Multi‐sensor medical image fusion using pyramid‐based DWT: a multi‐resolution approach

Abstract

Generally, image fusions are carried out on two‐dimensional (2D) images, but the operations with the 2D images increase the computational complexity than vector data. This study presents an algorithm with Laplacian pyramid built on 1D discrete wavelet transform (DWT) called modified multi‐resolution DWT (MMDWT) for multi‐sensor medical image fusion which was found to be efficient for n ‐level decomposition and can work with all mother wavelets with less computational complexity. The MMDWT methodology is compared with the discrete cosine transform, DWT, stationary WT, curvelet transform, principal component analysis, fuzzy and neurofuzzy technique and the performance measure is analysed. The performance evaluation of the MMDWT technique is illustrated using several sets of medical images provided by Health Care Global Enterprises Ltd. (HCG) Hospital Bangalore, based on the subjective and objective analyses. The result is validated by radiologists from HCG for subjective evaluation. The outcome of the MMDWT methodology is analysed with existing fusion algorithms and reveals the supremacy of the final fusion results.