Classification of lymphocytes, monocytes, eosinophils, and neutrophils on white blood cells using hybrid Alexnet-GoogleNet-SVM

• Published in: SN applied sciences 2021-04, Vol.3 (4), p.503, Article 503
• Main Authors: Çınar, Ahmet, Tuncer, Seda Arslan
• Format: Article
• Language: English
• Subjects: Accuracy; Algorithms; Applied and Technical Physics; Artificial neural networks; Blood; Chemistry/Food Science; Classification; Datasets; Deep learning; Discriminant analysis; Earth Sciences; Engineering; Engineering: Digital Image Processing; Environment; Eosinophils; Feature selection; Identification systems; Immune system; Infectious diseases; Leukemia; Leukocytes; Leukocytes (basophilic); Leukocytes (eosinophilic); Leukocytes (neutrophilic); Lymphocytes; Machine learning; Materials Science; Model accuracy; Monocytes; Morphology; Neural networks; Neutrophils; Research Article; Support vector machines
• ISSN: 2523-3963; 2523-3971
• DOI: 10.1007/s42452-021-04485-9

White blood cells (WBC), which form the basis of the immune system, protect the body from foreign invaders and infectious diseases. While the number and structural features of WBCs can provide important information about the health of people, the ratio of the subtypes of these cells and observable deformations are a good indicator in the diagnostic process. The recognition of cells of the type of lymphocytes, neutrophils, eosinophils, basophils and monocytes is critical. In this article, Deep Learning based Hybrid CNN (Convololutional Neural Network) model is proposed for classification of eosinophils, lymphocytes, monocytes, and neutrophils WBCs. The model presented is based on pretrained Alexnet and Googlenet architectures. The feature vector in the last pooling layer of both CNN architectures has been merged, and the resulting feature vector is classified by the Support Vector Machine. To determine the superiority of the proposed method, the classification was also performed and compared using pretrained Alexnet and Googlenet. Hybrid Alexnet-Googlenet-SVM model provides higher accuracy than pretrained Alexnet and Googlenet. The proposed method has been tested with WBC images from Kaggle and LISC database. Accuracy and F1-score were 99.73%, 0.99 and 98.23%, 0.98 for both data sets, respectively.