ML Anthology

CNN Based Yeast Cell Segmentation in Multi-Modal Fluorescent Microscopy Data

Ali Selman Aydin, Abhinandan Dubey, Daniel Dovrat, Amir Aharoni, Roy Shilkrot
CVPRW 2017 pp. 753-759
doi:10.1109/CVPRW.2017.105 /cvprw/2017/aydin2017cvprw-cnn/

Abstract

We present a method for foreground segmentation of yeast cells in the presence of high-noise induced by intentional low illumination, where traditional approaches (e.g., threshold-based methods, specialized cell-segmentation methods) fail. To deal with these harsh conditions, we use a fully-convolutional semantic segmentation network based on the SegNet architecture. Our model is capable of segmenting patches extracted from yeast live-cell experiments with a mIOU score of 0.71 on unseen patches drawn from independent experiments. Further, we show that simultaneous multi-modal observations of bio-fluorescent markers can result in better segmentation performance than the DIC channel alone.

CVPRW Semantic Scholar

Cite

Text

Aydin et al. "CNN Based Yeast Cell Segmentation in Multi-Modal Fluorescent Microscopy Data." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017. doi:10.1109/CVPRW.2017.105

Markdown

[Aydin et al. "CNN Based Yeast Cell Segmentation in Multi-Modal Fluorescent Microscopy Data." IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2017.](https://mlanthology.org/cvprw/2017/aydin2017cvprw-cnn/) doi:10.1109/CVPRW.2017.105

BibTeX

@inproceedings{aydin2017cvprw-cnn,
  title     = {{CNN Based Yeast Cell Segmentation in Multi-Modal Fluorescent Microscopy Data}},
  author    = {Aydin, Ali Selman and Dubey, Abhinandan and Dovrat, Daniel and Aharoni, Amir and Shilkrot, Roy},
  booktitle = {IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops},
  year      = {2017},
  pages     = {753-759},
  doi       = {10.1109/CVPRW.2017.105},
  url       = {https://mlanthology.org/cvprw/2017/aydin2017cvprw-cnn/}
}