Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Cellpose+, a morphological analysis tool for feature extraction of stained cell images

Israel A. Huaman, Fares D. E. Ghorabe, Sofya S. Chumakova, Alexandra A. Pisarenko, Alexey E. Dudaev, Tatiana G. Volova, Galina A. Ryltseva, Sviatlana A. Ulasevich, Ekaterina I. Shishatskaya, Ekaterina V. Skorb, Pavel S. Zun

TL;DR

The applications of Cellpose are extended, a state‐of‐the‐art cell segmentation framework, with feature extraction capabilities to assess morphological characteristics, and a new method is applied to assess morphological characteristics of cells stained with fluorescein isothiocyanate.

Abstract

Advanced image segmentation and processing tools present an opportunity to study cell processes and their dynamics. However, image analysis is often routine and time-consuming. Nowadays, alternative data-driven approaches using deep learning are potentially offering automatized, accurate, and fast image analysis. In this paper, we extend the applications of Cellpose, a state-of-the-art cell segmentation framework, with feature extraction capabilities to assess morphological characteristics. We also introduce a dataset of DAPI and FITC stained cells to which our new method is applied.

Cellpose+, a morphological analysis tool for feature extraction of stained cell images

TL;DR

The applications of Cellpose are extended, a state‐of‐the‐art cell segmentation framework, with feature extraction capabilities to assess morphological characteristics, and a new method is applied to assess morphological characteristics of cells stained with fluorescein isothiocyanate.

Abstract

Advanced image segmentation and processing tools present an opportunity to study cell processes and their dynamics. However, image analysis is often routine and time-consuming. Nowadays, alternative data-driven approaches using deep learning are potentially offering automatized, accurate, and fast image analysis. In this paper, we extend the applications of Cellpose, a state-of-the-art cell segmentation framework, with feature extraction capabilities to assess morphological characteristics. We also introduce a dataset of DAPI and FITC stained cells to which our new method is applied.

Paper Structure

This paper contains 11 sections, 4 figures, 1 table.

Table of Contents

  1. Introduction
  2. Methods
  3. Polymer production
  4. Cell culture and image acquisition
  5. Cell statistical analysis
  6. Results and discussion
  7. Cell segmentation
  8. Implementation of features extraction
  9. Discussion
  10. Conclusions
  11. Acknowledgements

Figures (4)

  • Figure 1: Workflow to obtain metrics from segmented cells. Initial raw data (a) is merged into a single image (b) and organized into sub folders to be processed (c). A cell segmentation procedure is performed using Cellpose (d). We extract metrics (e) according the defined folder structure, and finally we obtain results (f) in the form of images and CSV files containing mentioned metrics (g).
  • Figure 2: Processing stages of a single image. From the image combined from FITC and DAPI (a), we extract cells contour and nuclei masks (b) for feature extraction. We use center coordinates to plot a Voronoi diagram (c) and get an uniformity reading of it (d). Scale bar, $50~\mu m$.
  • Figure 3: Updated Cellpose GUI. A new feature extraction tools marked in cyan, showing segmented cells with their respective area in $\mu m^2$ (a). Two new tabs, Masks and Images, are added to save segmented subjects and to visualize features respectively (b). We added the morphological features we can select to extract from the segmented subjects.
  • Figure 4: Features extracted from cells and nuclei according to their thickness level.