Image Processing Based Abnormal Blood Ells Detection

International Journal of Image, Graphics and Signal Processing, 2018

The aim of our work is to obtain a maximum rate of recognition of abnormal (cancerous) blood cells. We propose the development of a system based on kmeans methods, after an RGB channel decomposition by applying the algorithm which can segment our microscopic medical images. It turns out that the proposed system shows better segmentation and classification for the identification and detection of leukemia. The experimental results obtained are very encouraging, which helps hematologists to monitor the evolution of cancerous blood cells and make a good diagnosis.

International Journal of Engineering Research and, 2020

Analysis of blood smear is an important diagnostic test used in the diagnosis of an array of diseases. The method of automatic diagnosis of microscopic blood smear images by identifying and separating it to different categories of cells that are highlighted in the paper. Automation of this process ultimately narrows the scope of possible diseases saving a considerable amount of time. Identification of red blood cells (RBCs) is carried out/done by the system using different techniques of image processing operations like pre-processing, operations for morphology, labelling and extraction of features to calculate shape and size of the RBCs. Morphological properties can provide information regarding shape of the cell. By these operations and calculations, RBCs are classified. There are 2 stages in red cell classification process, first is the separation of RBCs to normal and abnormal followed by abnormal cells classification to three subclasses based on the cell shape and structure. The aim of this system is to assist pathologist by giving quick results by analysing the smear samples. The cure of these diseases is possible, when it is detected at an earlier stage.

2020

At present, the process of separating normal and abnormal red blood cells was carried out through laboratory testing, which often requires a lot of time and cost. Therefore, this paper presents an abnormal red blood cell detection scheme to make it easier to diagnose a disease, speed up the identification process so that it saves time and money. Because without having to go through a chemical process, which processes one by one so that it slows down the time of identification and uses high costs, the method proposed in this paper was to calculate the number of normal and abnormal blood cell objects using the digital image processing method using Matlab. This study could not only determine normal and abnormal blood cells using a feature extraction method based on shape. The impact of this study was to create a system to separate blood cells that have collided before the process of detecting the form and calculation of the number of normal and abnormal red blood cell objects in an image of a blood cell.

Advances in Intelligent Systems and Computing, 2021

Blood cancer or leukemia is the cancer which leads to abnormal formation of white blood cells in the blood by the blood marrow; it can be fatal disease if not diagnosed early. It can be detected and diagnosed at the earliest by using the image processing of microscopic images of blood cell. This method is cheap and very fast and accurate. This technique is currently being used in the hospitals to detect blood cancer of all types. In this paper, a method is prepared in which the white blood cells are separated from blood and its color, textural, geometrical features are extracted and fed into different types of classifiers like SVM, LDA, etc. These classifiers are used to detect whether cells are healthy or cancerous. To improve the accuracy of detection, we have checked the detection without principal component analysis (PCA) and also with PCA. Further, if cancer is detected, then KNN classifier is used to detect the type of the cancer. The counting of white blood cells is also done to make the method more accurate. This automated method is found to be highly accurate, fast, and cheap as compared to manual detection.

Advances in Intelligent Systems and Computing

In current times, pathologists visually inspect blood cell images under the microscope for the purpose of identifying blood disorders. Identified blood disorders are classified into several blood diseases. Our work aims at studying and designing a model (framework) for the detection of leukemia (blood cancer) and its types using microscopic blood sample images and analyzing them for diagnosis at an earlier stage. Earlier, hematologists used to visually inspect the microscopic images, thereby making the diagnosis process error-prone and time-consuming. However, the use of newly developed automatic image processing systems manages to successfully overcome most of the visual inspection related drawbacks. The early diagnosis of blood cancer will greatly aid in better treatment. In this process, the acquired dataset images are taken as inputs and the images are sent through different image processing techniques such as image enhancement (preprocessing), segmentation, feature extraction and classification. The method proposed is applied to a large number of images of varying quality and is found to provide satisfactory results.

In this paper, we present a segmentation method by thresholding for automated leukemia detection. This paper deals with the segmentation and threshold of blood cells for the purpose of detecting leukemia (abnormal blood cells). After the image acquisition and the preprocessing step, we proceeded to the application of the segmentation implemented in ImageJ. In order to show the interest of the proposed approach, we present the different cancerous regions identified with their characteristics for biomedical diagnostic aid. The proposed system is tested on image dataset and 96,63 % accuracy is achieved. The proposed system is successfully implemented in ImageJ, with the obtained experimental results are very encouraging.

International Journal for Research in Applied Science and Engineering Technology IJRASET, 2020

A complete blood cell count or CBC is considered as an important test in medical diagnosis to evaluate the overall health of a patient. Red Blood Cell count plays a vital role in identifying a person's health condition. The conventional method of blood counting is done manually by placing the blood smear under microscope that requires the skill of a pathologist. This manual counting of blood cells can lead to erroneous results and medical labouratory technicians are put under stress. The development of image processing technique and computer aided system will help to obtain precise results in less amount of time.

2020

Microscopic images of blood smear primarily contains RBCs, WBCs and Platelets, blood count is generally monitored by laboratory test known as CBC i.e. complete blood count, the major cellular component of blood is RBC, which is responsible for gaseous exchange and avails the oxygen for all the organs. In normal physiological conditions, front view and side view of RBC provide circular and biconcave images respectively. In blood borne diseases, generally there is variation in size, shape and in area with respect to normocytic RBCs. Especially in sickle cell anemia which is genetic blood disorder disease, the RBCs after de-oxygenation holds a sickle shape, which as a result causes many diseases. The purpose of this paper; use of Image processing techniques in finding the number of abnormal shaped cell; primary focus is in sickle shaped RBCs in the blood smear image and calculate its percentage and thus highlight the possibility of sickle cell anemia. Early, easy, fast and accurate det...

Leukemia is diagnosed with complete blood counts which is by calculating all blood cells and compare the number of white blood cells (White Blood Cells / WBC) and red blood cells (Red Blood Cells / RBC). Information obtained from a complete blood count, has become a cornerstone in the hematology laboratory for diagnostic purposes and monitoring of hematological disorders. However, the traditional procedure for counting blood cells manually requires effort and a long time, therefore this method is one of the most expensive routine tests in laboratory hematology clinic. Solution for such kind of time consuming task and necessity of data tracability can be found in image processing techniques based on blood cell morphology. This study aims to identify Acute Lymphocytic Leukemia (ALL) and Acute Myeloid Leukemia type M3 (AML M3) using Fuzzy Rule Based System based on morphology of white blood cells. Characteristic parameters witch extractedare WBC Area, Nucleus and Granule Ratio of white blood cells. Image processing algorithms such as thresholding, Canny edge detection and color identification filters are used.Then for identification of ALL, AML M3 and Healthy cells used Fuzzy Rule Based System with Sugeno method. In the testing process used 104 images out of which 29 ALL-Positive, 50 AML M3-Positive and 25 Healthy cells. Test results showed 83.65 % accuracy .

In many medical applications, computer vision is required to step behind the image preprocessing level and perform recognition tasks without human interaction. We focused our work on blood tests for leucocyte detection and counting. This test is generally performed manually and required for infection diagnosis. We developed a method for cells classification and counting using images from a laboratory microscope. This is a step forward for the automation of laboratory tests, producing good results without supervision and interaction. A camera calibration is required for the precise determination of the leucocyte formula.