Title: Hybrid image fusion of multimodality medical images for clinical diagnosis

Authors: Jyoti Agarwal; Sarabjeet Singh Bedi

Addresses: Department of Computer Science, RIMT, Bareilly, India ' Department of Computer Science, MJP Rohilkhand University, Bareilly, India

Abstract: In this paper, hybrid image fusion technique is implemented to improve the image content by fusing images taken from imaging tools. The computed tomography and magnetic resonance imaging are fused using dual tree complex wavelet transforms and curvelet transform. The obtained images are further fused using proposed hybrid technique. MATLAB R2013a coding is used for the fusion of image fusion transforms. Two set of images (brain and abdomen) are used to compare and evaluate the performance of the fusion algorithms. The fused images were evaluated using performance assessment criteria's i.e. entropy, root mean square error, correlation coefficient, peak signal to noise ratio, mutual information and edge association. Result shows that the fused image using hybrid transform contains more useful information and relevant details for disease diagnosis. Performance evaluation criteria's gives higher weightage to hybrid image fusion followed by curvelet and dual tree complex wavelet transforms.

Keywords: image fusion; dual tree complex wavelet transform; DT-CWT; curvelet transform; CVT; hybrid image fusion; wavelet transform.

DOI: 10.1504/IJTMCP.2017.087876

International Journal of Telemedicine and Clinical Practices, 2017 Vol.2 No.3, pp.225 - 241

Received: 01 Dec 2016
Accepted: 20 Dec 2016

Published online: 06 Nov 2017 *

Full-text access for editors Full-text access for subscribers Purchase this article Comment on this article