Home
Uni-Logo
 

Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins

Özgün Çiçek, Yassine Marrakchi, E. Antwi, B. DiVentura, Thomas Brox
MICCAI Workshop on Medical Image Learning with Less Labels and Imperfect Data, Springer, Vol.12446, 2020
Abstract: Deploying off-the-shelf segmentation networks on biomedical data has become common practice, yet if structures of interest in an image sequence are visible only temporarily, existing frame-by-frame methods fail. In this paper, we provide a solution to segmentation of imperfect data through time based on temporal propagation and uncertainty estimation. We integrate uncertainty estimation into Mask R-CNN network and propagate motion-corrected segmentation masks from frames with low uncertainty to those frames with high uncertainty to handle temporary loss of signal for segmentation. We demonstrate the value of this approach over frame-by-frame segmentation and regular temporal propagation on data from human embryonic kidney (HEK293T) cells transiently transfected with a fluorescent protein that moves in and out of the nucleus over time. The method presented here will empower microscopic experiments aimed at understanding molecular and cellular function.
Paper Supplementary Poster Publisher's link GitHub

Other associated files : slides-Recovering_the_Imperfect.pdf [861KB]  

Images and movies

 

BibTex reference

@InProceedings{CMB20,
  author       = "{\"O}. {\c{C}}i{\c{c}}ek and Y. Marrakchi and E. Antwi and B. DiVentura and T. Brox",
  title        = "Recovering the Imperfect: Cell Segmentation in the Presence of Dynamically Localized Proteins",
  booktitle    = "MICCAI Workshop on Medical Image Learning with Less Labels and Imperfect Data",
  series       = "Lecture Notes in Computer Science ",
  volume       = "12446",
  month        = " ",
  year         = "2020",
  publisher    = "Springer",
  url          = "http://lmbweb.informatik.uni-freiburg.de/Publications/2020/CMB20"
}

Other publications in the database