Detection of Sickle Cells using Image Processing

IJSTE - International Journal of Science Technology & Engineering | Volume 2 | Issue 09 | March 2016 ISSN (online): 2349-784X Detection of Sickle Cells using Image Processing Prof. I.A. Chintawar Professor Department of Electronics Engineering Rashtrasant Tukdoji Maharaj University, Nagpur Aishvarya Mishra Department of Electronics and Communication Rashtrasant Tukdoji Maharaj University, Nagpur Pravin Narnaware Department of Electronics Engineering Rashtrasant Tukdoji Maharaj University, Nagpur Chetan Kuhikar Department of Electronics Engineering Rashtrasant Tukdoji Maharaj University, Nagpur Abstract In this paper, Sickle cell anaemia a blood disorder resulting from the abnormalities of red blood cells characterized by presence of abnormal cells like sickle cells, ovalocyte, anisopoikilocyte. Patients suffering from this disease experience acute pain and infection in addition to other chronic conditions like anaemia, cardiac, pulmonary and brain complication. Different digital IMAGE PROCESSING techniques for identification of shape and size of cells present in blood. It has been shown that using MATLAB the image can be processed into different stages as edge detection, segmentation, classification and sickle detection finally leading to a successful outcome. Keywords: Anaemia, Sickle Cells, MATLAB, image processing ________________________________________________________________________________________________________ I. INTRODUCTION Sickle cell anaemia is one of its kind generally caused by abnormalities in R.B.C’S. Sickle cell disease usually presenting in childhood, occurs more commonly in people from parts of tropical and subtropical regions where malaria is or was very common. A healthy RBC is usually round in shape. But sometimes it changes its shape to form a sickle cell structure; this is called as sickling of RBC. An image processing algorithm to automate the diagnosis of sickle-cells present in thin blood smears is developed. Images are acquired using a charge-coupled device camera connected to a light microscope. Clustering based segmentation techniques are used to identify erythrocytes (red blood cells) and Sickle-cells present on microscopic slides. The cellular part of blood molecule contains several different cell types. One of the most important and the most numerous cell types are red blood cells. The other cell types are the white blood cells and platelets. Anemia is the most common disorder of the blood. “Anemia”, the name is derivative from the ancient Greek word anaimia, which means “Lack of Blood”. It is possible because of reduction in Red Blood Cells (RBCs) or resulting in lesser than normal quantity of haemoglobin in the blood. In this paper detection of sickle cells using microscopic images is done with the help of image processing. Block Diagram: Fig. 1: Stages of Processing the Microscopic Image. All rights reserved by www.ijste.org 335 Detection of Sickle Cells using Image Processing (IJSTE/ Volume 2 / Issue 09 / 063) II. MATLAB MATLAB is the most widely used engineering program in several areas with regard to engineering, calculations and simulation, image processing, and other functions as this program is used for academic purposes, especially for scientific research purposes. MATLAB covers many industries (such as aerospace and defense, automotive, biotechnology treatment, medicines, and medical industries, telecommunications. Developing a computer-based information system using image processing techniques that need to use well-supported programming environment which has wide range of functions in digital image processing, so in this work, MATLAB version 7.10.0.499 has been used. There are many functions in MATLAB which help in developing image processing systems such as (imread, rgb2gray, imadjust, im2bw, bwareaopen, bwboundaries, and impixel).see table (2.2) Table - (2.2) Some of MATLAB Functions. (Natick, 2010) Image Processing Techniques: Image processing is one of the branches of computer science, its task is focused on performing certain processing on images in order to enhance them or extract certain types of information, according to already predetermined criteria. Traditional image processing techniques consisted of six sequential steps, which are: image acquisition, pre-processing, segmentation, feature extraction, classification, and finally image understanding. Image processing techniques have many applications; however, in this work it is found that biomedical image processing is used to develop a system that helps improving anemia Diagnosis. Abnormal Morphology of RBCs: when assessing RBCs in the blood film five major features should be taken into consideration. These include: RBC size, color or hemoglobin content, shape, presence of intracellular. Nevertheless, changes in other cell lines can also help in the diagnosis of the precise type of anemia. Before discussing the above features, it’s worth knowing that in most individuals RBCs are 7.2 μm in diameter (Turgeon, 2012), round biconcave in shape, normocytic, normochromic cells without intracellular inclusions, lying side by side in the blood smear. Note that red cell morphology must be scanned in a good counting area (Hoffbrand, Moss, 2011). 1- Red blood cells size: while examining the RBCs for their size, one can compare the size of RBCs to the size of nucleus of a small lymphocyte. RBCs that are larger or smaller than the size of the nucleus may be macrocytic or microcytic, respectively. Nonetheless, it’s the value of MCV that make the precise decision of the RBC’s size. The average size of an RBC is 7.2 μm with a range of 6.8 to 7.5 μm. - Normocyte: normal size of RBC. - Macrocyte: larger than the normal RBC (>8.2 μm) - Microcytic: smaller than the normal RBC, <7.2 μm.This is detected by elevated RDW in RBC indices. 2- Color or hemoglobin content: after examining the size, Hemoglobin content should be checked. A normal erythrocyte has a pinkish-red color with a slightly lighter-colored center (central pallor) when stained with a blood stain, such as Wright, Leishman, Giemsa stain or other stains. Under normal conditions, when the color, central pallor, and hemoglobin content are All rights reserved by www.ijste.org 336 Detection of Sickle Cells using Image Processing (IJSTE/ Volume 2 / Issue 09 / 063) proportional, the erythrocyte is referred to as normochromic. Cells with decreased hemoglobin content or increased central pallor arereferred to as hypochromic. 3- Inclusions: the next to be examined is RBC inclusions. There are several inclusions that can be seen in erythrocytes: (Hoffbrand, Moss, 2011) - Basophilic stippling: are tiny, blue granules, which are composed of RNA residues, diffusely distributed throughout the RBC. This is especially common in lead poisoning. - Howell-jolly bodies: Is round dark- staining nuclear remnants. Their presence implies defective splenic function or a maturation defect. - Reticulcyte: increasing red blood cells production is caused by younger enucleate red blood cells containing very small amount of RNA which are released from bone marrow respond to an anemia. Image Acquisition: The image is first acquired from a live video feed or an existing image can be loaded from the memory. We shall consider that the acquired image is in RGB format which is a true color format for an image. In MATLAB, the captured or imported RGB image is three dimensional and each pixel is represented by an element of a matrix whose size corresponds to the size of the image. Fig. 2: RGB image of blood smear. Creating Gray Scale Image: The image of blood smear had been taken by photomicroscope which is colored, but in some of the coming next phases for the system is handled with 2-dimintion images (that only includes gray scale), so the image should be converted to gray scale. The function: Grayscale-image=rgb2gray (image-name); Fig. 3: Gray scale image after using function(rgb2gray) All rights reserved by www.ijste.org 337 Detection of Sickle Cells using Image Processing (IJSTE/ Volume 2 / Issue 09 / 063) Image Enhancement: Processing an image so that the result is more suitable for a particular application. i.e. sharpening or de-blurring an out of focus image, highlighting noise. Increase the contrast of the image. Enhance color difference between background and objects that will be useful in extracting the objects boundary. Preprocessing: In order to process the image in an efficient manner the test image Fig. is converted from RGB to Gray scale. A set of processes is used in data preparation and filtering to remove the noise. An intelligent implementation is used to make it ready for later analysis later with the aim to automate cognition of the image and its content without human help. The techniques used at this phase are different according to the nature of information needed to be extracted from the image. Fig. 4: Gray scale of RGB image. Stage of segmentation: Edge Detection Edge detection is then carried out to mark the border of each cell body using Matlab toolbox [13,14,15]. Fig shows the RBCs and Sickle Cell Preset in a small segment of Edge detected image Fig. 5: Shape Detection: The shape of Sickle cell is marked in the image by a red circle and hence can identify the number of sickle cell present in the image. Also the mean radius of each cell is calculated. Generally when parasite attacks the RBC, they deform the structure of the cell which no longer remains circular. The distance of each pixel from the centre of mass of the each cell body is calculated and the range of radii value is noted. Image Segmentation: Thresholding –based on histogram characteristics of pixel intensities of image. Morphological Operation –Continuity based techniques which involve the processing of shapes, to segment the red blood cell images. Colour Image segmentation –allow more reliable image segmentation than greyscale images and applying of hue feature. All rights reserved by www.ijste.org 338 Detection of Sickle Cells using Image Processing (IJSTE/ Volume 2 / Issue 09 / 063) Model-based contour tracing –to overcome the problem of automatically segmenting a Scanning Electron Microscopic image of red blood cells that have high number of overlapping cells and relatively smooth contour. Result: Lastly after developing computer-based information, the results will be computed and represented which aimed to enhance blood anemia diagnosis, so the main results consist of into three main points: 1) Classifying each cell alone: the system classifies cells after extracting properties and examining them in 12th kinds we have studied. 2) Computing the number of cells for each kind: system counts number of cells for each kind alone which helps counting percentages. 3) Computing the percentage of cells number: depending on cells number that were examined and classified and the number of cells in each kind, this system counts the percentage of each kind depending on the whole number of cells that were examined. The characteristic of this system is that it supports the property of varied photos personification which also helps in results punctuality and giving clear, useful results to anemia disease. REFERENCES Silpa shaju;Prof G.K.Sadanandan in 2016 “Sonar image processing technique for reducing noise”. Hamghalam M, Motameni M & Kelishomi A in 2009 “Leukocyte segmentation in giemsa-stained image of peripheral blood smears based on active contour”. [3] Hirimutugoda, Y.M. Wijayrathna in 2010 “Image analysis system for detection of red cell disorder using artificial neural networks”. [4] Bruza, P. D., & Van der Weide, Th. P. (1993). The Semantics of Data Flow Diagrams, University of Nijmegen. [5] Diggs, L. Sturm, W. D. & Bell, A. (1985). The Morphology of Human Blood Cells. Abbott Park, IL: Abbott Lab. [6] Gonzal, R.C. & Wood, R. E. (2002).Digital Image Processing Using MATLAB.Prentice Hall. [7] Natick, M. A. (2009) “image processing toolbox”, the Math works, Inc.3 Apple Hill Drive. [8] Liao, Q. & Deng, Y. (2002).An Accurate Segmentation Method for White Blood Cell Images. InProc. IEEE Int. Symp.Biomed.Imag., Washington, DC, 245–248. [9] Chen, P. Yan, X. &Zheng C. (2006) .Recognition of Blood and Bone Marrow Cells using Kernel-based Image Retrieval. IJCSNS International Journal of Computer Science and Network Security .6:29-34. [10] Hirimutugoda, Y.M. &Wijayarathna, G. (2010).Image Analysis System for Detection of Red Cell Disorder Using Artificial Neural Networks. Journal of Biomedical Informatics, Sri Lanka vol.1, no 1, 35-42. [1] [2] All rights reserved by www.ijste.org 339