International Journal of Advanced Engineering Research and Science (IJAERS) Vol-3, Issue-2 , Feb- 2016]

ISSN: 2349-6495

www.ijaers.com Page | 25

Analysis of Medical Image Processing and its Application in Healthcare

Dr. K.Sakthivel, B.R.Swathi, S.Vishnu Priyan, C.Yokesh

Department of CSE, K.S.Rangasamy College of Technology,Tiruchengode Abstract—Medical image processing is the most challenging and emerging field now a days.With fundamentally improving technical knowledge, enhanced technological support and well-constructed medical equipment, medical diagnosis is increasingly becoming easy for doctors and medical staffs. However accurate diagnosis is still not possible. The approximate values and prediction may effect to a certain range but do not provide a cure.This is due to using of multiple and multiple testing systems when choosing between best and reliable becomes questionable.When it comes to Scan,X-rays and MRIs, the image results between each test samples shows significant variations and it is still arguable to find out the best pick.As MRIs are better choice due to it’s considerable efficiency rate, it has been often preferred in medical image diagnosis.Processing of MRI image is one of the integral part of this field. The proposed strategy is to detect,analyze and extract the tumor from patient’s MRI scan images of the brain. This method incorporates with some noise removal functions, segmentation,filtering processes and morphological operations which are the basic concepts of image processing.MATLAB provides a complete full packed environment to support image analysis domain with some built-in function and wide range of image processing tools.Thus,detection and extraction of tumor cells from MRI scan images of the brain is done by using MATLAB software.

Keywords— GUI, MATLAB, MRI, Segmentation, Enhancement.

I. INTRODUCTION Image processing is a method to convert an image into digital form and perform some operations on it, in order to get an enhanced image or to extract some useful information from it. It is a type of signal dispensation in which input is image, like video frame or photograph and output may be image or characteristics associated with that image. Usually Image Processing system includes treating images as two dimensional signals while applying already set signal processing methods to them. It is among rapidly

growing technologies today, with its applications in various aspects of a business. Image Processing forms core research area within engineering and computer science disciplines too. The two types of methods used for Image Processing are Analog and Digital Image Processing. Analog or visual techniques of image processing can be used for the hard copies like printouts and photographs. Image analysts use various fundamentals of interpretation while using these visual techniques. The image processing is not just confined to area that has to be studied but on knowledge of analyst. Association is another important tool in image processing through visual techniques. So analysts apply a combination of personal knowledge and collateral data to image processing. Digital Processing techniques help in manipulation of the digital images by using computers. As raw data from imaging sensors from satellite platform contains deficiencies. To get over such flaws and to get originality of information, it has to undergo various phases of processing. The three general phases that all types of data have to undergo while using digital technique are Pre- processing, enhancement and display, information extraction. Image processing basically includes the following three steps.

• Importing the image with optical scanner or by digital photography

• Analyzing and manipulating the image which includes data compression and image enhancement and spotting patterns that are not to human eyes like satellite photographs

• Output is the last stage in which result can be altered image or report that is based on image analysis.

II. LITERATURE REVIEW Image processing is the field in which the information from images can be retrieved using suitable algorithm. The morphological image processing is used to detect the tumors from the brain either malignant or non-malignant tumors. The brain tumors some times change to malignant

International Journal of Advanced Engineering Research and Science (IJAERS) Vol-3, Issue-2 , Feb- 2016]

ISSN: 2349-6495

www.ijaers.com Page | 26

will leads to cancer. There are several techniques to capture image of brain like MRI, CT scan etc… A tumor is a mass of tissue that grows out of control of the normal forces that regulates growth. The multifaceted brain tumors can be split into two common categories depending on the tumors beginning, their enlargement prototype and malignancy. Primary brain tumors are tumors that take place commencing cells in the brain or commencing the wrapper of the brain. U.Vanitha et al performed morphological operations like dilation, erosion etc… was done to remove the tumor from the MRI Image. Recent techniques achieved in researches for detection of brain tumor can be broadly classified as 1. Histogram based method. 2. Morphological operation is applied to MRI images of Brain. 3. Edge base segmentation and color base segmentation. 4. Cohesion self-merging based partition K-mean [2]. The proposed work carried out processing of MRI brain images for detection and classification of tumor and non-tumor image by using classifier. The image processing techniques like histogram equalization, image enhancement, image segmentation and then extracting the features for Detection of tumor. Extracted feature are stored in the knowledge base. An appropriate classifier is developed to recognize the brain tumors by selecting various Features. The system is designed to be user friendly by using MATLAB GUI tool. Dr. P.V. Ramaraju et al proposed pre-processing of MRI images is the primary step in image analysis which perform image enhancement and noise reduction techniques which are used to enhance the image quality, then some morphological operations are applied to detect the tumor in the image. The MRI brain image is acquired from patient’s database and then Image acquisition, pre-processing, image segmentation is performed for brain tumor detection [11]. SivaSankari.S et al used median filter for removing noise from an image. The median filter is a non-linear digital filtering technique, is often used to remove noise. Median filtering is very widely used in digital image processing because, under certain conditions, it preserves edges while removing noise. The median filter is normally used to reduce noise in an image, somewhat like the, mean filter. However, it often does a better job than the mean filter [13].

III. PROPOSED SYSTEM Segmentation is a process that is used to identify an object orpattern in the given work space. The main goalis to partition an image into several segments so that each

segment can be analyzed precisely.The preliminary function is to read the input image .Here the input image is MRI image. The input image may contain RBG color and this RBG color should be removed so that the further process will be enhanced clearly. So the RBG color should be converted to greyscale image. Segmentation operation is performed with the resulted greyscale image. There may be presence of noise in the image. So it must be removed by the noise removal technique. Then the morphological operation includes detection of the entire cell, dilation of the cell, filling the entire gaps, smoothing of the object is done simultaneously.The steps are as follows:-

• Segmentation

• Noise Removal

• Morphological Operation

• Image Enhancement

• Image Filtering The preliminary function is to read the input image.Here the input image is MRI image. The input image may contain RBG color and this RBG color should be removed so that the further process will be enhanced clearly. So the RBG color should be converted to greyscale image. Segmentation operation is performed with the resulted greyscale image. There may be presence of noise in the image. So it must be removed by the noise removal technique. Then the morphological operation includes detection of the entire cell, dilation of the cell, filling the entire gaps, smoothing of the object is done simultaneously. 3.1 Segmentation Image segmentation is a process where the image can be partitioned into cluster of pixels which are similar based on some criteria. Different groups must not interact with each other, and neighboring cells can be compared. The result of segmentation is the splitting up of the image into connected areas. Thus segmentation is concerned with dividing an image into meaningful regions. MR image segmentation is an important but a difficult problem in medical image processing. In general, it cannot be solved using straightforward, conventional image processing techniques. There will be some variation in signal intensities for one same tissue type, which affect the tissue intensities.Segmentation process is thus used to partition such cells. By using MATLAB, the tumor is detected as a result of segmentation and optimal global thresholding. The brain tumor detection is a great help for the physicians and a boon for the medical imaging and industries working on the production of CT scan and MRI imaging.

International Journal of Advanced Engineering Research and Science (IJAERS)

www.ijaers.com

Fig. 1: Segmentation 3.2 Noise Removal It is not sure that the Digital image contains no noisein the image will be in the form of that result in pixel values that do not reflect the true intensities of the real scene. There are several ways that noise can be introduced into an image, depending on how the image is created. For example:

• If the image is scanned from a photograph made film, the film grain is a source of noise. Noise can also be the result of damage to the film, or be introduced by the scanner itself.

• If the image is acquired directly in a digital format, the mechanism for gathering the data (such as a CCD detector) can introduce noise.

• Electronic transmission of image data can introduce noise.

To simulate the effects of some of the problems listed above, the toolbox provides theimnoisefunction, wbe used to perform some manipulation operation with noise3.4 Morphological Operation Morphological operations results in the same sized output as the input image size. In a morphological operation, the value of each pixel in the output image iscomparison of the corresponding pixel in the input image with its neighbors. By choosing the size anneighborhood, we can construct a morphological operation that is sensitive to specific shapes in the input image. One of the basic morphological operations is dilationDilation adds pixels to the boundaries of objects in an image. The number of pixels added or removed from the objects in an image depends on the size and shape of the structuring element used to process the imagmorphological dilation, the state of any given pixel in the output image is determined. 3.3 Image Enhancement To improve the interpretability or perception of information, images are enhanced and it provides input for other automated image processing techniques. The principal objective of image enhancement is to modify attributes of an image to make it more suitable for a given

International Journal of Advanced Engineering Research and Science (IJAERS)

It is not sure that the Digital image contains no noise. Errors that result in pixel

values that do not reflect the true intensities of the real scene. There are several ways that noise can be introduced into an image, depending on how the image is created. For

If the image is scanned from a photograph made on film, the film grain is a source of noise. Noise can also be the result of damage to the film, or be

If the image is acquired directly in a digital format, the mechanism for gathering the data (such as a CCD

Electronic transmission of image data can introduce

To simulate the effects of some of the problems listed function, which can

be used to perform some manipulation operation with noise.

results in the same sized output . In a morphological operation, the

value of each pixel in the output image is based on a comparison of the corresponding pixel in the input image with its neighbors. By choosing the size and shape of the

can construct a morphological operation that is sensitive to specific shapes in the input image.

rations is dilation. Dilation adds pixels to the boundaries of objects in an image. The number of pixels added or removed from the objects in an image depends on the size and shape of the structuring element used to process the image. In the morphological dilation, the state of any given pixel in the

or perception of it provides ̀ better'

input for other automated image processing techniques. The principal objective of image enhancement is to modify attributes of an image to make it more suitable for a given

task and a specific observer. During this process, one or more attributes of the image are modified. Filtering is technique for enhancing the image. Image division is done on the basis of similar attributesthey are separated into groups. Basic purpose of segmentation is the extraction of affected regions from the image, from which information can easily be perceived. Thresholding is used for segmentation as it is most suitable for the present application in order to obtain a binarized image with gray level 1 representing the tumor and gray level 0 representing the backgroun After converting the image in the binary format, morphological operations are applied on the converted binary image. The purpose of the morphological operators is to separate the tumor part of the image. Now only the tumor portion of the image is visiThis portion has the highest intensity than other regions of the image. 3.5Image Filtering Filter process removes unwanted component or featurean image. It defines the feature of filters as apartial suppression of some aspect of the imagebackground noise will be removedexclusively act in thefrequency domaifield of image processing exist. Correlations can be removed for certain frecomponents and not for othersfrequency domain. The most common methods used for filteriimages till now are the low pass filteringand median filtering (for smoothening). But these methods have certain drawbacks like blurring the details as well as edges in an MRI image. So, out. It sharpens the image and preserves the high frequency information within an image. applied.

Fig. 2: Salt and P

Vol-3, Issue-2 , Feb- 2016]

ISSN: 2349-6495

Page | 27

task and a specific observer. During this process, one or of the image are modified. Filtering is

technique for enhancing the image. ivision is done on the basis of similar attributes and

into groups. Basic purpose of segmentation is the extraction of affected regions from the

om which information can easily be perceived. Thresholding is used for segmentation as it is most suitable for the present application in order to obtain a binarized image with gray level 1 representing the tumor and gray level 0 representing the background. After converting the image in the binary format, morphological operations are applied on the converted binary image. The purpose of the morphological operators is to separate the tumor part of the image. Now only the tumor portion of the image is visible, shown as white color. This portion has the highest intensity than other regions of

process removes unwanted component or feature in an image. It defines the feature of filters as a complete or a

on of some aspect of the image. As a result, will be removed. Filters do not

frequency domain,especially in the image processing many other targets for filtering

exist. Correlations can be removed for certain frequency components and not for others without having to act in the

The most common methods used for filtering of medical low pass filtering(for sharpening)

(for smoothening). But these methods have certain drawbacks like blurring the details as well as edges in an MRI image. So, high pass filtering is carried

sharpens the image and preserves the high frequency information within an image. Here median pass filtering is

Salt and Pepper Noise Image

International Journal of Advanced Engineering Research and Science (IJAERS)

www.ijaers.com

Fig. 3: Median Filtered Image

3.6 Image Preprocessing When MRI images are viewed on computer screen, they look like black and white but in actual they contain some primary colors (RGB) content. So, for further processing of MRI brain image, it must be converted to perfect grayscale image in which the red, green and blue components all have equal intensity in RGB space. The original MRI brain image has properties 320x320x3 and conversion to grayscale image makes the properties 320x320. This step is carried out to improve the quality of the image to make it ready for further processing. This improved and enhanced image will help in detecting edges and improving the quality of the overall image.

3.7 Image Preprocessing using MATLABThe Image Processing Toolbox is a collection of functions that extend the capabilities of the MATLAB’s numeric computing environment. The toolbox supports a wide range of image processing operations, including:

• Geometric operations

• Neighborhood and block operations

• Linear filtering and filter design

• Transforms

• Image analysis and enhancement

• Binary image operations

IV. CONCLUSIONThe main objective of the proposed methodabnormal cells based on the optimal features classification is performed based on obtained Magnetic Resonance Images. The accurate results depends on selection, classification and processing techniques and datasets obtained from MRI images. Series of oare made on obtained datasets using MATLAB and the results obtainedare evaluated to be more accurate

International Journal of Advanced Engineering Research and Science (IJAERS)

Median Filtered Image

When MRI images are viewed on computer screen, they look like black and white but in actual they contain some primary colors (RGB) content. So, for further processing of MRI brain image, it must be converted to perfect grayscale

en and blue components all have equal intensity in RGB space. The original MRI brain image has properties 320x320x3 and conversion to grayscale image makes the properties 320x320. This step is carried out to improve the quality of the image

dy for further processing. This improved and enhanced image will help in detecting edges and improving

Image Preprocessing using MATLAB The Image Processing Toolbox is a collection of functions

of the MATLAB’s numeric computing environment. The toolbox supports a wide range of image processing operations, including:

Neighborhood and block operations

ement

CONCLUSION of the proposed methodis to analyze the

on the optimal features set. This classification is performed based on obtained Magnetic

results depends on the selection, classification and processing techniques and

from MRI images. Series of observations are made on obtained datasets using MATLAB functions and the results obtainedare evaluated to be more accurate

and robust when compared with the other classifiers.resulted process would certainly enhance and help the current diagnosis techniques

REFERENCE[1] Mohinder Singh, Pankaj Kr. Saini

Tumor Detection in Medical Imaging using MATLAB”, International Research Journal of Engineering and Technology (IRJET)Vol.02, No.2, pp.191-196

[2] P.Prabhu Deepak,N.PonNageswaran, U.Vanitha, (2015) “Tumor Detection In Brain UsinMorphological Image Processing”, Journal of Applied Science and Engineering Methodologies Vol.01, No.1, pp. 131-136

[3] V.Kala, Dr.K.Kavitha (2015)“Brain Tumor Extraction from MRI Images Using MATLAB”, International Journal of Advanced Technology in EngineScience, Vol.03, No.1,pp.453459

[4] Mohinder Singh, Pankaj Kr. SainiTumor and Clustering Techniques Review”, International Journal of Emerging Technology and Innovative Engineering Vol.01, No.6, pp.110

[5] Azhar,Ed-EdilyMohd. Muhd. MudzaZawZawHtikeandShoon Lei Win (2014), “Brain Tumor Detection And Localization In Magnetic Resonance Imaging”, International Journal of Information Technology Convergence and Services (IJITCS), Vol.4, No.1, pp. 1

[6] M.Manikandan, Rohini Pau(2014) “Brain Tumor MRI Image Segmentation and Detection in Image Processing”, IJRET: International Journal of Research in Engineering and Technology Vol.3, No.1, pp.1-5

[7] Nidhi, PoonamKumari (2014), ”Brain Tumor and Edema Detection using MATLAB 7.6.0.324”, International Journal of Computer Engineering and Technology, Vol.5, No.3, pp. 122Patil, Dr. A. S. Bhalchandra (2014) “Brain Tumor Extraction from MRI Images Using MATLAB”, International Journal of Emerging Innovative Engineering Vol.02, No.1, pp.1

[8] Balakumar.B, MuthukumarSubramanyam, P.Raviraj, (2014) “An Automatic Brain Tumor Detection and Segmentation Scheme for Clinical Brain Images”,International Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS) Vol.02, No.1, pp.37-42

Vol-3, Issue-2 , Feb- 2016]

ISSN: 2349-6495

Page | 28

when compared with the other classifiers.The would certainly enhance and help the

current diagnosis techniques.

REFERENCE Pankaj Kr. Saini (2015) “Brain

Tumor Detection in Medical Imaging using MATLAB”, International Research Journal of Engineering and Technology (IRJET)Vol.02, No.2,

N.PonNageswaran, R.Sathappan, (2015) “Tumor Detection In Brain Using

Morphological Image Processing”, Journal of Applied Science and Engineering Methodologies Vol.01, No.1,

V.Kala, Dr.K.Kavitha (2015)“Brain Tumor Extraction from MRI Images Using MATLAB”, International Journal of Advanced Technology in Engineering and Science, Vol.03, No.1,pp.453459

, Pankaj Kr. Saini (2015) “Brain Tumor and Clustering Techniques Review”, International Journal of Emerging Technology and Innovative Engineering Vol.01, No.6, pp.110

EdilyMohd. Muhd. MudzakkirMohd. Hatta, ZawZawHtikeandShoon Lei Win (2014), “Brain Tumor Detection And Localization In Magnetic Resonance Imaging”, International Journal of Information Technology Convergence and Services (IJITCS), Vol.4, No.1, pp. 1-11

Rohini Paul Joseph, C. Senthil Singh, (2014) “Brain Tumor MRI Image Segmentation and Detection in Image Processing”, IJRET: International Journal of Research in Engineering and Technology

Nidhi, PoonamKumari (2014), ”Brain Tumor and

ion using MATLAB 7.6.0.324”, International Journal of Computer Engineering and Technology, Vol.5, No.3, pp. 122-131 [8] Rajesh C. Patil, Dr. A. S. Bhalchandra (2014) “Brain Tumor Extraction from MRI Images Using MATLAB”, International Journal of Emerging Technology and Innovative Engineering Vol.02, No.1, pp.1-4

Gayathri Devi .S MuthukumarSubramanyam, P.Raviraj, (2014) “An Automatic Brain Tumor Detection and Segmentation Scheme for Clinical Brain Images”,International Journal of Emerging Technologies in Computational and Applied Sciences (IJETCAS) Vol.02, No.1,

International Journal of Advanced Engineering Research and Science (IJAERS) Vol-3, Issue-2 , Feb- 2016]

ISSN: 2349-6495

www.ijaers.com Page | 29

[9] Arun Bansal, Geetika Gupta, Rupinder Kaur, Munish Bansal (2014) “Analysis and Comparison of Brain Tumor Detection and Extraction Techniques from MRI Images”, International Journal of Advanced Research in Electrical, Electronics and Instrumentation Engineering, Vol.03, No.11,pp. 13274-13282

[10] Gurpreet Kaur, Er. Karamjeet Singh (2014) “A Comprehensive Review of Various Medical Image Processing Techniques for MRI Images”, International Journal of Advanced Research in Computer Science and Software Engineering, Vol.04, No.5, pp. 1069-1072

[11] Dr. P.V. Ramaraju, ShaikBaji (2014) “Brain Tumour classification, Detection and Segmentation Using Digital Image Processing and Probabilistic Neural Network Techniques”, International Journal of Emerging Trends in Electrical and Electronics, Vol.10, No.10, pp. 15-20

[12] Sumitharaj.R, Shanthi.K (2014), “Segmentation of Brain Tumor from MRI Image by Improved Fuzzy System”, International Journal of Advances in Engineering & Technology, Vol.7, No.3, pp. 967-973

[13] Sangeetha.R, ShenbagaRajan.A, Sindhu.M,, SivaSankari.S, (2014) “Feature Extraction of Brain Tumor Using MRI”, International Journal of Innovative Research in Science, Engineering and Technology, Vol.03, No.3, pp. 10281-10286

[14] PrachiGadpayleand, Prof.P.S.Mahajani (2013) “Detection and Classification of Brain Tumor inMRI Images”, International Journal of Emerging Trends in Electrical and Electronics, Vol.05, No.1, pp.45-49

[15] AruMehrotra,KimmiVerma, Shardendu Singh, VijayetaPandey (2013) “Image Processing Techniques For The Enhancement of Brain Tumor Patterns”, International Journal of Advanced Research in Electrical, Electronics and Instrumentation EngineeringVol.02, No.4,pp.1611-1615