirm that the proposed method is superior in performance to the DWT and PCA methods individually.