Identification of Parasitized Single Cell from Normal Using Deep Learning Approach

Abstract

Patients' cells need to be examined, thus healthcare facilities require changes as well as advancements in terms of instruments and technology, notably software that aids in the diagnosis of certain symptoms and diseases by looking at them. This aids in the identification and diagnosis of intracellular parasites in a person's cell, making it easier to identify a person's health condition. These parasites are responsible for a variety of acute and chronic illnesses. The paper aims to provide an enhanced model for cell classification. This will help to increase the accuracy of detection for intercellular parasites within the patient cell and easily diagnose a person’s health condition. In response to that, the system implements a deep learning technique in cell categorization using the YOLOv3 algorithm. Having a model with 90.6% mean Average precision, made a cell classification with 99.06% precision determining whether the subjected single cell is parasitized or normal.