Computer Assisted Detection And Counting For Diagnosis Of Blood Cancer
Author(s):
M.Shakunthala , P.Nandhini, B.Pooja Harini
Keywords:
Leukemia classification, White blood cell count, Watershed segmentation, SVM,KNN and CNN classifiers.)
Abstract
Leukemia is a type of cancer which damages blood and bone marrow .It can be fatal illness if not diagnosed at earlier stage .Typically complete blood count(CBC) or morphological image analysis is employed to manually diagnose the malignant neoplastic disease cells .These ways are time consuming and fewer corrective measures has to be taken. In this paper it is planned for the detection of acute lymphocytic leukemia (ALL), acute myeloid leukemia (AML),chronic lymphocytic leukemia(CLL), chronic myeloid leukemia(CML)by microscopic blood image analysis. Initially various kinds of cells are separated from the image i.e white blood cells, red blood cells and platelets and then lymphocytes are separated from white blood cells. Watershed segmentation is performed to separate grouped lymphocytes for counting of cells. After that form and colour options are extracted from these lymphocytes and given to SVM ,KNN and CNN classifiers to classify into traditional and blast cells. Counting of the WBCs is also done for accurate diagnosis. This type of malignant neoplastic disease detection system is found to be more practical , fast and accurate as compared to manual method.
