Medical image fusion based on redundancy DWT and Mamdani type min-sum mean-of-max techniques with quantitative analysis

Medical imaging requires capturing different aspects of a human body. To capture tissues, cartilages, bones and nerves one needs different sensors and different modalities which results in different images from each modality of the same body part. Image fusion is a process by which one can fuse such images from different modalities in a single image. In this paper, a novel DWT-type2 fuzzy method is proposed to fuse two images (CT and MRI images). In this method, initially, the source images are decomposed into low-level and high-level subbands by discrete wavelet transformation (DWT). As the second step, for fusion, Type-2 fuzzy technique is applied on a low-level subband and average fusion method is applied on the high-level subbands in order to enhance the most prominent features present in CT image and MRI image. Finally, the fused low-level subband and highlevel subbands are reconstructed to form the final fused image using inverse-DWT. To test the proposed fusion method, the experiment is carried out on the MRI-T2 image, functional MRI image and CT image. The fused images have been subjectively and objectively evaluated based on certain evaluation measures and the obtained results have been presented in the paper. From the results, one can observe that the proposed method provides an improvement over other primitive fusion methods.

show abstract

“…SSIM is a measure used to measure the similarity between the fused and source image [14]. The SSIM can be defined as…”

Section: Structural Similarity Indexmentioning

confidence: 99%

CT and MRI Image Fusion Based on Discrete Wavelet Transform and Type-2 Fuzzy Logic

Agarwal¹,

Soundrapandiyan²,

Karuppiah³

et al. 2017

IJIES

View full text Add to dashboard Cite

show abstract

“…The Image fusion techniques are also used in medical science. Medical image fusion helps to do an accurate disease diagnosis [10]. Medical fusion image generally combine functional image and anatomical image to produce one image with plenty of information for an accurate diagnose of disease [11].…”

Section: Introductionmentioning

confidence: 99%

An Enhanced DCT based Image Fusion using Adaptive Histogram Equalization

Singh¹,

Banga²

2014

IJCA

View full text Add to dashboard Cite

Image fusion fuses the information from several images of one scene to obtain a precise, complete and reliable image which is more appropriate for human visual perception or additional vision processing. The quality of an image is closely related to image focus. The discrete cosine transforms (DCT) based methods of image fusion are more suitable and time-saving in real-time systems using DCT based standards of still image or video. DCT based image fusion produced results but with lesser clarity, less PSNR value and more Mean square error. This paper proposes a new algorithm whose overall objective is to improve the results by combining DCT with adaptive histogram equalization. The experimental results and comparison has shown that the proposed algorithm provides a significant improvement over the existing DCT based fusion techniques.

show abstract

“…For the this reason, Medical image fusion is the only promising technique which is successful to attract researchers, scientist to guide the doctors by producing high quality fused images and by extracting suitable information from a variety of modalities say CT, MRI, SPET, PET etc. In the area of medical image fusion, there are various fusion techniques, but these techniques have certain limitations [2]. For example, Wavelet transform is famous technique but suffers from Shift variance and suffer with additive noise which can be reduced by Using DDWT (Dual Tree Discrete Wavelet Transform).…”

mentioning

confidence: 99%

“…It gives the contrast information of the image Higher value of SNR indicates more contrast. [2] SNR=Mean/Standard Deviation (4)…”

mentioning

confidence: 99%

See 1 more Smart Citation

New Technique for Image Fusion Using DDWT and PSO In Medical field

PPatil¹

2015

IJRITCC

View full text Add to dashboard Cite

Abstract-Image fusion is a process where multiple images (more than one) from different or same images of object are combined to form a single resultant fused image. This fused image is more informative, descriptive and qualitative as compared to its original input images or than individual images. The fusion technique in medical images is useful for resourceful disease diagnosis purpose and for doctors having varying experiences. This paper illustrates multimodality medical image fusion techniques and their results evaluated and analyzed with six quantitative metrics specified in last section of the paper.In this paper, a multimodality image fusion algorithm based on Dual tree discrete wavelet transform and particle swarm optimization (PSO) is proposed. Firstly, the source images are divided into low-frequency coefficients and high-frequency coefficients by the dual-tree discrete wavelet transform (DDWT) as separate parallel branch of band. PSO is used to determine to obtain proper fusion weight parameter from highfrequency coefficients from segmented images by DDWT. Also PSO is used to determine α parameter called scalar weight. Finally, the fused image is reconstructed by the inverse DDWT. Thus quality of fused image is measured with PSNR, SNR, OCE, MI, Entropy

show abstract

Medical image fusion based on redundancy DWT and Mamdani type min-sum mean-of-max techniques with quantitative analysis

Cited by 27 publications

References 9 publications

CT and MRI Image Fusion Based on Discrete Wavelet Transform and Type-2 Fuzzy Logic

CT and MRI Image Fusion Based on Discrete Wavelet Transform and Type-2 Fuzzy Logic

An Enhanced DCT based Image Fusion using Adaptive Histogram Equalization

New Technique for Image Fusion Using DDWT and PSO In Medical field

Contact Info

Product

Resources

About