S. K. Nath, K. Palaniappan, and F. Bunyak

Lecture Notes in Computer Science (MICCAI), Volume 4190, pgs. 101--108, 2006

cell detection, cell segmentation, active contours, cell tracking, biomedical

PlainText, Bibtex, PDF, DOI, Google Scholar

Abstract

Current level-set based approaches for segmenting a large number of objects are computationally expensive since they require a unique level set per object (the N-level set paradigm), or log2N level sets when using a multiphase interface tracking formulation. Incorpo- rating energy-based coupling constraints to control the topological in- teractions between level sets further increases the computational cost to O(N2). We propose a new approach, with dramatic computational sav- ings, that requires only four, or fewer, level sets for an arbitrary number of similar objects (like cells) using the Delaunay graph to capture spatial relationships. Even more significantly, the coupling constraints (energy- based and topological) are incorporated using just constant O(1) com- plexity. The explicit topological coupling constraint, based on predicting contour collisions between adjacent level sets, is developed to further prevent false merging or absorption of neighboring cells, and also reduce fragmentation during level set evolution. The proposed four-color level set algorithm is used to efficiently and accurately segment hundreds of in- dividual epithelial cells within a moving monolayer sheet from time-lapse images of in vitro wound healing without any false merging of cells.