Establishment and Verification of Neural Network for Rapid and Accurate Cytological Examination of Four Types of Cerebrospinal Fluid Cells.

Luyue Jiang,Gang Zhao,Zhuangde Jiang,Gang Niu,Zhen Xie,Yi Quan,Wei Ren,Yangyang Liu,Matthew Xinhu Ren,Yu Wang ,Heping Wu

doi:10.3389/fmed.2021.749146

Abstract

Fast and accurate cerebrospinal fluid cytology is the key to the diagnosis of many central nervous system diseases. However, in actual clinical work, cytological counting and classification of cerebrospinal fluid are often time-consuming and prone to human error. In this report, we have developed a deep neural network (DNN) for cell counting and classification of cerebrospinal fluid cytology. The May-Grünwald-Giemsa (MGG) stained image is annotated and input into the DNN network. The main cell types include lymphocytes, monocytes, neutrophils, and red blood cells. In clinical practice, the use of DNN is compared with the results of expert examinations in the professional cerebrospinal fluid room of a First-line 3A Hospital. The results show that the report produced by the DNN network is more accurate, with an accuracy of 95% and a reduction in turnaround time by 86%. This study shows the feasibility of applying DNN to clinical cerebrospinal fluid cytology.

Highlights

The central nervous system (CNS) is one of the most crucial systems in the human body
When perturbed by an infectious disease, the human body responds by increasing white blood cells (WBCs) population leading to an inflammation of the CNS, which leads to increased mortality and morbidity if not correctly diagnosed and properly treated
This study presents a pioneering application of image-based deep neural network (DNN) to patient samples in a clinical setting

Summary

INTRODUCTION

The central nervous system (CNS) is one of the most crucial systems in the human body. When perturbed by an infectious disease, the human body responds by increasing WBC population leading to an inflammation of the CNS, which leads to increased mortality and morbidity if not correctly diagnosed and properly treated. The global burden of CNS infections in 2016 was tabulated in a recent study [1] and estimated to be 9.4 million incidences with a mortality rate of 5% or 458,000 deaths annually. With such a high clinical priority and impact, there is always a need for improvement on the aspect of rapid diagnose for CNS infection

A Neural Network for CSF Examination

MATERIALS AND METHODS

CONCLUSION

Findings

ETHICS STATEMENT