Split and merge watershed: A two-step method for cell segmentation in fluorescence microscopy images

Gamarra, Margarita; Zurek, Eduardo; Escalante, Hugo Jair; Hurtado, Leidy; San‐Juan‐Vergara, Homero

doi:10.1016/j.bspc.2019.101575

Cited by 67 publications

(32 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…JSTA relies on initial seed identification (nuclei or cell centers), and incorrect identification can lead to split or merged cells. JSTA currently does not split or merge cells, but this postprocessing step could be added to further improve segmentation (Chaudhuri & Agrawal, 2010;Surut & Phukpattaranont, 2010;Correa-Tome & Sanchez-Yanez, 2015;Gamarra et al, 2019). On the data side, as JSTA leverages external reference data, it will naturally increase in its performance as both the quality and quantity of reference cell type taxonomies improve (HuBMAP Consortium, 2019).…”

Section: Discussionmentioning

confidence: 99%

Joint cell segmentation and cell type annotation for spatial transcriptomics

Littman

Hemminger

Foreman

et al. 2021

Molecular Systems Biology

View full text Add to dashboard Cite

RNA hybridization‐based spatial transcriptomics provides unparalleled detection sensitivity. However, inaccuracies in segmentation of image volumes into cells cause misassignment of mRNAs which is a major source of errors. Here, we develop JSTA, a computational framework for joint cell segmentation and cell type annotation that utilizes prior knowledge of cell type‐specific gene expression. Simulation results show that leveraging existing cell type taxonomy increases RNA assignment accuracy by more than 45%. Using JSTA, we were able to classify cells in the mouse hippocampus into 133 (sub)types revealing the spatial organization of CA1, CA3, and Sst neuron subtypes. Analysis of within cell subtype spatial differential gene expression of 80 candidate genes identified 63 with statistically significant spatial differential gene expression across 61 (sub)types. Overall, our work demonstrates that known cell type expression patterns can be leveraged to improve the accuracy of RNA hybridization‐based spatial transcriptomics while providing highly granular cell (sub)type information. The large number of newly discovered spatial gene expression patterns substantiates the need for accurate spatial transcriptomic measurements that can provide information beyond cell (sub)type labels.

show abstract

Section: Discussionmentioning

confidence: 99%

Joint cell segmentation and cell type annotation for spatial transcriptomics

Littman

Hemminger

Foreman

et al. 2021

Molecular Systems Biology

View full text Add to dashboard Cite

show abstract

“…In the near future, we plan to increase the number of samples per experimental setting, as well as test MF2C3 on other cell lines according to the next biological in vivo studies [61]. Moreover, we aim at improving colony counting also by splitting the merged colonies by means of watershed-based approaches [62]. Our ultimate goal is to integrate the reliable results achieved by MF2C3 into quantitative biology analyses involving the evaluation of antiproliferative drug effects [63], by also being beneficial to Systems Biology models [64].…”

Section: Discussionmentioning

confidence: 99%

MF2C3: Multi-Feature Fuzzy Clustering to Enhance Cell Colony Detection in Automated Clonogenic Assay Evaluation

et al. 2020

View full text Add to dashboard Cite

A clonogenic assay is a biological technique for calculating the Surviving Fraction (SF) that quantifies the anti-proliferative effect of treatments on cell cultures: this evaluation is often performed via manual counting of cell colony-forming units. Unfortunately, this procedure is error-prone and strongly affected by operator dependence. Besides, conventional assessment does not deal with the colony size, which is generally correlated with the delivered radiation dose or administered cytotoxic agent. Relying upon the direct proportional relationship between the Area Covered by Colony (ACC) and the colony count and size, along with the growth rate, we propose MF2C3, a novel computational method leveraging spatial Fuzzy C-Means clustering on multiple local features (i.e., entropy and standard deviation extracted from the input color images acquired by a general-purpose flat-bed scanner) for ACC-based SF quantification, by considering only the covering percentage. To evaluate the accuracy of the proposed fully automatic approach, we compared the SFs obtained by MF2C3 against the conventional counting procedure on four different cell lines. The achieved results revealed a high correlation with the ground-truth measurements based on colony counting, by outperforming our previously validated method using local thresholding on L*u*v* color well images. In conclusion, the proposed multi-feature approach, which inherently leverages the concept of symmetry in the pixel local distributions, might be reliably used in biological studies.

show abstract

“…This globally optimal model-based approach relies on convex level set energies and parameterized elliptical shape priors. Differently, no detection with ellipse fitting was exploited in [ 16 ], as this shape prior is not always suitable for representing the shape of the cell nuclei because of the highly variable appearance. In particular, a two-stage method combining the split-and-merge and watershed algorithms was proposed.…”

Section: Introductionmentioning

confidence: 99%

“…The authors of [ 22 ] proposed an approach for automatically creating high-quality experiment-specific ground truth for segmentation of bright-field images of cultured cells based on end-point fluorescent staining, then exploited to train a DCNN [ 34 ]. In general, applying DCNNs to microscopy images is still challenging due to the lack of large datasets labeled at the single cell level [ 34 ]; moreover, Gamarra et al [ 16 ] showed that watershed-based methods can achieve performance comparable to DCNN-based approaches. Thus, unsupervised techniques that do not require a training phase (i.e., data fitting or modeling) represent valuable solutions in this practical context [ 19 , 35 ].…”

Section: Introductionmentioning

confidence: 99%

ACDC: Automated Cell Detection and Counting for Time-Lapse Fluorescence Microscopy

et al. 2020

View full text Add to dashboard Cite

Advances in microscopy imaging technologies have enabled the visualization of live-cell dynamic processes using time-lapse microscopy imaging. However, modern methods exhibit several limitations related to the training phases and to time constraints, hindering their application in the laboratory practice. In this work, we present a novel method, named Automated Cell Detection and Counting (ACDC), designed for activity detection of fluorescent labeled cell nuclei in time-lapse microscopy. ACDC overcomes the limitations of the literature methods, by first applying bilateral filtering on the original image to smooth the input cell images while preserving edge sharpness, and then by exploiting the watershed transform and morphological filtering. Moreover, ACDC represents a feasible solution for the laboratory practice, as it can leverage multi-core architectures in computer clusters to efficiently handle large-scale imaging datasets. Indeed, our Parent-Workers implementation of ACDC allows to obtain up to a 3.7× speed-up compared to the sequential counterpart. ACDC was tested on two distinct cell imaging datasets to assess its accuracy and effectiveness on images with different characteristics. We achieved an accurate cell-count and nuclei segmentation without relying on large-scale annotated datasets, a result confirmed by the average Dice Similarity Coefficients of 76.84 and 88.64 and the Pearson coefficients of 0.99 and 0.96, calculated against the manual cell counting, on the two tested datasets.

show abstract

Split and merge watershed: A two-step method for cell segmentation in fluorescence microscopy images

Cited by 67 publications

References 27 publications

Joint cell segmentation and cell type annotation for spatial transcriptomics

Joint cell segmentation and cell type annotation for spatial transcriptomics

MF2C3: Multi-Feature Fuzzy Clustering to Enhance Cell Colony Detection in Automated Clonogenic Assay Evaluation

ACDC: Automated Cell Detection and Counting for Time-Lapse Fluorescence Microscopy

Contact Info

Product

Resources

About