Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images

Schematic of the pipeline: a ResNet-18 encoder pretrained on ImageNet feeds U-Net and Feature Pyramid Network decoders. This is a schematic, not the paper's figure.

Abstract

The segmentation of cells is necessary for biologists in the morphological statistics for quantitative and qualitative analysis in Phase-contrast Microscopy (PCM) images. In this paper, we address the cell segmentation problem in PCM images. Deep Neural Networks (DNNs) commonly is initialized with weights from a network pre-trained on a large annotated data set like ImageNet have superior performance than those trained from scratch on a small dataset. Here, we demonstrate how encoder-decoder type architectures such as U-Net and Feature Pyramid Network (FPN) can be improved by an alternative encoder which pre-trained on the ImageNet dataset. In particular, our experimental results confirm that the image descriptors from ResNet-18 are highly effective in accurate prediction of the cell boundary and have higher Intersection over Union (IoU) in comparison to the classical U-Net and require fewer training epochs.

Method

Pretrained encoder

An ImageNet-pretrained ResNet-18 replaces the plain encoder of U-Net and FPN.

Two decoders

Both U-Net and Feature Pyramid Network decoders are tested with the new encoder.

Sharper boundaries

ResNet-18 image descriptors predict cell boundaries accurately, with higher IoU than classical U-Net and fewer training epochs.

Resources

Publisher: IEEE Xplore
Open access: Full text (IYTE GCRIS)
DOI: 10.1109/SIU49456.2020.9302304

BibTeX

@inproceedings{ayanzadeh2020deep,
  title = {Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images},
  author = {Ayanzadeh, Aydin and {\"O}zuysal, {\"O}zden Yal{\c{c}}in and Okvur, Devrim Pesen and {\"O}nal, Sevgi and T{\"o}reyin, Beh{\c{c}}et U{\u{g}}ur and {\"U}nay, Devrim},
  booktitle = {2020 28th Signal Processing and Communications Applications Conference (SIU)},
  pages = {1--4},
  year = {2020},
  organization = {IEEE},
  doi = {10.1109/SIU49456.2020.9302304}
}