Active Contour Segmentation based on Approximate Entropy - Application to Cell Membrane Segmentation in Confocal Microscopy

摘要: Segmentation of cellular structures is primary interest in cell imaging for shape reconstruction and to provide crucial information about possible morphology changes during radiotherapy instance. From the particular perspective predictive oncology, this paper reports on a novel method membrane segmentation from single channel actin tagged fluorescence confocal microscopy images, which remains challenging task. Proposed based use Approximate Entropy formerly introduced by Pincus embedded within Geodesic Active Contour approach. can be seen as an estimator regularity sequence values and, consequently, used edge detector. In prospective study, preliminary study detector function first proposed with focus robustness noise, some promising results obtained images are also shown. Copyright © 2014 SCITEPRESS - Science Technology Publications. All rights reserved.