INTRODUCTION

Medical imaging is an important source of diagnosing the malfunctions inside human body.  Some crucial medical imaging instruments are X-ray, Ultrasound, Computed Tomography (CT), and Magnetic Resonance Imaging (MRI). Medical ultrasound imaging is one of the significant techniques in detecting and visualizing the hidden body parts. There could be distortions due to improper contact or air gap between the transducer probe and the human body. Another kind of distortion that may occur during ultrasound imaging is due to the beam forming process and also during the signal processing stage. In order to overcome through various distortions, image processing has been successfully used. Image processing is a significant technique in medical field, especially in surgical decisions. Converting an image into homogeneous regions has been an area of hot research from a decade, especially when the image is made up of complex textures. Various techniques have been proposed for this task, including spatial frequency techniques. Image processing techniques have been used widely depending on the specific application and image modalities. Computer based detection of abnormal growth of tissues in a human body are preferred to manual processing methods in the medical investigations because of accuracy and satisfactory results. Several methods for processing the ultrasound images have been developed. The different methods of analyzing the scans can be classified under five broad categories. These are methods based on statistics (clustering methods), fuzzy sets theory, mathematical morphology, edge detection, and region growing? Image processing of ultrasound image allows extracting the invisible parts of human body and provides valuable information for further stages of the quantitative evaluation. Various methods have been proposed for processing ultrasound scans to make effective diagnosis. However, there is still a scope for improvement in terms of the quality of processed images.

Ultrasound images

Ultrasound imaging plays crucial role in cardiology, obstetrics, gynecology, abdominal imaging, etc., due to its non-invasive nature and capability of forming real time imaging. Medical Ultrasound imaging is done by using ultrasonic waves between 2 to 20 MHz ranges without the use of ionizing radiation. The basic principle in ultrasound imaging is that the ultrasonic waves are produced from the transducer and penetrates in the body tissues and when the wave reaches an object or a surface with different texture or acoustic nature, some fraction of the this energy is reflected back. The echoes so produced are received by the apparatus and changed into electric current. These signals are then amplified and processed to get displayed on CRT monitor.  The output image so obtained is known as ultrasound scan and the process is called as ultra-sonogram.  There are different modes of ultrasound imaging. The most common modes are (a) b-mode (the basic two-dimensional intensity mode), (b) m-mode (to assess moving body parts (e.g. cardiac movements) from the echoed sound), and (c) Color mode (pseudo coloring based on the detected cell motion using Doppler analysis). Ultrasound imaging technique is inexpensive and is very effective for cyst and foreign element recognition inside the human body

Aura transformation

Aura transformation is mainly used for analysis and synthesis of textures.  It is defined as the relative distribution of pixels intensities with respect to a predefined structuring element. The matrix computed from the local distribution of pixel intensities of the given texture is called aura matrix. Aura set and aura measure are the basic components of the aura based texture analysis. Aura set describes the relative presence of one gray level in the neighborhood of another gray level in a texture and its quantitative measure called aura measure.A neighborhood element is used to calculate the relative presence of one gray level with respect to another. The concept of Aura has also been applied to 3D textures to generate the solid textures from the input samples automatically without user intervention.

OBJECTIVES

The role of medical scans is vital in diagnosis and treatment. There is every possibility of distortion during the image acquisition process, which may badly affect the diagnosis based on these images. Thus, image Processing has become an essential exercise to extract the exact information from the medical images or Scans. In recent times, researchers made various attempts to enhance the biomedical images using various Signal processing methods. Several techniques have been explored and reported for improving the quality of the medical images. Still, there is a scope of improvement in the area of quality enhancement of the Medical scans. We investigated an aura based technique for enhancing the quality of medical Ultrasound images. An algorithm has been developed using aura transformation whose performance has been evaluated on a series of diseased and normal ultrasound images.

PROBLEM FORMULATION

An aura based technique is investigated for enhancing the quality of the ultrasound

Images for better medical diagnosis. Extensive investigations have been carried out with Ultrasound images involving different problems. The processed images, using aura based Algorithm, indicates the enhancement of the important regions of the ultrasound images. The Details of medical ultrasound imaging have been presented

METHODOLOGY / PLANNING OF WORK

In preprocessing step, the input ultrasound images are converted to gray scale and its modified to reduce the number of computations. The reduction depends on the expected size and texture of the abnormal region in the scan.

Different types of normal and diseased ultrasound images are processed for investigating the effect of aura on the neighborhood structures of the images. A neighborhood element is defined in the form of a 33 matrix.

The values of the elements of this matrix are estimated on the basis of gray scale values of the given ultrasound image. The input image is processed using this structuring element by traversing  it pixel by pixel on the whole image.

At every placement, the differences of the gray scale values of the neighborhood elements and the corresponding pixels below it are computed.

Depending upon the difference threshold Td, the 3×3 matrix of the difference is converted to zeros and ones.

If the difference is less than Td, the corresponding element is mar ked as one otherwise, zero in the difference matrix.

If the total number of ones in the difference matrix is more than a threshold value called matching threshold Tm, the pixel corresponding to the central element of the neighborhood element is marked as black, otherwise left unchanged.

This process is repeated for the entire input image.

The investigations have been carried out with different values of both the thresholds and input ultrasound images.

The evaluation for the enhancement in the processed ultrasound image with respect to the input image was carried out using the visual inspection.

FUTURE SCOPE

The investigations involving the images obtained from other medical imaging techniques are in our future plan. We can also enhance the quality of obtained images by applying a second level of filter after the image has been processed with our algorithm. We can also compare different level 2 filters so as to get the best combination of filter to be used with our algorithm.

CONCLUSION

In this study, investigations were carried out to enhance the quality of the ultrasound images usingmodified aura based transformation. It was observed that this transformation technique is relativelyless expensive, simple, and promising. The duration for processing the image is very less. The investigations further showed that theprocessed ultrasound images were enhanced in quality. The enhanced images may be used forpredicting the diseases inside the human body more effectively and accurately.

LITERATURE SURVEY

Image Decomposition Using Wavelet Transform

In this work, image has been decomposed on wavelet decomposition technique using different wavelet transforms with different levels of decomposition. Two different images were taken and on these images wavelet decomposition technique is implemented. The parameters of the image were calculated with respect to the original image. Peak signal to noise ratio (PSNR) and mean square error (MSE) of the decomposed images were calculated. PSNR is used to measure the difference between two images. From the several types of wavelet transforms, Daubechie (db) wavelet transforms were used to analyze the results. The value of threshold is rescaled for denoising purposes. De-noising methods based on wavelet decomposition is one of the most significant applications of wavelets.

Image enhancement technique on Ultrasound Images using Aura Transformation

The role of medical scans is vital in diagnosis and treatment. There is every possibility of distortion during  the image acquisition process, which may badly affect the diagnosis based on these images. Thus, image processing has become an essential exercise to extract the exact information from the medical images or scans. In recent times, researchers made various attempts to enhance the biomedical images using various signal processing methods. Several techniques have been explored and reported for improving the quality of the medical images. Still, there is a scope of improvement in the area of quality enhancement of the medical scans. In this paper, we investigated an aura based technique for enhancing the quality of medical ultrasound images. An algorithm has been developed using aura transformation whose performance has been evaluated on a series of diseased and normal ultrasound images.

Investigations of the MRI Images using Aura Transformation

The quality of biomedical images can be enhanced by using several transformations reported in the literature. The enhanced images may be useful to extract the exact information from these scans. In recent times, researchers exploited various mathematical models to smoothen and enhance the quality of the biomedical images with an objective to extract maximum useful medical information related to functioning or malfunctioning of the brain. Both real and non-real time based techniques have been explored and reported for this purpose. In this proposed work, aura based technique has been investigated for enhancing the quality of magnetic resonance imaging (MRI) scans of the human brain. The aura transformation based algorithm with some modifications has been developed and the performance of the algorithm is evaluated on a series of defected, diseased, and normal MRI brain images.

A completely automatic segmentation method for breast ultrasound images -using region growing

In this paper, we propose a fully auto-matic segmentation algorithm of masses on breast ultrasound images by using region growing technique. First, a seed point is selected automatically from the  mass region based on both textural features and spatial features. Then, from the  selected seed point, a region growing algorithm based on neutrosophic logic is implemented. The whole algorithm needs  no manual intervention at all and is completely automatic. Experiment results  show that the proposed segmentation algorithm is efficient in both selecting seed point and segmenting region of interests (ROIs).

Automatic Boundary Detection of Wall Motion in Two-dimensional Echocardiography Images

Medical image analysis is a particularly difficult problem because the  inherent characteristics of these images, including low contrast, speckle noise, signal dropouts and complex anatomical structures. An accurate analysis of wall motion in Two-dimensional echocardiography images is “important clinical diagnosis parameter for many cardiovascular diseases”. A challenge most researchers faced is how to speed up the clinical decisions and reduce human error of estimating accurately the true wall movements boundaries if can be done automatically will be a useful tool for assessing these diseases qualitatively and quantitatively.

MATLAB SOURCE CODE

Instructions to run the code

  1. Copy each of below codes in different M files.
  2. Place all the files in same folder
  3. Download the file from below and place in same folder
    1. results
  4. Also note that these codes are not in a particular order. Copy them all and then run the program.
  5. Run the “final.m” file

Code 1 – Script M File – Final.m

clc
clear
close all


% reading all the images at once
[IMAGES,n]=image_read;

% performing the preprocessing operations
[NHOOD,SE,u,r1,c1]=preprocessing;

% applying aura transformation on the image database created earlier
apply_aura(NHOOD,SE,u,r1,c1,IMAGES,n)

% 
% I=imread('image.jpg');
% I=rgb2gray(I);
% orig=I;
% figure, imshow(orig)
% title('Original Image')
% 
% [NHOOD,SE,u,r1,c1]=preprocessing;
% 
% for Tm=1:u
%     Tm
%     Iin=orig;
%     % checking all the pixels of the input image
%     Iout=aura(Iin);
%     
%     [PSNR(Tm),MSE(Tm),MAXERR,L2RAT]= measerr(orig,Iout);
%     ENTROPY(Tm)=entropy(I);
%     
%        
% end
% 
% 
% disp('Final Results are stored in the excel file : ')
% res=[1:u; MSE; PSNR; ENTROPY]

Code 2 – Function M File – apply_aura.m

function apply_aura(NHOOD,SE,u,r1,c1,IMAGES,n)

for i=1:n % running the code for all images in database
    Iin=IMAGES(:,:,i); % selecting an image
    PSNR=[];     MSE=[];     MAXERR=[];     L2RAT=[];     ENTROPY=[]; % initializing variables to store results
    
    for Tm=1:u
        
        Iout=aura(Iin,NHOOD,SE,u,r1,c1,Tm); % apply aura transformation on selected image
        outimagename=['Image' num2str(i) ' Tm=' num2str(Tm) '.jpg'];
        imwrite(Iout,outimagename)
        [PSNR(Tm),MSE(Tm),MAXERR(Tm),L2RAT(Tm)]= measerr(Iin,Iout);
        ENTROPY(Tm)=entropy(Iout);
        
    end 
    
    filename='results.xlsx';
    A={'Tm' 'MSE' 'PSNR' 'MAXERR' 'L2RAT'  'ENTROPY'};
    sheet=['image' num2str(i)];
    xlswrite(filename,A,sheet,'A1')
    
    filename='results.xlsx';
    A=[1:u; MSE; PSNR; MAXERR; L2RAT; ENTROPY]';
    sheet=['image' num2str(i)];
    xlswrite(filename,A,sheet,'A2')
    
end



Code 3 – Function M File – preprocessing.m

function [NHOOD,SE,u,r1,c1]=preprocessing

NHOOD=[1 1 1; 0 1 0; 0 1 0]; % defining the structuring element
SE=strel(NHOOD); % creating a structuring element
[r1,c1]=size(NHOOD);
u=r1*c1; %maximum value for Tm

end

Code 4 – Function M File – image_read.m

function [IMAGES,n]=image_read

IMAGES=[]; % empty matrix where images will be stored
n=10; % total number of images
for i=1:n  % running the loop for total number of images 
    im=imread(['image' num2str(i) '.jpg']); % reading an ith image
    if length(size(im))==3
%         i
%         disp('catch')
        im=rgb2gray(im); % convert to grayscale if it is a color image
    end
    im=imresize(im,[500 500]);
    IMAGES(:,:,i)=im; % storing the read image file into the empty matrix created earlier
end

end

Code 5 – Function M File – aura.m

function Iout=aura(Iin,NHOOD,SE,u,r1,c1,Tm)

I=Iin;
[r2,c2]=size(I);
for i=1:(r2-r1)
    for j=1:(c2-c1)
        mat=I(i:i+r1-1,j:j+c1-1);
        Tm_dash=length(find(mat==NHOOD));
        if Tm_dash>Tm
            a=i+round(r1/2);
            b=j+round(c1/2);
            I(a,b)=0;
        end
    end
end
Iout=I;

end

 

Write Your Comments

Your email address will not be published. Required fields are marked *

Recent Posts

Tags

ad-hoc networks AODV boundary detection process classification clustering clustering algorithm Colour Information computer vision Decryption Encryption EZRP ICM (Iterated Conditional Modes) image denoising image enhancement IMAGE PROCESSING image segmentation Imaging and image processing MANET Markov Random Fields neutrosophic logic optical network proposed method PSNR QLab system region growing Robert’s operator Seed point selection segmentation semi-automatic algorithm Shadow Detection shadow removal wall motion wireless communication Wireless network wireless networks Wireless Sensor Network wireless sensor networks ZRP