An Integrated Design Based on Dual Thresholding and Features Optimization for White Blood Cells Detection

Abstract

White blood cells (WBC) are an important component of the immune mechanism, as they protect the human body from parasites, viruses, fungi, and bacteria. The number of blood cells provides significant information related to infections such as AIDS, leukemia, deficiencies of immune and autoimmune infections. To heal an infection on time, it is critical to recognize it early on. Therefore, a method is proposed to accurately segment and classify WBC at an early stage. The RGB image is converted into HSV after which dual thresholding is applied to the saturation component to segment WBC. The 1000 features are extracted from Alexnet to FC8 layer, the Logits layer is selected for feature extraction from mobilenetv2, the node_202 layer is utilized to extract the features from the shuffle net, and the FC1000 layer is chosen from the Resnet-18 model. Four feature vectors are obtained from transfer learning models; these feature vectors are combined serially and create the final optimized vector by a non-dominated sorting genetic algorithm (NSGA). The classification results are investigated on the fusion of Alexnet, shuffle net, Resnet-18, mobilenetv2, and the fusion of mobilenetv2, shuffle net, and Resnet-18 whereas mobilenetv2 features are fused independently. The final optimized feature vector is passed to classifiers including Naïve Bayes (NB), Decision tree (DT), Ensemble, Linear Discriminant Analysis (LDA), Support vector machine (SVM), and K nearest neighbor (KNN) to classify WBC. The method is tested on three publicly available datasets as LISC, ALL_IDB1, and ALL_IDB2. The method achieved the maximum of 1.00 accuracy to classify the blast/non-blast cells, 0.9992 accuracy on Basophil cells, and 1.00 accuracy on Lymphocyte, Neutrophil, Monocyte, Eosinophil, and mixture of these cells. When compared to existing modern approaches, the proposed method produces better outcomes.