FAB Classification based Leukemia Identification and prediction using Machine Learning

Background and Objective: Leukemia identification, detection, & classification has erupted an intriguing field in medical research. Several methodologies are convenient in theprevious work to detect five types WBCs (lymphocytes, eosinophils, monocytes, neutrophils, and basophils). Single cell Blood's smear images used for experiment. Propounded method is used for leukemia recognition, uncovering and distribution based on FAB classification. Methodology: This propounded task has developed French-American and British (FAB) classification-based detection module on blood smearimages (BSIs). Methods like pretreatment, segmentation, feature extraction, distribution are used in detection method. The Propounded algorithm-based propounded model is used for segmentation, which is combination of the segmented results of the Linde-Buzo-Gray (LBG) algorithm, Adaptive canny used for edge identification and Hysteresis and watershed algorithm used for thresholding. The shape, texture features, color of segmented image are picked by neural network and classification is performed by Support Vector Machine (SVM) and prediction by Naïve Bayes Classifier (NBC). Result: Dataset-master and Cellavison dataset is being used for the experimentation. The BSIs are considered for the Evaluation based on ROC curve analysis metrics like TPR, TNR and accuracy. Our propounded solution obtains superior classification performance in the given dataset. The suggested classifier enhanced the classification average accuracy to 99.06% and Mean Square Error (MSE) is 0.0407. Conclusion: The enhanced accuracy had achieved by enhancing performance and classification with comparison with some other methods.