Automated Segmentation of Cells in Phase Contrast Optical Microscopy Time Series Images

Schematic of the study: time-series phase-contrast images are segmented by traditional and deep learning approaches and evaluated against manual annotations. This is a schematic, not the paper's figure.

Abstract

Phase contrast optical microscopy is a preferred imaging technique for live-cell, temporal analysis. Segmentation of cells from time series data acquired with this technique is a labor-intensive and time-consuming task that cell biology researchers need solution for. In this study traditional image processing and deep learning based approaches for automated cell segmentation from phase contrast optical microscopy time series are presented, and their performances are evaluated against manually annotated datasets.

Method

Time-series data

Phase-contrast microscopy time series of live cells, frame by frame.

Two approaches

Traditional image processing and deep learning based approaches for automated segmentation.

Manual evaluation

Both approaches are evaluated against manually annotated datasets.

Resources

Publisher: IEEE Xplore (DOI)
DOI: 10.1109/TIPTEKNO.2019.8895080

BibTeX

@inproceedings{binici2019automated,
  title = {Automated Segmentation of Cells in Phase Contrast Optical Microscopy Time Series Images},
  author = {Binici, R{\i}fk{\i} Can and {\c{S}}ahin, Umut and Ayanzadeh, Aydin and T{\"o}reyin, Beh{\c{c}}et U{\u{g}}ur and {\"O}nal, Sevgi and Okvur, Devrim Pesen and {\"O}zuysal, {\"O}zden Yal{\c{c}}{\i}n and {\"U}nay, Devrim},
  booktitle = {2019 Medical Technologies Congress (TIPTEKNO)},
  pages = {1--4},
  year = {2019},
  organization = {IEEE},
  doi = {10.1109/TIPTEKNO.2019.8895080}
}