Multimodal Medical Image Fusion using Autoassociative Neural Network

S. Patnaik and T. Sahoo (India)


Image Fusion, auto-associative neural network, RLS learning,


In this paper, a principal component extraction based image fusion technique, using auto-associative neural network, has been implemented and analyzed. Fusion of images taken at different resolutions, intensity and by different techniques, helps physicians to extract the features that may not be normally visible in a single image by different modalities. This work aims at fusion of two images containing varied information. Proposed algorithm takes care of registration as well as fusion in a single pass. Attempt has been taken to fuse one MRI-T1 image containing a greater detail about anatomical structure and a corresponding CT image. The fusion strategy decomposes images into multiple levels by using eigen vectors from standard data base for different parts and structures in the body. Analysis of the finer details available at different levels improves the quality of the fused image significantly. The performance and relative importance of the proposed methodology is investigated by calculating signal to noise ratio.

Important Links:

Go Back