Cell Segmentation with Random Ferns and Graph-cuts

Browet, Arnaud; Vleeschouwer, Christophe De; Jacques, Laurent; Mathiah, Navrita; Saykali, Bechara; Migeotte, Isabelle

doi:10.1101/039958

Cited by 7 publications

(6 citation statements)

References 26 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The observable facet areas also become larger. With the advancement of 3D segmentation techniques [60][61][62][63][64], one can use these signatures as a toolkit to probe interfacial tensions in a 3D tissue, so that cells themselves can tell us about relative magnitudes of tissue surface tension nearby.…”

Section: Discussionmentioning

confidence: 99%

Geometric signatures of tissue surface tension in a three-dimensional model of confluent tissue

Sahu,

Schwarz,

Manning

2021

Preprint

View full text Add to dashboard Cite

In dense biological tissues, cell types performing different roles remain segregated by maintaining sharp interfaces. To better understand the mechanisms for such sharp compartmentalization, we study the effect of an imposed heterotypic tension at the interface between two distinct cell types in a fully 3D model for confluent tissues. We find that cells rapidly sort and self-organize to generate a tissue-scale interface between cell types, and cells adjacent to this interface exhibit signature geometric features including nematic-like ordering, bimodal facet areas, and registration, or alignment, of cell centers on either side of the two-tissue interface. The magnitude of these features scales directly with the magnitude of imposed tension, suggesting that biologists can estimate the magnitude of tissue surface tension between two tissue types simply by segmenting a 3D tissue. To uncover the underlying physical mechanisms driving these geometric features, we develop two minimal, ordered models using two different underlying lattices that identify an energetic competition between bulk cell shapes and tissue interface area. When the interface area dominates, changes to neighbor topology are costly and occur less frequently, which generates the observed geometric features.

show abstract

Section: Discussionmentioning

confidence: 99%

Geometric signatures of tissue surface tension in a three-dimensional model of confluent tissue

Sahu,

Schwarz,

Manning

2021

Preprint

View full text Add to dashboard Cite

show abstract

“…Browet et al [6], working with mouse embryo cells, estimated pixel probabilities for cell interior, borders, and background -in line with our multiclass approach -and then minimized an energy cost function to match the class probabilities via graph-cuts. We favored to avoid the pitfalls of graph-cuts and the thresholding adopted in their formulation to define seeds within cells.…”

Section: Arxiv:180207465v1 [Cscv] 21 Feb 2018mentioning

confidence: 99%

Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells

Peña

Fernández

Ren

et al. 2018

2018 25th IEEE International Conference on Image Processing (ICIP)

View full text Add to dashboard Cite

We propose a new multiclass weighted loss function for instance segmentation of cluttered cells. We are primarily motivated by the need of developmental biologists to quantify and model the behavior of blood T-cells which might help us in understanding their regulation mechanisms and ultimately help researchers in their quest for developing an effective immunotherapy cancer treatment. Segmenting individual touching cells in cluttered regions is challenging as the feature distribution on shared borders and cell foreground are similar thus difficulting discriminating pixels into proper classes. We present two novel weight maps applied to the weighted cross entropy loss function which take into account both class imbalance and cell geometry. Binary ground truth training data is augmented so the learning model can handle not only foreground and background but also a third touching class. This framework allows training using U-Net. Experiments with our formulations have shown superior results when compared to other similar schemes, outperforming binary class models with significant improvement of boundary adequacy and instance detection. We validate our results on manually annotated microscope images of T-cells.

show abstract

“…the pixel-wise semantic annotation of images, can be found in [45] for natural images. A similar approach albeit in the context of medical image processing is used for the segmentation of kidney components in CT data [46] and cells in microscopic images [47]. In contrast to Random Forests (see e.g.…”

Section: Introductionmentioning

confidence: 99%

Random Ferns for Semantic Segmentation of PolSAR Images

Wei

Hänsch

2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Random Ferns -as a less known example of Ensemble Learning -have been successfully applied in many Computer Vision applications ranging from keypoint matching to object detection. This paper extends the Random Fern framework to the semantic segmentation of polarimetric synthetic aperture radar images. By using internal projections that are defined over the space of Hermitian matrices, the proposed classifier can be directly applied to the polarimetric covariance matrices without the need to explicitly compute predefined image features. Furthermore, two distinct optimization strategies are proposed: The first based on pre-selection and grouping of internal binary features before the creation of the classifier; and the second based on iteratively improving the properties of a given Random Fern. Both strategies are able to boost the performance by filtering features that are either redundant or have a low information content and by grouping correlated features to best fulfill the independence assumptions made by the Random Fern classifier. Experiments show that results can be achieved that are similar to a more complex Random Forest model and competitive to a deep learning baseline.

show abstract

Cell Segmentation with Random Ferns and Graph-cuts

Cited by 7 publications

References 26 publications

Geometric signatures of tissue surface tension in a three-dimensional model of confluent tissue

Geometric signatures of tissue surface tension in a three-dimensional model of confluent tissue

Multiclass Weighted Loss for Instance Segmentation of Cluttered Cells

Random Ferns for Semantic Segmentation of PolSAR Images

Contact Info

Product

Resources

About