A Novel Approach for Fusion of Multimodality Medical Images

Multi modal medical image fusion has a great contribution in the field of medical imaging and has proved helpful in the field of clinical diagnosis. In this paper, a novel discrete wavelet transform (DWT) based approach for fusion of multi modal medical images is presented which is developed by taking into account the characteristics of Human Visual System (HVS) and also the physical meaning of the wavelet coefficients. Besides this some existing well-known image fusion methods are discussed. Image fusion aims to generate a new image by combining two or more images in order to produce a more informative and clear fused image. The image fusion can be performed using pixel or region based methods. The images are first decomposed and then different fusion rules are applied on the low frequency and high frequency bands depending upon the requirement of the fusion to be done. After the fused coefficients have been obtained the inverse discrete wavelet transform (IDWT) is applied to obtain the fused image.