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

Abstract

Abstract-The aim of this paper is to detail the development of a novel tracking framework that is able to extract the cell motility indicators and to determine the cellular division (mitosis) events in large time-lapse phase-contrast image sequences. To address the challenges induced by non-structured (random) motion, cellular agglomeration, and cellular mitosis, the process of automatic (unsupervised) cell tracking is carried out in a sequential manner, where the inter-frame cell association is achieved by assessing the variation in the local cellular structures in consecutive frames of the image sequence. In our study a strong emphasis has been placed on the robust use of the topological information in the cellular tracking process and in the development of targeted pattern recognition techniques that were designed to redress the problems caused by segmentation errors, and to precisely identify mitosis using a backward (reversed) tracking strategy. The proposed algorithm has been evaluated on dense phase contrast cellular data and the experimental results indicate that the proposed algorithm is able to accurately track epithelial and endothelial cells in time-lapse image sequences that are characterized by low contrast and high level of noise. Our algorithm achieved 86.10% overall tracking accuracy and 90.12% mitosis detection accuracy.

Robust Nucleus/Cell Detection and Segmentation in Digital Pathology and Microscopy Images: A Comprehensive Review

“…Raimondo et al [41] have proposed an HAT based nucleus detection approach on fluorescence in situ hybridization (FISH) images, and the details are listed in Algorithm 2. Similar procedures for nucleus detection are applied to IHC stained breast cancer images [61] and phase contrast microscopy images [42]. In [43], [62], HAT is applied to nucleus marker detection in original intensity images, which will guide the subsequent watershed segmentation in fluorescence microscopy images.…”

Fully unsupervised symmetry-based mitosis detection in time-lapse cell microscopy

“…Encoding local cells' neighborhood connections using triangulation was previously suggested in several cell tracking algorithms (Li et al, 2010;Liu et al, 2010Liu et al, , 2011Thirusittampalam et al, 2013;Liu et al, 2016Liu et al, , 2017b, mainly for its stability in the presence of cell migration and division (illustrated in Fig. A.3.a, see Appendix).…”

“…Numerous methods exploit time-lapse microscopy dynamics and use cell tracks to detect cell divisions. In the work of Thirusittampalam et al (2013), a mother cell is associated with only one of the daughter cells, afterwards performing backward tracking to connect the two daughters with the mother cell. In Arbelle et al (2018) an appearance of a new cell, which is not located at the frame's edge, implies a possible mitotic event.…”

Unsupervised HEp-2 mitosis recognition in indirect immunofluorescence imaging

“…Even though mitotic cell recognition is a crucial phase of the procedure, so far most of the efforts have been directed towards the implementation of techniques for the classification of intensity [1] and pattern [2], [3] or for HEp-2 cell segmentation [4], [5]. On the other hand, most of the literature on mitosis recognition addresses very different imaging applications, such as time-lapse microscopy [6] or histopathology [7]. Hence, the proposed approaches cannot be easily adapted to the context of IIF-ANA testing.…”