Automated particle and cell phenotyping using object recognition and tracking based on machine learning algorithms

Gergely B. Hantos; Gergely Simon; Matčj Hejda; Anne L. Bernassau; Marc P. Y. Desmulliez

doi:10.1109/IUS52206.2021.9593615

Automated particle and cell phenotyping using object recognition and tracking based on machine learning algorithms

Gergely B. Hantos, Gergely Simon, Matčj Hejda, Anne L. Bernassau, Marc P. Y. Desmulliez

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

1 Citation (Scopus)

15 Downloads (Pure)

Abstract

Knowledge of the acoustic contrast factor of biological entities can provide useful information regarding defects or cell stages in biological applications of microfluidics. It is also a valuable input in the design of acoustic particle manipulators or sorters. To calculate the contrast factor, the required physical properties can be obtained using contact measurements, but these are not desirable as they can damage particles or cells. In indirect approaches, reference particles are employed and the behavior of the unknown particles or cells is compared with that of the reference particles. Here we propose an image recognition-based framework to automate the entire characterization workflow and obtain acoustic contrast factor without intervention. We use 10 micron diameter polystyrene particles as reference and obtain contrast of 6 and 15 micron particle as a proof of concept. Excellent agreement with expected value within 5% is seen for the 15 micron diameter particles.

Original language	English
Title of host publication	2021 IEEE International Ultrasonics Symposium (IUS)
Place of Publication	Piscataway, N.J.
Publisher	IEEE
Pages	1-4
Number of pages	4
ISBN (Electronic)	9781665403559
ISBN (Print)	9781665447775
DOIs	https://doi.org/10.1109/IUS52206.2021.9593615
Publication status	Published - 13 Nov 2021
Event	2021 IEEE International Ultrasonics Symposium (IUS) - Virtual, Xi'an, China Duration: 11 Sept 2021 → 16 Sept 2021 https://2021.ieee-ius.org/

Publication series

Name	IEEE Ultrasonics Symposium
Publisher	IEEE
ISSN (Print)	1948-5719
ISSN (Electronic)	1948-5727

Conference

Conference	2021 IEEE International Ultrasonics Symposium (IUS)
Abbreviated title	IUS 2021
Country/Territory	China
City	Xi'an
Period	11/09/21 → 16/09/21
Internet address	https://2021.ieee-ius.org/

Keywords

microjluidics
machine learning
object recognition
acoustic contrast factor
mechanical characterization
micrometers
machine learning algorithms
image recognition
particle measurements
manipulators
acoustics
biology

Access to Document

10.1109/IUS52206.2021.9593615

Hantos-etal-IUS-2021-Automated-particle-and-cell-phenotyping-using-object-recognition-and-tracking-based-on-machine-learningAccepted author manuscript, 1.08 MBLicence: Strath_1

Cite this

@inproceedings{3b833f2436734610b2e42e1e91ff3351,

title = "Automated particle and cell phenotyping using object recognition and tracking based on machine learning algorithms",

abstract = "Knowledge of the acoustic contrast factor of biological entities can provide useful information regarding defects or cell stages in biological applications of microfluidics. It is also a valuable input in the design of acoustic particle manipulators or sorters. To calculate the contrast factor, the required physical properties can be obtained using contact measurements, but these are not desirable as they can damage particles or cells. In indirect approaches, reference particles are employed and the behavior of the unknown particles or cells is compared with that of the reference particles. Here we propose an image recognition-based framework to automate the entire characterization workflow and obtain acoustic contrast factor without intervention. We use 10 micron diameter polystyrene particles as reference and obtain contrast of 6 and 15 micron particle as a proof of concept. Excellent agreement with expected value within 5% is seen for the 15 micron diameter particles.",

keywords = "microjluidics, machine learning, object recognition, acoustic contrast factor, mechanical characterization, micrometers, machine learning algorithms, image recognition, particle measurements, manipulators, acoustics, biology",

author = "Hantos, {Gergely B.} and Gergely Simon and Mat{\v c}j Hejda and Bernassau, {Anne L.} and Desmulliez, {Marc P. Y.}",

note = "{\textcopyright} 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.; 2021 IEEE International Ultrasonics Symposium (IUS), IUS 2021 ; Conference date: 11-09-2021 Through 16-09-2021",

year = "2021",

month = nov,

day = "13",

doi = "10.1109/IUS52206.2021.9593615",

language = "English",

isbn = "9781665447775",

series = "IEEE Ultrasonics Symposium",

publisher = "IEEE",

pages = "1--4",

booktitle = "2021 IEEE International Ultrasonics Symposium (IUS)",

url = "https://2021.ieee-ius.org/",

}

Hantos, GB, Simon, G, Hejda, M, Bernassau, AL & Desmulliez, MPY 2021, Automated particle and cell phenotyping using object recognition and tracking based on machine learning algorithms. in 2021 IEEE International Ultrasonics Symposium (IUS). IEEE Ultrasonics Symposium, IEEE, Piscataway, N.J., pp. 1-4, 2021 IEEE International Ultrasonics Symposium (IUS), Xi'an, China, 11/09/21. https://doi.org/10.1109/IUS52206.2021.9593615

Automated particle and cell phenotyping using object recognition and tracking based on machine learning algorithms. / Hantos, Gergely B.; Simon, Gergely; Hejda, Matčj et al.
2021 IEEE International Ultrasonics Symposium (IUS). Piscataway, N.J.: IEEE, 2021. p. 1-4 (IEEE Ultrasonics Symposium).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Automated particle and cell phenotyping using object recognition and tracking based on machine learning algorithms

AU - Hantos, Gergely B.

AU - Simon, Gergely

AU - Hejda, Matčj

AU - Bernassau, Anne L.

AU - Desmulliez, Marc P. Y.

N1 - © 2021 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting /republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2021/11/13

Y1 - 2021/11/13

N2 - Knowledge of the acoustic contrast factor of biological entities can provide useful information regarding defects or cell stages in biological applications of microfluidics. It is also a valuable input in the design of acoustic particle manipulators or sorters. To calculate the contrast factor, the required physical properties can be obtained using contact measurements, but these are not desirable as they can damage particles or cells. In indirect approaches, reference particles are employed and the behavior of the unknown particles or cells is compared with that of the reference particles. Here we propose an image recognition-based framework to automate the entire characterization workflow and obtain acoustic contrast factor without intervention. We use 10 micron diameter polystyrene particles as reference and obtain contrast of 6 and 15 micron particle as a proof of concept. Excellent agreement with expected value within 5% is seen for the 15 micron diameter particles.

AB - Knowledge of the acoustic contrast factor of biological entities can provide useful information regarding defects or cell stages in biological applications of microfluidics. It is also a valuable input in the design of acoustic particle manipulators or sorters. To calculate the contrast factor, the required physical properties can be obtained using contact measurements, but these are not desirable as they can damage particles or cells. In indirect approaches, reference particles are employed and the behavior of the unknown particles or cells is compared with that of the reference particles. Here we propose an image recognition-based framework to automate the entire characterization workflow and obtain acoustic contrast factor without intervention. We use 10 micron diameter polystyrene particles as reference and obtain contrast of 6 and 15 micron particle as a proof of concept. Excellent agreement with expected value within 5% is seen for the 15 micron diameter particles.

KW - microjluidics

KW - machine learning

KW - object recognition

KW - acoustic contrast factor

KW - mechanical characterization

KW - micrometers

KW - machine learning algorithms

KW - image recognition

KW - particle measurements

KW - manipulators

KW - acoustics

KW - biology

U2 - 10.1109/IUS52206.2021.9593615

DO - 10.1109/IUS52206.2021.9593615

M3 - Conference contribution book

SN - 9781665447775

T3 - IEEE Ultrasonics Symposium

SP - 1

EP - 4

BT - 2021 IEEE International Ultrasonics Symposium (IUS)

PB - IEEE

CY - Piscataway, N.J.

T2 - 2021 IEEE International Ultrasonics Symposium (IUS)

Y2 - 11 September 2021 through 16 September 2021

ER -

Automated particle and cell phenotyping using object recognition and tracking based on machine learning algorithms

Abstract

Publication series

Conference

Keywords

Access to Document

Fingerprint

Cite this