Enhancing acute leukemia classification through hybrid fuzzy C means and random forest methods

Leukemia is a category of cancer that is normally found in blood and bone marrow, and which causes rapid abnormal development in the making of white blood cells than the required amount. The produced white blood cells could be ineffective to fight against harmful infections and can even prejudice or restrict the capability of the bone marrow to generate red blood cells and blood platelets. If this is not diagnosed in the earlier stage, it may start to affect the function of the internal organs and cause death. Normally, entire blood counts image analysis and diagnosis are done manually which is an inaccurate and time-intensive process. In this proposed method the classification is tested with two Machine Learning algorithms which are Hybrid Fuzzy C Means (FCM) and Random Forest algorithm (RF) and Support Vector Machine for the detection and classification of Acute Leukemia disease and their performance was evaluated. The dataset comprised of 8637 images which included infected images, normal images and augmented images from different dataset providers and RGB to CMYK conversion with histogram equalization is applied for pre-processing, K means for Image Segmentation. Experimental results convey that Hybrid FCM and RF Algorithm attained an accuracy of 99.06 %, a sensitivity of 99.4 %, and a specificity of 97.8 % respectively, and the ROC (Receiver Operating Characteristic) curve shows that the result produced by the Hybrid FCM & RF based Classifier is best suitable in diagnosing the classification of the Acute Leukemia disease. The tool used for developing the proposed method was Matlab R2018 software.