City Research Online

Segmentation of Overlapping Macrophages Using Anglegram Analysis

Solis Lemus, J., Stramer, B., Slabaugh, G.G. and Reyes-Aldasoro, C. C. (2017). Segmentation of Overlapping Macrophages Using Anglegram Analysis. Paper presented at the Medical Image Understanding and Analysis (MIUA) 2017, 11 Jul 2017, Edinburgh, UK.

Abstract

This paper describes the automatic segmentation of overlapping cells through different algorithms. As the first step, the algorithm detects junctions between the boundaries of overlapping objects based on the angles between points of the overlapping boundary. For this purpose, a novel 2D matrix with multiscale angle variation is introduced, i.e anglegram. The anglegram is used to find junctions of overlapping cells. The algorithm to retrieve junctions from the boundary was tested and validated with synthetic data and fluorescently labelled macrophages observed on embryos of Drosophila melanogaster. Then, four different segmentation techniques were evaluated: (i) a Voronoi partition based on the nuclei positions, (ii) a slicing method, which joined the clumps together (junction slicing), (iii) a partition based on the following of the edges from the junctions (edge following), and (iv) a custom self-organising map to fit to the area of overlap between the cells. Only (ii)-(iv) were based on the junctions. The segmentation results were compared based on precision, recall and Jaccard similarity. The algorithm that reported the best segmentation was the junction slicing.

Publication Type: Conference or Workshop Item (Paper)
Additional Information: The final publication is available at Springer via https://link.springer.com/chapter/10.1007/978-3-319-60964-5_69.
Departments: School of Mathematics, Computer Science & Engineering > Computer Science
URI: http://openaccess.city.ac.uk/id/eprint/17830
[img]
Preview
Text - Accepted Version
Download (4MB) | Preview

Export

Downloads

Downloads per month over past year

View more statistics

Actions (login required)

Admin Login Admin Login