An Efficient PET-MRI Medical Image Fusion based on IHS-NSCT-PCA Integrated Method
Padmavathi K1, Maya V Karki2

1Padmavathi K.*, Department of EC, NMAM Institute of Technology, Nitte, Karnataka, Udupi, India.
2Maya V Karki, Department. of EC, Ramaiah Institute of Technology, Bengaluru, Karnataka, India.
Manuscript received on November 22, 2019. | Revised Manuscript received on December 15, 2019. | Manuscript published on December 30, 2019. | PP: 2073-2079 | Volume-9 Issue-2, December, 2019. | Retrieval Number:  B3365129219/2019©BEIESP | DOI: 10.35940/ijeat.B3365.129219
Open Access | Ethics and Policies | Cite | Mendeley
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC BY-NC-ND license (

Abstract: Merging of multiple imaging modalities leads to a single image that acquire high information content. These find useful applications in disease diagnosis and treatment planning. IHS-PCA method is a spatial domain approach for fusion that offersfinestvisibility but demands vast memory and it lacks steering information. We propose an integrated approach that incorporates NSCT combined with PCA utilizing IHS space and histogram matching. The fusion algorithm is applied on MRI with PET image and improved functional property was obtained. The IHS transform is a sharpening technique that converts multispectral image from RGB channels to Intensity Hue and Saturation independent values. Histogram matching is performed with intensity values of the two input images. Pathological details in images can be emphasized in multi-scale and multi-directions by using PCA withNSCT. Fusion rule applied is weighted averaging andprincipal components are used for dimensionality reduction. Inverse NSCT and Inverse IHS are performed so as to obtain the fused image in new RGB space. Visual and subjective investigation is compared with existing methods which demonstrate that our proposed technique gives high structural data content with high spatial and spectral resolution compared withearlier methods.
Keywords: NSCT,fusion, Histogram, IHS, PCA.