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

Ali Selman Aydin, Abhinandan Dubey, Daniel Dovrat, Amir Aharoni, Roy Shilkrot; Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, 2017, pp. 1-7

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.

Related Material


[pdf]
[bibtex]
@InProceedings{Aydin_2017_CVPR_Workshops,
author = {Selman Aydin, Ali and Dubey, Abhinandan and Dovrat, Daniel and Aharoni, Amir and Shilkrot, Roy},
title = {CNN Based Yeast Cell Segmentation in Multi-Modal Fluorescent Microscopy Data},
booktitle = {Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops},
month = {July},
year = {2017}
}