Fusion of CT and MR Liver Images Using Multiresolution Analysis Methods

Abstract

There are various medical imaging techniques such as Computed Tomography (CT) and Magnetic Resonance (MR) techniques. Both techniques give complex features of the region to be imaged. This study proposes an approach that uses Multiresolution Analysis (MRA) methods to fuse CT and MR liver images to obtain as detailed images as possible for medical diagnostic purposes. The transform coefficients are obtained by applying MRA methods to the images. Images are combined by applying 3 different fusion rules to these transform coefficients. Peak Signal to Noise Rate (PSNR), Structural Similarity Index Measure (SSIM) and Mean Square Error (MSE) values are calculated to evaluate the fused images. When comparing the methods, the best result was obtained using complex-valued curvelet transform.

Image Fusion and Deep Learning Based Ear Recognition Using Thermal and Visible Images

“…The development of wavelets has made Multiresolution Analysis (MRA) methods very popular. MRA methods, operating at various scales, are frequently employed in image processing applications to capture different features of images (Cihan & Ceylan, 2021). By displaying images at different scales, one can easily detect inconspicuous features at various levels (Morlet et al, 1982).…”

“…It serves as an effective tool in image analysis methods by enabling local analysis through the separation of data into various frequency components. This segmentation allows the examination of large signals in small areas (Cihan & Ceylan, 2021). Figure 1 illustrates the 2D-DWT process involving low-pass and high-pass filter banks.…”