Blood Cell Classification using Neural Network Models

Abstract

Blood cells classification is a crucial aspect in medical diagnosis. Several machine learning models have been proposed under various researches for classification of blood cells in recent years. However, the traditional machine learning algorithms are limited in the accurate detection of abnormal cells. In this study, we propose deep learning based approach for blood cell classification and evaluate the efficiency of multi-layer neural network model built for the classification of the various types of White Blood Cells using Convolutional Neural Networks (CNN) and Recurrent Neural Networks (RNN) in combination. The proposed method leverages the strengths of both CNN and RNN and gives better results.