Detection and tracking of leukocytes in intravital microscopy images via spatial-temporal processing

Abstract

In recent years, a large number of researchers have focused their efforts and interests for the in vivo study of cellular and molecular mechanisms of leukocyte-endothelial interactions in the microcirculation of various tissues and in various inflammatory conditions. The main goal of these studies is to develop more effective therapeutic strategies for the treatment of inflammatory and autoimmune diseases. In these types of studies, the intravital microscopy imaging is considered to be the gold standard technique since it allows the acquisition of images with high temporal resolution and low spatial depth. Currently, analysis of leukocyte-endothelial interactions in small animals is performed in a visual manner by means of intravital microscopy image sequences. Besides being time consuming, this procedure can lead to visual fatigue of the observer and thus generate false statistics. In this context, this research proposal aims to study and develop computer techniques for the automatic detection and tracking of leukocytes in intravital video microscopy. The proposed approach intends to combine results of the frame by frame processing (2D - spatial analysis) of the video and results of the three-dimensional analysis (3D - temporal analysis) of the image formed by stacking all video frames. While the 2D image processing aims to produce more accurate information about the cell morphology, the 3D processing intends to assist in both the dynamic analysis of cell movement and eliminating ambiguous results from overlapping cells and artifacts resulting from the 2D segmentation. In this project, intravital microscopy videos obtained from a study of multiple sclerosis conducted with mice will be used. Techniques for noise reduction and motion stabilization of the image sequences will also be investigated and comprise a step of preprocessing. The results will be analyzed qualitatively by comparing the measurements obtained by the conventional visual analysis approach (with the manual annotations), and quantitatively using the method of ROC curves for the evaluation of the 2D processing and using the Hausdorff measure for evaluating the paths of leukocytes. (AU)