A hybrid fusion of multimodal medical images for the enhancement of visual quality in medical diagnosis

Abstract

In the field of medical imaging, Multimodal Medical Image Fusion (MIF) is a method of extracting complementary information from diverse source images from different modalities such as Magnetic Resonance Imaging, Computed Tomography, Single Photon Emission Computed Tomography, and Positron Emission Tomography and coalescing them into a resultant image. Image fusion of multimodal medical images is the present-day studies in the field of medical imaging, biomedical research, and radiation medicine and is widely familiar by medical and engineering fields. In medical image fusion, single method of fusion is not proficient as it always lags in information while comparing with other available techniques. Hence, fusion for hybrid image is used to perform the image processing by applying multiple fusion rules. The integration of these results was obtained together as a single image. In proposed system, Shearlet Transform (ST) and Principal Component Analysis (PCA) are used to apply integrated fusion. The fusion technique is applied for CT that is Computed Tomography and Magnetic Resonance Imaging (MRI) images, where these images are first transformed using the Shearlet Transform and PCA is applied to the transformed images. Finally, the fusion image is acquired using Inverse Shearlet transform (IST). The proposed system performance is evaluated by using specific metrics, and it is demonstrated that the outcome of proposed integrated fusion performs better when compared to existing fusion techniques.