Computational Framework for Simulating Fluorescence Microscope Images With Cell Populations

Abstract

Fluorescence microscopy combined with digital imaging constructs a basic platform for numerous biomedical studies in the field of cellular imaging. As the studies relying on analysis of digital images have become popular, the validation of image processing methods used in automated image cytometry has become an important topic. Especially, the need for efficient validation has arisen from emerging high-throughput microscopy systems where manual validation is impractical. We present a simulation platform for generating synthetic images of fluorescence-stained cell populations with realistic properties. Moreover, we show that the synthetic images enable the validation of analysis methods for automated image cytometry and comparison of their performance. Finally, we suggest additional usage scenarios for the simulator. The presented simulation framework, with several user-controllable parameters, forms a versatile tool for many kinds of validation tasks, and is freely available at http://www.cs.tut.fi/sgn/csb/simcep.

Smart Stadium for Smarter Living: Enriching the Fan Experience

“…The bacterial cells dataset: This dataset contains 200 synthetic images, emulating microscopic views of the colonies of bacterial cell [18]. Such synthetic images are highly realistic and simulate effects such as cell overlaps, shape variability, out-of-focus blur, vignetting, etc.…”

Uncertainty-aware estimation of population abundance using machine learning

“…The experimental dataset is produced with a simulation program [18]. It is very unbalanced due to scarce positive examples.…”

Principles of Bioimage Informatics: Focus on Machine Learning of Cell Patterns

“…Analysis on cell and organelle shapes can be done in a manner similar to nuclear shape. A vast majority of methods use parametric representation of cell shapes [31,32,33].…”