Automated image segmentation for detecting cell spreading for metastasizing assessments of cancer development

TL;DR

This paper presents an automated image segmentation method for microscopic cell images to aid in cancer development studies, highlighting the challenges in accurate boundary detection under realistic conditions.

Contribution

The paper introduces a segmentation approach combining G-neighbor smoothing, Kauwahara filtering, and local standard deviation for boundary detection in DIC cell images.

Findings

Segmentation approach can detect cell boundaries in realistic conditions

Boundary detection remains a challenging problem

Ground truth dataset created using NIH FIJI/ImageJ

Abstract

The automated segmentation of cells in microscopic images is an open research problem that has important implications for studies of the developmental and cancer processes based on in vitro models. In this paper, we present the approach for segmentation of the DIC images of cultured cells using G-neighbor smoothing followed by Kauwahara filtering and local standard deviation approach for boundary detection. NIH FIJI/ImageJ tools are used to create the ground truth dataset. The results of this work indicate that detection of cell boundaries using segmentation approach even in the case of realistic measurement conditions is a challenging problem.