Segmentation and Tracking of Mammary Epithelial Organoids in
Brightfield Microscopy

J 2023

Segmentation and Tracking of Mammary Epithelial Organoids in Brightfield Microscopy

HRADECKÁ, Lucia, David WIESNER, Jakub SUMBAL, Zuzana SUMBALOVÁ KOLEDOVÁ, Martin MAŠKA et. al.

Basic information

Original name

Segmentation and Tracking of Mammary Epithelial Organoids in Brightfield Microscopy

Authors

HRADECKÁ, Lucia (703 Slovakia, belonging to the institution), David WIESNER (203 Czech Republic, belonging to the institution), Jakub SUMBAL (203 Czech Republic, belonging to the institution), Zuzana SUMBALOVÁ KOLEDOVÁ (703 Slovakia, belonging to the institution) and Martin MAŠKA (203 Czech Republic, guarantor, belonging to the institution)

Edition

IEEE Transactions on Medical Imaging, 2023, 0278-0062

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10200 1.2 Computer and information sciences

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 10.600 in 2022

RIV identification code

RIV/00216224:14330/23:00130029

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1109/TMI.2022.3210714

UT WoS

000907160700023

Keywords in English

organoid segmentation; organoid tracking; brightfield microscopy; deep learning; image synthesis

Abstract

V originále

We present an automated and deep-learningbased workflow to quantitatively analyze the spatiotemporal development of mammary epithelial organoids in twodimensional time-lapse (2D+t) sequences acquired using a brightfield microscope at high resolution. It involves a convolutional neural network (U-Net), purposely trained using computer-generated bioimage data created by a conditional generative adversarial network (pix2pixHD), to infer semantic segmentation, adaptive morphological filtering to identify organoid instances, and a shape-similarity-constrained, instance-segmentation-correcting tracking procedure to reliably cherry-pick the organoid instances of interest in time. By validating it using real 2D+t sequences of mouse mammary epithelial organoids of morphologically different phenotypes, we clearly demonstrate that the workflow achieves reliable segmentation and tracking performance, providing a reproducible and laborless alternative to manual analyses of the acquired bioimage data.

Links

GA21-20374S, research and development project

Name: Segmentace a sledování buněk se složitým tvarem

Investor: Czech Science Foundation

MUNI/A/1145/2021, interní kód MU

Name: Rozsáhlé výpočetní systémy: modely, aplikace a verifikace XI. (Acronym: SV-FI MAV XI.)

Investor: Masaryk University

MUNI/G/1446/2018, interní kód MU

Name: Deciphering the mechanisms of mammary epithelial branched pattern formation through iterative biological and mathematical modelling

Investor: Masaryk University, INTERDISCIPLINARY - Interdisciplinary research projects

Citovat

HRADECKÁ, Lucia, David WIESNER, Jakub SUMBAL, Zuzana SUMBALOVÁ KOLEDOVÁ and Martin MAŠKA. Segmentation and Tracking of Mammary Epithelial Organoids in Brightfield Microscopy. IEEE Transactions on Medical Imaging. 2023, vol. 42, No 1, p. 281-290. ISSN 0278-0062. Available from: https://dx.doi.org/10.1109/TMI.2022.3210714.

@article{2220797,
   author = {Hradecká, Lucia and Wiesner, David and Sumbal, Jakub and Sumbalová Koledová, Zuzana and Maška, Martin},
   article_number = {1},
   doi = {http://dx.doi.org/10.1109/TMI.2022.3210714},
   keywords = {organoid segmentation; organoid tracking; brightfield microscopy; deep learning; image synthesis},
   language = {eng},
   issn = {0278-0062},
   journal = {IEEE Transactions on Medical Imaging},
   title = {Segmentation and Tracking of Mammary Epithelial Organoids in Brightfield Microscopy},
   url = {https://doi.org/10.1109/TMI.2022.3210714},
   volume = {42},
   year = {2023}
}

TY  - JOUR
ID  - 2220797
AU  - Hradecká, Lucia - Wiesner, David - Sumbal, Jakub - Sumbalová Koledová, Zuzana - Maška, Martin
PY  - 2023
TI  - Segmentation and Tracking of Mammary Epithelial Organoids in Brightfield Microscopy
JF  - IEEE Transactions on Medical Imaging
VL  - 42
IS  - 1
SP  - 281-290
EP  - 281-290
SN  - 02780062
KW  - organoid segmentation
KW  - organoid tracking
KW  - brightfield microscopy
KW  - deep learning
KW  - image synthesis
UR  - https://doi.org/10.1109/TMI.2022.3210714
N2  - We present an automated and deep-learningbased workflow to quantitatively analyze the spatiotemporal development of mammary epithelial organoids in twodimensional time-lapse (2D+t) sequences acquired using a brightfield microscope at high resolution. It involves a convolutional neural network (U-Net), purposely trained using computer-generated bioimage data created by a conditional generative adversarial network (pix2pixHD), to infer semantic segmentation, adaptive morphological filtering to identify organoid instances, and a shape-similarity-constrained, instance-segmentation-correcting tracking procedure to reliably cherry-pick the organoid instances of interest in time. By validating it using real 2D+t sequences of mouse mammary epithelial organoids of morphologically different phenotypes, we clearly demonstrate that the workflow achieves reliable segmentation and tracking performance, providing a reproducible and laborless alternative to manual analyses of the acquired bioimage data.
ER  -

HRADECKÁ, Lucia, David WIESNER, Jakub SUMBAL, Zuzana SUMBALOVÁ KOLEDOVÁ and Martin MAŠKA. Segmentation and Tracking of Mammary Epithelial Organoids in Brightfield Microscopy. \textit{IEEE Transactions on Medical Imaging}. 2023, vol.~42, No~1, p.~281-290. ISSN~0278-0062. Available from: https://dx.doi.org/10.1109/TMI.2022.3210714.

Detailed Information on Publication Record