ESTIMATION OF PARAMETERS IN A PLANAR SEGMENT PROCESS WITH A BIOLOGICAL APPLICATION

• Main Authors: Viktor Benes, Jakub Vecera, Benjamin Eltzner, Carina Wollnik, Florian Rehfeldt, Veronika Kralova, Stephan Huckemann
• Format: Article
• Language: English
• Published: Slovenian Society for Stereology and Quantitative Image Analysis 2017-03-01
• Series: Image Analysis and Stereology
• Subjects: parameter estimation; random segment process; stem cell; stress fibre
• Online Access: https://www.ias-iss.org/ojs/IAS/article/view/1627

The paper deals with modeling of segment systems in a bounded planar set (a cell) by means of random segment processes. Two models with a density with respect to the Poisson process are presented. In model I interactions are given by the number of intersections, model II includes the length distribution and takes into account distances from the centre of the cell. The estimation of parameters of the models is suggested based on Takacz-Fiksel method. The method is tested first using simulated data. Further the real data from fluorescence imaging of stress fibres in mesenchymal human stem cells are evaluated. We apply model II which is inhomogeneous. The degree-of-fit testing of the model using various characteristics yields quite satisfactory results.