Use of Alexnet Architecture in the Detection of Bone Marrow White Blood Cancer Cells

Abstract

The cancer-affected area in white blood cell pictures is studied in this paper. AlexNet architecture is used to classify different types of white blood cells. This model, which was trained on cell pictures, first preprocesses the photos before extracting the best feature. The feature is extracted using the convolutional layer, Relu layer, and max pooling layer. For categorization of Eosinophils, Lymphocytes, Monocytes, and Neutrophils, the extracted features are input into a softmax and a completely linked layer. The various phases of image processing are used to improve the quality and accuracy of blood cancer detection. The accuracy of the blood sample image is determined by the affected area.