Disease Identification using WBC Count Project propose to form a process that can help in disease identification during blood test with minimum human involvement and that can produce optimum result.The proportion of counts of different types of white blood cells in the bone marrow, called differential counts, provides invaluable information to doctors for diagnosis.
Due to the tedious nature of the differential white blood cell counting process, an automatic system is preferable. In this paper, we investigate whether information about the nucleus alone is adequate to classify white blood cells. This is important because segmentation of nucleus is much easier than the segmentation of the entire cell, especially in the bone marrow where the white blood cell density is very high. In the experiments, a set of manually segmented images of the nucleus are used to decouple segmentation errors.
We analyze a set of white-bloodcell- nucleus-based features using mathematical morphology. The classification performances are evaluated by two evaluation measures: traditional and classwise classification rates. Furthermore, we compare our results with other classifiers and previously proposed nucleus-based features. White blood cells in bone marrow are classified according to their maturation stages. When a white blood cell becomes older, its size, the size and shape of the nucleus, and many other characteristics change. White blood cells in the myelocytic or granulocytic series can be classified into six classes, i.e., myeloblast, promyelocyte, myelocyte, metamyelocyte, band, and polymorphonuclear (PMN) in that order from the youngest to the oldest cells. Three samples of each class are shown to illustrate the possible variation within each class.
• We propose a method for the classification of white blood cells using only their nucleus information. This idea is very useful in practice because one of the difficulties in the differential counting in bone marrow is how to deal with the cells that touch each other.
• This problem occurs frequently in cells of the bone marrow because there the white blood cells are very dense. If the cell classification is based only on the information about the nucleus, then we do not need to segment the entire cell, and only nucleus segmentation is adequate.
• Although many techniques have been applied to cell segmentation, this problem is not solved, especially in touching cells.
• In this system we take a image of the blood sample taken for analysis.
This image is then changed in jpg format.The image is then changed into black and white image to get more contrast.
Using boundary fill algorithm we can color the boundary of different kind of cells present in that sample picture.
After that number of wbc cells can be found.That is called wbc count .
HARDWARE AND SOFTWARE REQUIREMENTS
The minimum hardware required for the development of the project is:
1) Processor : Pentium 4
2) Hard disc :40 GB
3) RAM : 256 MB
4) Monitor : 15’’VGA color
1) Operating system : windos XP professional
2) Front end : microsoft visual studio.net
3) Coding language : visual C#.Net
The project is divided into following four modules.They are:
1) Input and preprocessing module
2) Segmentation module
3) Classification module
4) Disease detection module
All four modules and their specifications are written below:
1) Input and preprocessing module : • First of all we have to give all necessary detail of patient like name,age,sex and blood group. • This module is to convert the blood sample into grayscale image. Why because we need a common color to detect the edges of cells. • After the grey scale conversion, the grey scaled image is given for noise removal.
2) Segmentation module: • Segmentation module for finding edges of the white blood cell and find detect the six stages of nucleus from the white blood cell.This is done with the help of canny detector.
3) Classification module: • This module is to compare the input blood sample with the trained blood sample. This module also helps us to classify the white blood cells. Here we compare the edges of nucleus in the input sample with the edges of nucleus in the trained sample to identify the stage of WBC and count of each stage
4) Disease detection module: • This module is to detect the disease of the given blood sample. The input is the count of each stage of WBC in the given blood sample.
White blood cell is an important constituent of blood.In this project at first step blood sample image is taken and that undergoes for grayscale conversion.before that patient id is created.The grayscale image is removed with noise and then we use canny detector method for detecting the edeges of cell.Binerization of cell is done before canny detection.after edge detection wbc cells are counted and report is generated.The final report is then shown.
Hence we achieved the objective and successfully developed a process that helps in counting wbc with minimum human involvement.