TRAgen: A Tool for Generation of Synthetic Time-Lapse Image Sequences of Living Cells

Ulman, Vladimír; Orémuš, Zoltán; Svoboda, David

doi:10.1007/978-3-319-23231-7_56

Cited by 4 publications

(3 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…We specifically created this dataset to highlight the limitations of methods that predict axis-aligned bounding boxes. Dataset TRAgen: Synthetically generated images of an evolving cell population from [18] (cf. Fig.…”

Section: Datasetsmentioning

confidence: 99%

Cell Detection with Star-Convex Polygons

Schmidt

Weigert

Broaddus

et al. 2018

Lecture Notes in Computer Science

1,152

952

View full text Add to dashboard Cite

Automatic detection and segmentation of cells and nuclei in microscopy images is important for many biological applications. Recent successful learning-based approaches include per-pixel cell segmentation with subsequent pixel grouping, or localization of bounding boxes with subsequent shape refinement. In situations of crowded cells, these can be prone to segmentation errors, such as falsely merging bordering cells or suppressing valid cell instances due to the poor approximation with bounding boxes. To overcome these issues, we propose to localize cell nuclei via star-convex polygons, which are a much better shape representation as compared to bounding boxes and thus do not need shape refinement. To that end, we train a convolutional neural network that predicts for every pixel a polygon for the cell instance at that position. We demonstrate the merits of our approach on two synthetic datasets and one challenging dataset of diverse fluorescence microscopy images.

show abstract

Section: Datasetsmentioning

confidence: 99%

Cell Detection with Star-Convex Polygons

Schmidt

Weigert

Broaddus

et al. 2018

Lecture Notes in Computer Science

1,152

952

View full text Add to dashboard Cite

show abstract

“…Although it appears that synthetic datasets have obtained reasonable fidelity and acceptance among many researchers, employing time‐lapse synthetic data and such simulators continues to occur rather sparingly in the field of cell tracking. Note that there is also a lack of benchmark reference datasets with time‐lapse synthetic images; thus, tracking algorithm researchers are often left with manual expert annotation or expert revision of results . Nonetheless, we have recently noticed a few articles that have suggested new tracking algorithms and also their evaluation on time‐lapse synthetic datasets.…”

Section: Conclusion and Discussionmentioning

confidence: 99%

“…The proposed framework (written in Matlab®) was capable of mimicking spatio‐temporal cell dynamics, including cell division events. Having the same motivation, Ulman et al proposed to simulate 2D time‐lapse tissue‐like dense populations of arbitrary cells that move, grow and divide using an agent‐based crowd motion simulation adapted to a virtual in vitro environment. The implementation is publicly available and allows users to automatically overlay user‐defined textures onto the cells, thereby allowing for a visually tailored simulation.…”

Section: Simulation At Various Scalesmentioning

confidence: 99%

Virtual cell imaging: A review on simulation methods employed in image cytometry

et al. 2016

Self Cite

View full text Add to dashboard Cite

The simulations of cells and microscope images thereof have been used to facilitate the development, selection, and validation of image analysis algorithms employed in cytometry as well as for modeling and understanding cell structure and dynamics beyond what is visible in the eyepiece. The simulation approaches vary from simple parametric models of specific cell components-especially shapes of cells and cell nuclei-to learning-based synthesis and multi-stage simulation models for complex scenes that simultaneously visualize multiple object types and incorporate various properties of the imaged objects and laws of image formation. This review covers advances in artificial digital cell generation at scales ranging from particles up to tissue synthesis and microscope image simulation methods, provides examples of the use of simulated images for various purposes ranging from subcellular object detection to cell tracking, and discusses how such simulators have been validated. Finally, the future possibilities and limitations of simulation-based validation are considered. © 2016 International Society for Advancement of Cytometry.

show abstract