PROJECT TITLE :

Multimodal Medical Image Sensor Fusion Framework Using Cascade of Wavelet and Contourlet Transform Domains

ABSTRACT:

Multimodal medical image fusion is effectuated to minimize the redundancy whereas augmenting the necessary data from the input pictures acquired using different Medical Imaging sensors. The sole aim is to yield one fused image, that could be more informative for an efficient clinical analysis. This paper presents a two-stage multimodal fusion framework using the cascaded combination of stationary wavelet rework (SWT) and non sub-sampled Contourlet transform (NSCT) domains for images acquired using 2 distinct medical imaging sensor modalities (i.e., magnetic resonance imaging and computed tomography scan). The major advantage of employing a cascaded combination of SWT and NSCT is to improve upon the shift variance, directionality, and section info in the finally fused image. The primary stage employs a principal part analysis algorithm in SWT domain to reduce the redundancy. Maximum fusion rule is then applied in NSCT domain at second stage to reinforce the distinction of the diagnostic options. A quantitative analysis of fused pictures is disbursed using dedicated fusion metrics. The fusion responses of the proposed approach are compared with different state-of-the-art fusion approaches; depicting the prevalence of the obtained fusion results.