A Novel Framework for Tracking In-vitro Cells in Time-lapse Phase Contrast Data

Abstract

With the proliferation of modern microscopy imaging technologies the amount of data that has to be analysed by biologists is constantly increasing and as a result the development of automatic approaches that are able to track cellular structures in timelapse images has become an important field of research. The aim of this paper is to detail the development of a novel tracking framework that is designed to extract the cell motility indicators in phase-contrast image sequences. To address issues that are caused by nonstructured (random) motion and cellular agglomeration, cell tracking is formulated as a sequential process where the inter-frame cell association is achieved by assessing the variation in the local structures contained in consecutive frames of the image sequence. We have evaluated the proposed algorithm on dense phase contrast cellular data and the reported results indicate that the developed algorithm is able to accurately track MadinDarby Canine Kidney (MDCK) Epithelial Cells in image data that is characterised by low contrast and high level of noise.

A Linear Time Algorithm of Computing Hausdorff Distance for Content-based Image Analysis

“…However, forward distance, df is not always equal to backward distance, db. They are defined as To obtain a symmetric distance the maximum value between df and db is taken as Hausdorff distance [7,11]. So, a more general description of symmetric Hausdorff distance, H , is…”

An active particle-based tracking framework for 2D and 3D time-lapse microscopy images

“…Various methods have been proposed to address the above challenges and they can be broadly classified into two categories [2],[4]. In the first category cells are detected in each frame and the cell to cell correspondence is carried out for each two adjacent frames in the sequence [2],[5].…”

A Novel Framework for Cellular Tracking and Mitosis Detection in Dense Phase Contrast Microscopy Images

“…< 1. The last term in (8) penalises the large displacements of the node v in frame T+1 with respect to the position of the node u in frame T. The reference edge structure associated with T uD  is defined as:…”

“…< 1 that have in their local structure at least a pair of matched nodes included in the list R, we calculate the partial matching confidence PMC(. ), using (8), that evaluates both the similarity for triangles and mesh edges with respect to the reference nodes containing in the list R. In this node association stage we also evaluate the distance between the nodes to place a higher degree of confidence when matching the nodes with MC(.) < 1.…”

“…These challenges vary to a great extent depending on the characteristics of the imaging systems or on the nature of the cell lines being analyzed, and as a result numerous semiautomatic [4]- [6] and fully automatic [1], [8], [11] cell tracking algorithms were proposed in the literature. When the published algorithms are evaluated from a computer vision standpoint, two main categories can be identified.…”