Leukemia or blood cancer is caused due to cancer of blood forming tissues by large number of abnormal increase in white blood cells in bone marrow. According to the predominant type of white blood cells, the course of disease is classified. The major classification of leukemia are acute and chronic leukemia. Acute leukemia gets worse very fast whereas chronic leukemia gets worse slowly. Leukemia can be subdivided based into type of blood cells affected. If cancerous transformation affects lymphocytes, it is lymphocytic/ lymphoid leukemia and if it produces red cells, platelets and other white blood cells, it is myeloid / myelocytic leukemia. Hence acute and chronic leukemia are subdivided as Acute Lymphoid Leukemia (ALL), Acute Myeloid Leukemia (AML), Chronic Lymphoid Leukemia (CLL), Chronic Myeloid Leukemia (CML). The classification can be done by using a machine learning classifier called SVM (Support Vector Machine) classifier. This paper analysis the types of blood cancer by using the blood smear images of healthy and leukemic people with help of image processing techniques.

Diagnosis of Leukemia and its types Using Digital Image Processing Techniques

Leukemia, the malignancy of blood-forming tissues, becomes fatal if not detected in the early stages. It is detected through a blood smear test that involves the morphological analysis of the stained blood slide. The manual microscopic examination of slides is tedious, time-consuming, error-prone, and subject to inter-observer and intra-observer bias. Several computerized methods to automate this task have been developed to alleviate these problems during the past few years. However, no exclusive comprehensive review of these methods has been presented to date. Such a review shall be highly beneficial for novice readers interested in pursuing research in this domain. This article fills the void by presenting a comprehensive review of 149 papers detailing the methods used to analyze blood smear images and detect leukemia. The primary focus of the review is on presenting the underlying techniques used and their reported performance, along with their merits and demerits. It also enumerates the research issues that have been satisfactorily solved and open challenges still existing in the domain.

https://dl.acm.org/doi/pdf/10.1145/3514495

Automated Analysis of Blood Smear Images for Leukemia Detection: A Comprehensive Review

Various types of algorithms have been widely used for image segmentation in digital image processing. Every algorithm has features that make it unique to be applied to specific cases. One of the applications of image segmentation is to detect white blood cells. Certain objects such as blood cells must be able to be well segmented because their existence is very crucial to support the accuracy of disease detection related to haematology or the branch of medical science that studies the morphology of blood and blood-forming tissues. Three image segmentation algorithms were compared through this study: Seed Region Growing, Otsu Thresholding and Active Contour Without Edge. Comparative analysis of the three algorithms was done by counting the number of white blood cell objects that were successfully segmented with the actual number of cells that were counted manually. A total of 30 images of blood smears were taken from people suffering from acute myeloid leukemia M1. The average accuracy values from each algorithm were used to determine which image segmentation algorithm is the most suitable for application in the case of white blood cells segmentation. The results showed that Active Contour Without Edge is the most appropriate among the other algorithms

/pdf/a-comparative-study-of-digital-image-segmentation-algorithms-1kajkcwt3t.pdf

A Comparative Study of Digital Image Segmentation Algorithms for Acute Myeloid Leukemia M1 White Blood Cells Images

Leukemia is a blood cancer caused by a rise in the number of white blood cells in your body. Those white blood cells crowd out the red blood cells and platelets that your body needs to be healthy. The extra white blood cells don’t work right. However, the macroscopic examination of human blood necessitates various microscopic techniques, including color imaging, segmentation, and clustering, to distinguish patients with the disease. The white blood cell count can be higher than normal and prevent the immune system from functioning properly. The most reliable method to detect leukemia is with the assistance of a microscope. Automation of this form of Leukemia diagnosis is required because fewer and more expensive precise tests are required than the above. Blood slides don't reveal the findings because of hematologists' combined experience and tiredness, and those results can vary significantly from one PSO to another. As it is reasonably inexpensive and effective, blood-stained histopathology imaging to test for leukemia is a low-cost and innovative choice. The fuzzy-c segmentation coefficients of this paper are compared to those for image segmentation k. Using the GLCM to separate color characteristics from photographs performs better precision than using Fuzzy-classifications. Fuzzy's consistency level is 96%, while sharpness is 83% CNN is mainly a television outlet. The whole project has been done using the MATLAB toolkit.

CML: Chronic Myeloid Leukemia Detection Using Particle Swarm Optimization and Fuzzy C-Means Clustering

In present scenario, imaging in act an important role throughout the integrated medical process from indicative and find out about diseases through studies. Considering most of the imaging techniques have gone directly digital, with unceasingly increasing perseverance, these medical image processing has to confront many upcoming challenges from broad data measures. In our paper we describe the process of analysing cancer cell and how image processing is helpful and immensely important in medical science. The paper analyse and discover bacteria under blood cells through its rate of growth of bacteria in blood with the help of object recognition technique of image processing by getting the image through microscope. This work presents an precise way of static image processing technique of object recognition for detection and prognosis of cancer cell. This method used for diagnosis of abnormal growth of cells in any body part using blood cell image. This procedure include artificial expert system techniques, such as machine learning, artificial neural network, and fuzzy logic with medical imaging techniques. We subsist blood images as input for our expert system to analyse and detect the classification of growth of abnormal cell through static image processing technique. This paper presents another technique of image processing as pattern recognition for analysis and classification of cancer cells using microscopic blood cells images..The proposed method achieved sensitivity of 80%. specificity of 91.04% and accuracy of 96.4%.

/pdf/an-artificial-system-for-prognosis-cancer-cells-through-47m0m5cvb2.pdf

An Artificial System for Prognosis Cancer Cells through Blood Cells Images using Image Processing

The machine-controlled identification of malignant cells from microscopic diagnostic assay pictures of blood samples helps in assuaging the diagnostic problems of leukemia and provides higher results if the biologically explainable and clinically important feature primarily based approaches are used for the identification of malignancy and the severity of the disease. Identification method might have error rates up to 40%; Due to this drawback it is necessary to develop a second opinion tool which helps the doctors and pathologists in a classified detection of the leukemia disease. The analysis shows a discourse method for leukemia and its subtypes detection from microscopic blood cell images which can be done by applying image processing techniques followed by a detailed classification analysis on the dataset images.

Sachin Deshpande

Papers

Computer aided leukemia detection using digital image processing techniques