Welcome to Scribd, the world's digital library. Read, publish, and share books and documents. See more
Standard view
Full view
of .
Look up keyword
Like this
0 of .
Results for:
No results containing your search query
P. 1
Comp Proceedings

Comp Proceedings

Ratings: (0)|Views: 65|Likes:
Published by scholaram

More info:

Published by: scholaram on Jul 27, 2012
Copyright:Attribution Non-commercial


Read on Scribd mobile: iPhone, iPad and Android.
download as DOC, PDF, TXT or read online from Scribd
See more
See less





Medical Image Fusion Based on Wavelet Transform
Ganesh J. Jagtap
Lecturer in Information Technology,SVPM’s Institute of Technology & Engineering, Malegaon(Bk),Tal: Baramati, Dist: Pune 413102
 If the analysis of the characters of CT medical image is carried out, it seems that a novel method for this particular image fusion is using discrete wavelet transform and independent component analysis. Firstly, each of CT images is de-composed by 2-D discrete wavelet transform. Then independent component analysis is used to analyze the wavelet coefficients in different level for acquiring independent component. At last, the use of wavelet reconstruction for synthesizing one CT medical image, which could contain more integrated accurate detail information of different soft tissue such asmuscles and blood vessels is made. By contrast, the efficiency of method is better than weighted average method or laplacian pyramid method in medical image fusion field. Nowadays, the study of multimodality medical image is very important because of increasing clinical applicationdemanding. We can get the different benefits from the information in the images of different modalities.
In the recent years, the study of multimodality medical image fusion attracts muchattention with the increasing of clinic application demanding. Radiotherapy plan, for instance,often benefits from the complementary information in images of different modalities. Dosecalculation is based on the computed tomography (CT) data, while tumor outlining is often better performed in the corresponding magnetic resonance (MR) scan. For medical diagnosis,CT provides the best information on denser tissue with less distortion, MRI provides better information on soft tissue with more distortion, and PET provides better information on bloodflow and flood activity with low space resolution in general. With more availablemultimodality medical images in clinical applications, the idea of combining images fromdifferent modalities becomes very important and medical image fusion has merged as a newand promising research field. The general object of image fusion is to combine thecomplementary information from multimodality images. Some image fusion methods have been introduced in the literatures, including statistical method (Bayesian's decision), Fuzzy setmethod, neural network method, Laplacian pyramid method and wavelet transform method. Itshould be noted that the fusion methods are application-dependent.
In the signal processing theory, the nature of non-periodic and transient signals cannoteasily be analyzed by conventional transforms. So, an alternative mathematical tool-wavelettransform, developed by MATLAB is used to extract the relevant time-amplitude informationfrom a signal.Woei-Fuh Wang ital[1] worked on PET-MRI image registration and fusion, providingfused image which gives both physiological and anatomical information with high spatialresolution for use in clinical diagnosis and therapy.Gemma Piella[2] presents new approach for accessing quality in image fusion byconstructing ideal fused image, used it as reference image and compare with the experimentalfused results. Mean Squared Matrices are widely used for these comparisons.Paul Hill, Nishan Canagarajah and Dave[3] Bull have introduced novel application of shift- invarient and directionally selective Dual Tree Complex wavelet transform (DT-CWT)
to image fusion, providing improved qualitative and quantitative results.Myungjin Choi, RaeYoung Kim, Myeong-Ryong NAM, and Hong Oh Kim[4] proposed the curvelet transform for image fusion .The curvelet-based image fusion method provides richer information in thespatial and spectral domains simultaneously. They performed Landsat ETM+ image fusionand found optimum fusion results.Yu Lifeng, Zu Donglin, Wang Weidong , Bao Shanglian[5] have proposed integratedscheme to fuse medical images from different modalities. First they have registered imagesusing SVD-ICP (Iterative Closest Points) method and evaluated the different fusion results byapplying different selection rules.QU Xiao have associated NSCT (Non Subsampled Countourlet Transform) withPCNN (Pulse Coupled Neural Networks) and employed in image fusion. Spatial frequency in NSCT domains is input to motivate PCNN and coefficients in NSCT with large firing timesare selected as coefficients of the fused image[6].
Take a more than two images reconstruction using Wavelet Transform to these imagesand the process of combining relevant information from two or more images into a singleimage. The resulting image will be more informative than any of the input images.
 3.2. Block Diagram
Figure. 3.1. Image Fusion Scheme
3.3. Module Wise Description
First, the CT and MRI images to be fused are decomposed by discrete wavelettransform. The images should be decomposed into same levels. These sub-band imagesconstitute the details of the original images.Using IDWT, have to combine the information from each image by fusion rules,taking significant components from each level.
3.3.1. Multiresolution Analysis
Although the time and frequency resolution problems are results of a physical phenomenon (the Heisenberg uncertainty principle) and exist regardless of the transform used,it is possible to analyze any signal by using an alternative approach called the multiresolutionanalysis (MRA). MRA, as implied by its name, analyzes the signal at different frequencieswith different resolutions. Every spectral component is not resolved equally as was the case inthe Short Time Fourier Transform (STFT).MRA is designed to give good time resolution and poor frequency resolution at highfrequencies and good frequency resolution and poor time resolution at low frequencies. Thisapproach makes sense especially when the signal at hand has high frequency components for 
short durations and low frequency components for long durations. Fortunately, the signals thatare encountered in practical applications are often of this type.The wavelet transform is a powerful tool for multiresolution analysis. Themultiresolution analysis requires a set of nested multiresolution sub-spaces as illustrated in thefollowing figure:
Figure. 3.2. Nested Multiresolution Spaces
The original space
can be decomposed into a lor resolution sub-space
, thedifference between
can be represented by the complementary sub-space
.Similarly, can continue to decompose
. The above graph shows 3-leveldecomposition. For an N-level decomposition, will obtain N+1 sub-spaces with one coarsestresolution sub-space
and N difference sub-space
, i is from 1 to N. Each digital signalin the space
can be decomposed into some components in each sub-space. In many cases,it's much easier to analyze these components rather than analyze the original signal itself.
3.3.2. Filter Bank Analysis
The corresponding representation in frequency space is intuitively shown in thefollowing graph: Can apply a pair of filters to divide the whole frequency band into twosubbands, and then apply the same procedure recursively to the low-frequency band on thecurrent stage. Thus, it is possible to use a set of FIR filters to achieve the abovemultiresolution decomposition. Here is one way to decompose a signal using filter banks.
Figure. 3.3. Multiresolution frequency bands
The effect of this shifting and scaling process is to produce a time-scale representation,as depicted in Figure 4. As can be seen from a comparison with the STFT, which employs awindowed FFT of fixed time and frequency resolution, the wavelet transform offers superior temporal resolution of the high frequency components and scale (frequency) resolution of thelow frequency components. This is often beneficial as it allows the low frequencycomponents, which usually give a signal its main characteristics or identity, to be

You're Reading a Free Preview

/*********** DO NOT ALTER ANYTHING BELOW THIS LINE ! ************/ var s_code=s.t();if(s_code)document.write(s_code)//-->