Volume 5, Issue 9, September 2019 (ISSN: 2394 – 6598)
ANALYSIS AND DETECTION OF WBC CANCER CELLS USING RANDOM
FOREST CLASSIFIER
Niranjana R1, Francy Irudaya Rani.E2, Manoj P3, Naveen Nagarajan S4, Raaja P5
1-2Assistant Professor, 3-4UG Scholar,
1-5 Department of ECE, Francis Xavier Engineering College, Vannarpettai,Tirunelveli,Tamilnadu, India.
1[email protected] , 2[email protected] , 3[email protected],4[email protected],
ABSTRACT
The stem cells which are present in the bone marrow produces the blood cells in our body. There are totally three types of blood cells presents in the blood and they are Red Blood Cells , White Blood Cells and the Platelets. From the above three classifications, White blood cells play an important role. Because it protects our body from the infection by fighting with the foreign agent. According to World Health Organisation (WHO), cancer is considered as the second leading cause of death in the World. Thus, the main scope of the project is to detect the cancer cells present in the white blood cells. The WBC Cancer cells are further divided in to two major categories. They are ALL (Acute Lympotic Leukemia), and AML (Acute Myolegenous Leukemia) both of the categories include similar symptoms diseases that may confusing in diagnosing. To avoid this confusion and produce high accuracy results, Random Forest Classifier is used.
Keywords— Microscopic image, RGB to Grey Scale, Linear Contrast Stretching, Adaptive Histogram Equalisation, Cell Nucleus Segmentation, Border Segmentation, WBC Cell Segmentation, Feature Extraction, Classifier Using Random Forest Classifier.
I. INTRODUCTION
The image processing is the form of signal processing for which the input is an image, such as a photograph or video frame. Then the output of an image could be represented as an image or the set of characteristics or the parameters related to an image. The standard signal processing techniques are applied in the images to treat the image as the two dimensional signal for the image processing techniques. Images gain much broader scopes in modern science and technologies, because of the growing importance of scientific
visualization. The example is micro array data included in genetic research.
The digital image processing is an important field in an image processing. An algorithm which is used to perform image processing on the digital images is called as the digital image processing. Comparing to the analog image processing, the digital image processing provides much wider range of algorithms to be applied to the input data and avoid some problems like noise and signal distortion during the processing. The digital image processing is particularly applicable for classification,
future extraction, pattern recognition and projection.
images are defined over two dimensions (perhaps more) digital image processing may be modeled in the form of multidimensional systems. The objective of the system to diagnosis of white blood cells cancer diseases such as Leukemia with two classes Acute Lympotic Leukemia (ALL) and Acute Myolegenous Leukemia (AML). For reducing the death mortality of the patients and to improve the recognition accuracy.
II. EXISTING SYSTEM
When the blood sample is tested with microscope, large number of lymphoblasts are detected.
The lymphoblasts could produce harmful effects like causing a lack of proportion in the blood cell count and create non-healty environment for the other cells present in the blood. Thus in the FAB method different variability and patterns of lymphoblasts are analyzed. In this system the Fuzzy C means compared with k means for image segmentation. Gabor Texture Extraction method is used to extract colour features from the images and finally extract features for the classification. Thus, the FCM clustering algorithm is the soft segmentation which has been widely used for microscopic image segmentation. And it is the method which allows the single data belongs to more then one cluster.
III. PROPOSED SYSTEM
The microscopic study of human blood has led to the conclusion that a set of methods, including microscope colour imaging, segmentation, classification, and clustering can allow the identification of patients suffering from leukaemia. Machine learning is one of the methods used in image processing for detection of blast cells. Our proposed system composed of two contributory approaches. One differentiate between M5 Acute Myeloid
Leukemia (AML), L1 and L2 Acute lymphoblastic leukemia(ALL), while the second differentiate between the remaining sub categories. We grouped our concerned diseases into two separate sets due to similar visual features that actually confuse doctors and may cause misclassification.
3.1 METHODOLOGY AND WORKING
Our proposed system composed of two contributory approaches. One differentiate between M5 Acute Myeloid Leukemia (AML), L1 and L2 Acute lymphoblastic leukemia(ALL), while the second differentiate between the remaining sub categories.
According to the doctor expectation of the input blood sample, the system goes through one of the two proposed approaches. A different set of features is computed per approach. Cascading recognition process by two approaches increase the overall system efficiency of discriminating between the diseases as stated in the experiment section.
Fig. 1 Input Image
The input image of blood sample is shon below and it will pre-processed.
Inp RG
B
Preprocessing Lin
ear
Ad apti
Cell Nuc Bor
der WB
C Feat
ure
Clas
sific
Fig. 2 Pre-Processing RGB to Grey Scale Conversion
The main purpose of preprocessing is to improve the image data that suppresses unwanted distortions or
enhances some image features. In this project first the input RGB image is converted into gray scale image.
Linear Contrast Stretching
Improvement of an image by stretching the range of intensity values is called as the linear contrast stretching. Thus the linear contrast stretching is also called as Normalization.
Adaptive Histogram Equalization
Adaptive histogram equalization (AHE) is an image processing technique used to
improve contrast in images.It is therefore suitable for improving the local contrast and enhancing the definitions of edges in each region of an image.
Border Segmentation
Extracting and improving the outline of the image is called as the border segmentation.
Cell Nucleus Segmentation
Color detection is applied on the cell mask with specified range of colors to segment nucleus mask. By simple pixel to pixel subtraction of these two masks we can easily extract an accurate mask for the cytoplasm.
Global Thresholding of an Image
The separate nucleus cells among all WBC input blood samples by using the predicted threshold value.
WBC Cancer Cell Segmentation
It is clear that the affected nucleus were indicated saperately using WBC cell segmentation.
IV. CONCLUSION
The design, development and evaluation of an automated system to accurately detect white blood cells cancer diseases. The proposed solution converts images to YCBCR color space and construct Gaussian distribution of CB and CR values. Statistical, texture, size ratio and morphological features are then computed to train classifier. Random Forest classifier is the best classifier that is able to differentiate between different types and the one which gives us the best accuracy. The system achieved 94.3 % accuracy in detecting and classifying types and sub-types.
REFERENCES
[1]. B. Manoj Kumar and N. Muthukumaran, 'Design of Low power high Speed CASCADED Double
Tail Comparator', International Journal of Advanced Research in Biology Engineering Science and Technology, Vol. 2, No. 4, pp.18-22, June 2016.
[2]. P. Venkateswari, E. Jebitha Steffy, Dr. N.
Muthukumaran, 'License Plate cognizance by Ocular Character Perception', International Research Journal of Engineering and Technology, Vol. 5, No. 2, pp. 536-542, February 2018.
[3]. N. Muthukumaran, Mrs R.Sonya, Dr. Rajashekhara and V. Chitra, 'Computation of Optimum ATC Using Generator Participation Factor in Deregulated System', International Journal of Advanced Research Trends in Engineering and Technology, Vol. 4, No. 1, pp. 8-11, January 2017.
[4]. J. Keziah, N. Muthukumaran, 'Design of K Band Transmitting Antenna for Harbor Surveillance Radar Application', International Journal on Applications in Electrical and Electronics Engineering, Vol. 2, No. 5, pp. 16-20, May 2016.
[5]. Dr. N. Muthukumaran, Dr. R. Joshua Samuel Raj, Arumugathammal. E, Karthika. N, Karthika. S, Sangeetha. M, 'Design of Underground Mine Detecting Robot using Sensor Network', International Journal of Emerging Technology and Innovative Engineering, Volume 5, Issue 7, pp.
519-524, July 2019.
[6]. Ms. A. Aruna, Ms.Y.Bibisha Mol, Ms.G.Delcy, Dr.
N. Muthukumaran, 'Arduino Powered Obstacles Avoidance for Visually Impaired Person', Asian Journal of Applied Science and Technology, Vol.
2, No. 2, pp. 101-106, April 2018.
[7]. N. Muthukumaran and R. Ravi, 'VLSI Implementations of Compressive Image Acquisition using Block Based Compression Algorithm', The International Arab Journal of
Information Technology, vol. 12, no. 4, pp. 333- 339, July 2015.
[8]. VP. Anubala, N. Muthukumaran and R. Nikitha,
"Performance Analysis of Hookworm Detection using Deep Convolutional Neural Network," 2018 International Conference on Smart Systems and Inventive Technology (ICSSIT), pp. 348-354, 2018, doi: 10.1109/ICSSIT.2018.8748645.
[9]. B. Renuka, B. Sivaranjani, A. Maha Lakshmi, Dr.
N. Muthukumaran, 'Automatic Enemy Detecting Defense Robot by using Face Detection Technique', Asian Journal of Applied Science and Technology, Vol. 2, No. 2, pp. 495-501, April 2018.
[10]. R.Pandi Selvam and V.Palanisamy “Performance of Cluster-Based Multi-Source Multicasting in Mobile Ad hoc Networks”, International Journal of Computer and Network Security (IJCNS)-Vol:2 No:7, July 2010,pp.42-46.ISSN:2076-2739.
[11]. R.Pandi Selvam and V.Palanisamy “A Cluster- Based Multi-Source Multicast Routing Protocol using genetic algorithm for Mobile Ad-hoc Networks”, IEEE and ACM International Conference on Wireless Technologies for Humanitarian Relief”, Amrita University, Kochin, Kerala on 18th – 21st December 2011. pp.393- 399. ISBN:978-1-4503-1011-6.
[12]. R.Pandi Selvam “A Study of Black Hole Attack and its Prevention Techniques in MANET”
International Journal of Computer Applications (IJCA)- Vol:162–No:8, pp.1-6, 2017. ISSN:0975- 8887.
[13]. N. Muthukumaran, 'Analyzing Throughput of MANET with Reduced Packet Loss', Wireless Personal Communications, Vol. 97, No. 1, pp. 565- 578, November 2017.
[14]. Ms. Mary Varsha Peter, Ms. V. Priya, Ms. H.
Petchammal, Dr. N. Muthukumaran, 'Finger Print Based Smart Voting System', Asian Journal of Applied Science and Technology, Vol. 2, No. 2, pp.
357-361, April 2018.
[15]. R. Sudhashree, N. Muthukumaran, 'Analysis of Low Complexity Memory Footprint Reduction for Delay and Area Efficient Realization of 2D FIR Filters', International Journal of Applied Engineering Research, Vol. 10, No. 20, pp. 16101- 16105, 2015.
[16]. Dr. N. Muthukumaran, Dr. R. Joshua Samuel Raj, Manjula. R, Pavithra. L, Nagalakshmi. T, 'Automatic Identification and Management in Parking Lot through IOT', International Journal of Emerging Technology and Innovative Engineering, Volume 5, Issue 7, pp. 539-543, July 2019.
[17]. F.M. Aiysha Farzana, Abhinaya. M. K, Mrs.Friska, Dr. N. Muthukumaran, 'Design of Button Antenna for Wireless Body Network using HFSS', Indo- Iranian Journal of Scientific Research, Vol. 3, No.
1, pp. 48-54, January 2019.
[18]. F.M. Aiysha Farzana, Hameedhul Arshadh. A, Sara Safreen. M, Dr. N. Muthukumaran, 'Design and Analysis for Removing Salt and Pepper Noise in Image Processing', Indo-Iranian Journal of Scientific Research, Vol. 3, No. 1, pp. 42-47, January 2019.
[19]. Pamina, J., et al. "An Effective Classifier for Predicting Churn in Telecommunication." Jour of Adv Research in Dynamical & Control Systems 11 (2019).
[20]. A.Srinithi, E.Sumathi, K.Sushmithawathi, M.Vaishnavi, Dr. N. Muthukumaran, 'An Embedded Based Integrated Flood Forecasting through HAM Communication', Asian Journal of
Applied Science and Technology, Vol. 3, No. 1, pp.
63-67, January 2019.
[21]. F.M.Aiysha Farzana, Hameedhul Arshadh. A, Ganesan. J, Dr. N. Muthukumaran, 'High Performance VLSI Architecture for Advanced QPSK Modems', Asian Journal of Applied Science and Technology, Vol. 3, No. 1, pp. 45-49, January 2019.
[22]. Banumathi.A, Banupriya.A, Niranjana.R, Jayaraman.G, Dr. N. Muthukumaran, 'Advanced Illumination Measurement System in Highways', Asian Journal of Applied Science and Technology, Vol. 3, No. 1, pp. 39-44, January 2019.
[23]. N. Muthukumaran and R. Ravi, 'Hardware Implementation of Architecture Techniques for Fast Efficient loss less Image Compression System', Wireless Personal Communications, Volume. 90, No. 3, pp. 1291-1315, October 2016.
[24]. N. Muthukumaran and R. Ravi, 'The Performance Analysis of Fast Efficient Lossless Satellite Image Compression and Decompression for Wavelet Based Algorithm', Wireless Personal Communications, Volume. 81, No. 2, pp. 839-859, March 2015.
[25]. M. Ruban Kingston, N. Muthukumaran, R. Ravi, 'A Novel Scheme of CMOS VCO Design with reduce number of Transistors using 180nm CAD Tool', International Journal of Applied Engineering Research, Volume. 10, No. 14, pp. 11934-11938, 2015.
[26]. HardikPandit, Dipti Shah, ―The Model for Extracting a Portion of a Given Image Using Color Processing‖, International Journal of Engineering Research & Technology, Vol. 1 Issue 10, December- 2012.
