Tissue level segmentation and tracking of biological structures in microscopic images based on density maps

Abstract

During embryogenesis, cells coordinate to form geometric arrangements. These arrangements are initially noticed as stereotypical clumps of cells that further divide to form a rigorous structure with a high density of cells. In this work, we explore density-based segmentation and tracking of cellular structures as observed in microscopy images. Using a new modified form of the Mumford-Shah energy functional, we derived a variational level-set for density-based segmentation. The novelty of the work lies in evolving an initialized contour that represents a salient structure on density maps to automatically generate novel cell structures upon convergence. We validate our methods and show results on confocal ear images of the zebrafish embryo.

Image analysis for understanding embryo development: a bridge from microscopy to biological insights

“…Cell membrane images from zebrafish development have been segmented using methods based on the numerical solution of PDEs [44]. Depending on the resolution and the developmental stage, it is also possible to segment suprastructures at the tissue level [45]. Whatever the strategy, the assessment of segmentation accuracy remains a major challenge, and very few studies compare segmentation results with a gold standard shape [16 ].…”

Information Hiding Based on Chan-Vese Algorithm

“…[15] The first two terms in equation ( 3) are often referred as global binary fitting energy terms that seek to separate an image into two regions of constant image intensities. [9] To solve the minimization problem in equation ( 3), the level set method is used which replaces the unknown curve C by the level set Ø(x,y), considering that Ø(x,y)>o if the point (x,y) is inside C, Ø(x,y)<0 if (x,y) is outside C, and Ø(x,y)=0 if (x,y) is on C (see Figure (2)). Thus, the energy functional E CV (c 1 ,c 2 ,C) can be reformulated in terms of the level set function Ø(x,y):…”