A Geometric Descriptor for Cell-Division Detection

TL;DR

This paper introduces a geometric descriptor-based method utilizing wavelet filtering and symmetry tests to detect cell division events in image sequences, with centroid analysis pinpointing the exact division frame.

Contribution

The paper presents a novel geometric descriptor and a two-step centroid analysis approach for accurate cell-division detection in microscopy images.

Findings

Effective detection of cell division in image sequences.

Accurate localization of division frames.

Robustness to noise and variability.

Abstract

We describe a method for cell-division detection based on a geometric-driven descriptor that can be represented as a 5-layers processing network, based mainly on wavelet filtering and a test for mirror symmetry between pairs of pixels. After the centroids of the descriptors are computed for a sequence of frames, the two-steps piecewise constant function that best fits the sequence of centroids determines the frame where the division occurs.