Detection of leukocytes in intravital microscopy video images using convolutional neural networks

• Grant number: 18/07670-5
• Support Opportunities: Scholarships in Brazil - Scientific Initiation
• Effective date (Start): July 01, 2018
• Effective date (End): June 30, 2019
• Field of knowledge: Physical Sciences and Mathematics - Computer Science
• Principal Investigator: Ricardo José Ferrari
• Grantee: Amanda Basso de Oliveira
• Host Institution: Centro de Ciências Exatas e de Tecnologia (CCET). Universidade Federal de São Carlos (UFSCAR). São Carlos , SP, Brazil

Abstract

In recent years, a large number of researchers have turned their efforts and interests to the in vivo study of the cellular and molecular mechanisms of leukocyte-endothelium interaction in the microcirculation of various tissues and different inflammatory conditions. The primary objective of these studies is to develop more effective therapeutic strategies for the treatment of inflammatory diseases. For example, the Experimental Autoimmune Encephalomyelitis (EAE) model is the most commonly used model for the study of multiple sclerosis. In these types of studies, Intravital Microscopy (IM) imaging is considered the standard method of analysis, since it allows the acquisition of images with high temporal resolution and low spatial depth. Currently, the analysis of leukocyte-endothelium interactions in small animals is performed visually from a sequence of MI images. Despite being time-consuming, this procedure can lead to observer's visual fatigue and thus generate false statistics. In this context, this research proposal aims to study and develop a convolutional neural network for the detection of leukocytes in IM video images from in vivo experiments. The results will be analyzed quantitatively by comparing the manual annotations of the leukocytes, performed by a specialist, with the results of the automatic processing of the images, using the methodology of Precision-Recall curves.