Multispectral medical image fusion in Contourlet domain for computer based diagnosis of Alzheimer’s disease

Abstract

Computer based diagnosis of Alzheimer's disease can be performed by dint of the analysis of the functional and structural changes in the brain. Multispectral image fusion deliberates upon fusion of the complementary information while discarding the surplus information to achieve a solitary image which encloses both spatial and spectral details. This paper presents a Non-Sub-sampled Contourlet Transform (NSCT) based multispectral image fusion model for computer-aided diagnosis of Alzheimer's disease. The proposed fusion methodology involves color transformation of the input multispectral image. The multispectral image in YIQ color space is decomposed using NSCT followed by dimensionality reduction using modified Principal Component Analysis algorithm on the low frequency coefficients. Further, the high frequency coefficients are enhanced using non-linear enhancement function. Two different fusion rules are then applied to the low-pass and high-pass sub-bands: Phase congruency is applied to low frequency coefficients and a combination of directive contrast and normalized Shannon entropy is applied to high frequency coefficients. The superiority of the fusion response is depicted by the comparisons made with the other state-of-the-art fusion approaches (in terms of various fusion metrics).

Multispectral Medical Image Fusion for Alzheimer Disease Using Adaptive Blood Flow Weight Based Fusion Rule

“…The quality of fused images are analyzed using the proposed method for various performance measures and the values are summarized in Table 1 Table 2. Vikrant et al [14] has implemented a Non Sub-sampled Contourlet Transform (NSCT) based fusion method and compared their result with the various fusion methods such as Wavelet, Curvelet and Contourlet. It has been proved that NSCT method provided the better fusion result.…”

“…It is very difficult to restrict the disparaging process of disease. Even though the Alzheimer disease is not curable, if it is diagnosed in the early stage, the spreading of the disease can be slow down [14]. Hence, computer aided diagnosis is required with good fusion method.…”

“…However, the drawback is the guided image filter cannot represent the some edges of the image well and the weight map construction method also not represented the visual features in source images. Vikrant et al [14] proposed a multimodal medical image fusion based on directive contrast in NSCT domain. Phase congruency method is used to fuse low frequency coefficients whereas directive contrast method is used for fusing high frequency coefficients of source images.…”

Medical Image Fusion Based on Fast Finite Shearlet Transform and Sparse Representation

“…With the development of imaging devices, different sensors can acquire different information from images of the same scenario [1–4]. In medicine, images of different modes are properly fused to make the source images complementary to each other and thus obtain more informative images [5, 6].…”

Untitled

“…Source images could possess a variety of nature such as multimodal, multisensory, and multifocal. [7,8] Image fusion is an important field of application in military surveillance, remote sensing, satellite communication biometrics, and medical image diagnosis or radiology. A plethora of image fusion [9,10] experiments are being conducted on computed tomography (CT) to diagnose a tumor in legs, positron emission tomography and single photon emission computed tomography to monitor blood clotting in different parts of the body.…”