Multi-modality medical image fusion using hybridization of binary crow search optimization

  • PDF / 1,261,745 Bytes
  • 9 Pages / 595.276 x 790.866 pts Page_size
  • 44 Downloads / 163 Views

DOWNLOAD

REPORT


Multi-modality medical image fusion using hybridization of binary crow search optimization Velmurugan Subbiah Parvathy 1

&

Sivakumar Pothiraj 1

Received: 2 May 2019 / Accepted: 4 July 2019 # Springer Science+Business Media, LLC, part of Springer Nature 2019

Abstract In clinical applications, single modality images do not provide sufficient diagnostic information. Therefore, it is necessary to combine the advantages or complementarities of different modalities of images. In this paper, we propose an efficient medical image fusion system based on discrete wavelet transform and binary crow search optimization (BCSO) algorithm. Here, we consider two different patterns of images as the input of the system and the output is the fused image. In this approach, at first, to enhance the image, we apply a median filter which is used to remove the noise present in the input image. Then, we apply a discrete wavelet transform on both the input modalities. Then, the approximation coefficients of modality 1 and detailed coefficients of modality 2 are combined. Similarly, approximation coefficients of modality 2 and detailed coefficients of modality 1 are combined. Finally, we fuse the two modality information using novel fusion rule. The fusion rule parameters are optimally selected using binary crow search optimization (BCSO) algorithm. To evaluate the performance of the proposed method, we used different quality metrics such as structural similarity index measure (SSIM), Fusion Factor (FF), and entropy. The presented model shows superior results with 6.63 of entropy, 0.849 of SSIM and 5.9 of FF. Keywords Modality . Binary crow search optimization . Medical image fusion . Median filter . Discrete wavelet transform . Approximation coefficients . Detailed coefficients

1 Introduction The process of merging various input images’ primary feature into a single image that can provide better detailing than each individual image is known as image fusion. Image fusion is very crucial as it enhances the execution of object recognition systems by combining many sources of images with some other related data sets. Also it assists in enhancing geometric corrections, sharpening the images, substituting the defective data, improving some features which are invisible in wither of the images and contributes more data sets for better decision making [1]. Image fusion techniques are classified into three sorts such as pixel level, feature level and decision making

* Velmurugan Subbiah Parvathy [email protected] Sivakumar Pothiraj [email protected] 1

Department of Electronics and Communication Engineering, Kalasalingam Academy of Research and Education, Tamil Nadu, India

level. Pixel level fusion processes the pixels of source image and preserve almost every original image information. Feature level method processes the properties of the source image. Decision making level method utilizes data information gathered from pixel level or feature level fusion to make optimal decision to attain a particular objective [2]. Image fusion is mostly util