Deep-Learning-Based Segmentation of Small Extracellular
Vesicles in Transmission Electron Microscopy Images

J 2019

Deep-Learning-Based Segmentation of Small Extracellular Vesicles in Transmission Electron Microscopy Images

GÓMEZ-DE-MARISCAL, Estibaliz, Martin MAŠKA, Anna KOTRBOVÁ, Vendula POSPÍCHALOVÁ, Pavel MATULA et. al.

Basic information

Original name

Deep-Learning-Based Segmentation of Small Extracellular Vesicles in Transmission Electron Microscopy Images

Authors

GÓMEZ-DE-MARISCAL, Estibaliz (724 Spain), Martin MAŠKA (203 Czech Republic, guarantor, belonging to the institution), Anna KOTRBOVÁ (203 Czech Republic, belonging to the institution), Vendula POSPÍCHALOVÁ (203 Czech Republic, belonging to the institution), Pavel MATULA (203 Czech Republic, belonging to the institution) and Arrate MUÑOZ-BARRUTIA (724 Spain)

Edition

Scientific Reports, 2019, 2045-2322

Other information

Language

English

Type of outcome

Článek v odborném periodiku

Field of Study

10201 Computer sciences, information science, bioinformatics

Country of publisher

United States of America

Confidentiality degree

není předmětem státního či obchodního tajemství

References:

URL

Impact factor

Impact factor: 3.998

RIV identification code

RIV/00216224:14330/19:00107638

Organization unit

Faculty of Informatics

DOI

http://dx.doi.org/10.1038/s41598-019-49431-3

UT WoS

000485680900008

Keywords in English

image segmentation;deep learning;smal extracellular vesicles;transmission electron microscopy

Abstract

V originále

Small extracellular vesicles (sEVs) are cell-derived vesicles of nanoscale size (~30–200 nm) that function as conveyors of information between cells, refecting the cell of their origin and its physiological condition in their content. Valuable information on the shape and even on the composition of individual sEVs can be recorded using transmission electron microscopy (TEM). Unfortunately, sample preparation for TEM image acquisition is a complex procedure, which often leads to noisy images and renders automatic quantifcation of sEVs an extremely difcult task. We present a completely deep-learningbased pipeline for the segmentation of seVs in teM images. our method applies a residual convolutional neural network to obtain fne masks and use the Radon transform for splitting clustered sEVs. Using three manually annotated datasets that cover a natural variability typical for sEV studies, we show that the proposed method outperforms two diferent state-of-the-art approaches in terms of detection and segmentation performance. Furthermore, the diameter and roundness of the segmented vesicles are estimated with an error of less than 10%, which supports the high potential of our method in biological applications.

Links

GA17-05048S, research and development project

Name: Segmentace a trekování živých buněk v multimodálních obrazech

Investor: Czech Science Foundation

GJ17-11776Y, research and development project

Name: Funkční a biochemická analýza extracelulárních váčků z ascitů pacientek s karcinomem vaječníku

Investor: Czech Science Foundation

Citovat

GÓMEZ-DE-MARISCAL, Estibaliz, Martin MAŠKA, Anna KOTRBOVÁ, Vendula POSPÍCHALOVÁ, Pavel MATULA and Arrate MUÑOZ-BARRUTIA. Deep-Learning-Based Segmentation of Small Extracellular Vesicles in Transmission Electron Microscopy Images. Scientific Reports. 2019, vol. 9, No 13211, p. 1-10. ISSN 2045-2322. Available from: https://dx.doi.org/10.1038/s41598-019-49431-3.

@article{1557819,
   author = {GómezanddeandMariscal, Estibaliz and Maška, Martin and Kotrbová, Anna and Pospíchalová, Vendula and Matula, Pavel and MuñozandBarrutia, Arrate},
   article_number = {13211},
   doi = {http://dx.doi.org/10.1038/s41598-019-49431-3},
   keywords = {image segmentation;deep learning;smal extracellular vesicles;transmission electron microscopy},
   language = {eng},
   issn = {2045-2322},
   journal = {Scientific Reports},
   title = {Deep-Learning-Based Segmentation of Small Extracellular Vesicles in Transmission Electron Microscopy Images},
   url = {http://dx.doi.org/10.1038/s41598-019-49431-3},
   volume = {9},
   year = {2019}
}

TY  - JOUR
ID  - 1557819
AU  - Gómez-de-Mariscal, Estibaliz - Maška, Martin - Kotrbová, Anna - Pospíchalová, Vendula - Matula, Pavel - Muñoz-Barrutia, Arrate
PY  - 2019
TI  - Deep-Learning-Based Segmentation of Small Extracellular Vesicles in Transmission Electron Microscopy Images
JF  - Scientific Reports
VL  - 9
IS  - 13211
SP  - 1-10
EP  - 1-10
SN  - 20452322
KW  - image segmentation;deep learning;smal extracellular vesicles;transmission electron microscopy
UR  - http://dx.doi.org/10.1038/s41598-019-49431-3
L2  - http://dx.doi.org/10.1038/s41598-019-49431-3
N2  - Small extracellular vesicles (sEVs) are cell-derived vesicles of nanoscale size (~30–200 nm) that function as conveyors of information between cells, refecting the cell of their origin and its physiological condition in their content. Valuable information on the shape and even on the composition of individual sEVs can be recorded using transmission electron microscopy (TEM). Unfortunately, sample preparation for TEM image acquisition is a complex procedure, which often leads to noisy images and renders automatic quantifcation of sEVs an extremely difcult task. We present a completely deep-learningbased pipeline for the segmentation of seVs in teM images. our method applies a residual convolutional neural network to obtain fne masks and use the Radon transform for splitting clustered sEVs. Using three manually annotated datasets that cover a natural variability typical for sEV studies, we show that the proposed method outperforms two diferent state-of-the-art approaches in terms of detection and segmentation performance. Furthermore, the diameter and roundness of the segmented vesicles are estimated with an error of less than 10%, which supports the high potential of our method in biological applications.
ER  -

GÓMEZ-DE-MARISCAL, Estibaliz, Martin MAŠKA, Anna KOTRBOVÁ, Vendula POSPÍCHALOVÁ, Pavel MATULA and Arrate MUÑOZ-BARRUTIA. Deep-Learning-Based Segmentation of Small Extracellular Vesicles in Transmission Electron Microscopy Images. \textit{Scientific Reports}. 2019, vol.~9, No~13211, p.~1-10. ISSN~2045-2322. Available from: https://dx.doi.org/10.1038/s41598-019-49431-3.

Detailed Information on Publication Record