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

Aydin Ayanzadeh; Ozden Yalcin Ozuysal; Devrim Pesen Okvur; Sevgi Onal; Behcet Ugur Tgreyin; Devrim Unay

doi:10.1109/SIU49456.2020.9302304

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

Aydin Ayanzadeh, Ozden Yalcin Ozuysal, Devrim Pesen Okvur, Sevgi Onal, Behcet Ugur Tgreyin, Devrim Unay

Informatics Institute

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

3 Citations (Scopus)

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.

Original language	English
Title of host publication	2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings
Publisher	Institute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)	9781728172064
DOIs	https://doi.org/10.1109/SIU49456.2020.9302304
Publication status	Published - 5 Oct 2020
Event	28th Signal Processing and Communications Applications Conference, SIU 2020 - Gaziantep, Turkey Duration: 5 Oct 2020 → 7 Oct 2020

Publication series

Name	2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

Conference

Conference	28th Signal Processing and Communications Applications Conference, SIU 2020
Country/Territory	Turkey
City	Gaziantep
Period	5/10/20 → 7/10/20

Bibliographical note

Publisher Copyright:
© 2020 IEEE.

Funding

ACKNOWLEDGMENT The data used in this study is collected under the Marie Curie IRG grant (no: FP7 PIRG08-GA-2010-27697). Aydin Ayanzadeh’s work is supported, in part, by Vodafone Turkey, under project no. ITUVF20180901P04 within the context of ITU Vodafone Future Lab RD program. This work is in part funded by ˙TÜ BAP MGA-2017-40964. This work has been supported by the Scientific and Technological Research Council of Turkey (TUBITAK) under Grant 119E578.

Funders	Funder number
TUBITAK	119E578
Vodafone Turkey	ITUVF20180901P04
İTÜ Vodafone Future Lab	BAP MGA-2017-40964
Türkiye Bilimsel ve Teknolojik Araştirma Kurumu

Keywords

Cell Segmentation
Deep learning
Phase-Contrast microscopy

Access to Document

10.1109/SIU49456.2020.9302304

Cite this

Ayanzadeh, A., Ozuysal, O. Y., Okvur, D. P., Onal, S., Tgreyin, B. U., & Unay, D. (2020). Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images. In 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings Article 9302304 (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings). Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/SIU49456.2020.9302304

Ayanzadeh, Aydin ; Ozuysal, Ozden Yalcin ; Okvur, Devrim Pesen et al. / Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images. 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings).

@inproceedings{d8be45cb0fea43feb184a55878eb1a28,

title = "Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images",

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.",

keywords = "Cell Segmentation, Deep learning, Phase-Contrast microscopy",

author = "Aydin Ayanzadeh and Ozuysal, {Ozden Yalcin} and Okvur, {Devrim Pesen} and Sevgi Onal and Tgreyin, {Behcet Ugur} and Devrim Unay",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 28th Signal Processing and Communications Applications Conference, SIU 2020 ; Conference date: 05-10-2020 Through 07-10-2020",

year = "2020",

month = oct,

day = "5",

doi = "10.1109/SIU49456.2020.9302304",

language = "English",

series = "2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings",

publisher = "Institute of Electrical and Electronics Engineers Inc.",

booktitle = "2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings",

address = "United States",

}

Ayanzadeh, A, Ozuysal, OY, Okvur, DP, Onal, S, Tgreyin, BU & Unay, D 2020, Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images. in 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings., 9302304, 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings, Institute of Electrical and Electronics Engineers Inc., 28th Signal Processing and Communications Applications Conference, SIU 2020, Gaziantep, Turkey, 5/10/20. https://doi.org/10.1109/SIU49456.2020.9302304

Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images. / Ayanzadeh, Aydin; Ozuysal, Ozden Yalcin; Okvur, Devrim Pesen et al.
2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc., 2020. 9302304 (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution › peer-review

TY - GEN

T1 - Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images

AU - Ayanzadeh, Aydin

AU - Ozuysal, Ozden Yalcin

AU - Okvur, Devrim Pesen

AU - Onal, Sevgi

AU - Tgreyin, Behcet Ugur

AU - Unay, Devrim

PY - 2020/10/5

Y1 - 2020/10/5

N2 - 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.

AB - 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.

KW - Cell Segmentation

KW - Deep learning

KW - Phase-Contrast microscopy

UR - http://www.scopus.com/inward/record.url?scp=85100321434&partnerID=8YFLogxK

U2 - 10.1109/SIU49456.2020.9302304

DO - 10.1109/SIU49456.2020.9302304

M3 - Conference contribution

AN - SCOPUS:85100321434

T3 - 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

BT - 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings

PB - Institute of Electrical and Electronics Engineers Inc.

T2 - 28th Signal Processing and Communications Applications Conference, SIU 2020

Y2 - 5 October 2020 through 7 October 2020

ER -

Ayanzadeh A, Ozuysal OY, Okvur DP, Onal S, Tgreyin BU, Unay D. Deep Learning based Segmentation Pipeline for Label-Free Phase-Contrast Microscopy Images. In 2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings. Institute of Electrical and Electronics Engineers Inc. 2020. 9302304. (2020 28th Signal Processing and Communications Applications Conference, SIU 2020 - Proceedings). doi: 10.1109/SIU49456.2020.9302304

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

Abstract

Publication series

Conference

Bibliographical note

Funding

Keywords

Access to Document

Other files and links

Fingerprint

Cite this