Scanner independent deep learning-based segmentation framework applied to mouse embryos

Orlando Aristizabal; Daniel H. Turnbull; Jeffrey A. Ketterling; Yao Wang; Ziming Qiu; Tongda Xu; Hannah Goldman; Jonathan Mamou

doi:10.1109/IUS46767.2020.9251626

Scanner independent deep learning-based segmentation framework applied to mouse embryos

Orlando Aristizabal, Daniel H. Turnbull, Jeffrey A. Ketterling, Yao Wang, Ziming Qiu, Tongda Xu, Hannah Goldman, Jonathan Mamou

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

Abstract

We have applied a deep learning framework, trained on mouse embryo images acquired with a 40 MHz annular array, to volumetric data acquired with a VisualSonics Vevo 3100 commercial scanner using a 40-MHz linear array. The deep learning framework was robust enough to accurately segment out the body and the brain ventricle from the 3D data generated by the commercial scanner. These results show that there is no need to retrain the algorithm with hundreds of new manually segmented datasets.

Original language	English (US)
Title of host publication	IUS 2020 - International Ultrasonics Symposium, Proceedings
Publisher	IEEE Computer Society
ISBN (Electronic)	9781728154480
DOIs	https://doi.org/10.1109/IUS46767.2020.9251626
State	Published - Sep 7 2020
Event	2020 IEEE International Ultrasonics Symposium, IUS 2020 - Las Vegas, United States Duration: Sep 7 2020 → Sep 11 2020

Publication series

Name	IEEE International Ultrasonics Symposium, IUS
Volume	2020-September
ISSN (Print)	1948-5719
ISSN (Electronic)	1948-5727

Conference

Conference	2020 IEEE International Ultrasonics Symposium, IUS 2020
Country/Territory	United States
City	Las Vegas
Period	9/7/20 → 9/11/20

Keywords

Automatic segmentation
Convolutional network
Mouse embryo

ASJC Scopus subject areas

Acoustics and Ultrasonics

Access to Document

10.1109/IUS46767.2020.9251626

Cite this

Aristizabal, O., Turnbull, D. H., Ketterling, J. A., Wang, Y., Qiu, Z., Xu, T., Goldman, H., & Mamou, J. (2020). Scanner independent deep learning-based segmentation framework applied to mouse embryos. In IUS 2020 - International Ultrasonics Symposium, Proceedings Article 9251626 (IEEE International Ultrasonics Symposium, IUS; Vol. 2020-September). IEEE Computer Society. https://doi.org/10.1109/IUS46767.2020.9251626

Scanner independent deep learning-based segmentation framework applied to mouse embryos. / Aristizabal, Orlando; Turnbull, Daniel H.; Ketterling, Jeffrey A. et al.
IUS 2020 - International Ultrasonics Symposium, Proceedings. IEEE Computer Society, 2020. 9251626 (IEEE International Ultrasonics Symposium, IUS; Vol. 2020-September).

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

Aristizabal, O, Turnbull, DH, Ketterling, JA, Wang, Y, Qiu, Z, Xu, T, Goldman, H & Mamou, J 2020, Scanner independent deep learning-based segmentation framework applied to mouse embryos. in IUS 2020 - International Ultrasonics Symposium, Proceedings., 9251626, IEEE International Ultrasonics Symposium, IUS, vol. 2020-September, IEEE Computer Society, 2020 IEEE International Ultrasonics Symposium, IUS 2020, Las Vegas, United States, 9/7/20. https://doi.org/10.1109/IUS46767.2020.9251626

@inproceedings{7a506f19903b4370960d6bb5f5874551,

title = "Scanner independent deep learning-based segmentation framework applied to mouse embryos",

abstract = "We have applied a deep learning framework, trained on mouse embryo images acquired with a 40 MHz annular array, to volumetric data acquired with a VisualSonics Vevo 3100 commercial scanner using a 40-MHz linear array. The deep learning framework was robust enough to accurately segment out the body and the brain ventricle from the 3D data generated by the commercial scanner. These results show that there is no need to retrain the algorithm with hundreds of new manually segmented datasets.",

keywords = "Automatic segmentation, Convolutional network, Mouse embryo",

author = "Orlando Aristizabal and Turnbull, {Daniel H.} and Ketterling, {Jeffrey A.} and Yao Wang and Ziming Qiu and Tongda Xu and Hannah Goldman and Jonathan Mamou",

note = "Publisher Copyright: {\textcopyright} 2020 IEEE.; 2020 IEEE International Ultrasonics Symposium, IUS 2020 ; Conference date: 07-09-2020 Through 11-09-2020",

year = "2020",

month = sep,

day = "7",

doi = "10.1109/IUS46767.2020.9251626",

language = "English (US)",

series = "IEEE International Ultrasonics Symposium, IUS",

publisher = "IEEE Computer Society",

booktitle = "IUS 2020 - International Ultrasonics Symposium, Proceedings",

}

TY - GEN

T1 - Scanner independent deep learning-based segmentation framework applied to mouse embryos

AU - Aristizabal, Orlando

AU - Turnbull, Daniel H.

AU - Ketterling, Jeffrey A.

AU - Wang, Yao

AU - Qiu, Ziming

AU - Xu, Tongda

AU - Goldman, Hannah

AU - Mamou, Jonathan

PY - 2020/9/7

Y1 - 2020/9/7

N2 - We have applied a deep learning framework, trained on mouse embryo images acquired with a 40 MHz annular array, to volumetric data acquired with a VisualSonics Vevo 3100 commercial scanner using a 40-MHz linear array. The deep learning framework was robust enough to accurately segment out the body and the brain ventricle from the 3D data generated by the commercial scanner. These results show that there is no need to retrain the algorithm with hundreds of new manually segmented datasets.

AB - We have applied a deep learning framework, trained on mouse embryo images acquired with a 40 MHz annular array, to volumetric data acquired with a VisualSonics Vevo 3100 commercial scanner using a 40-MHz linear array. The deep learning framework was robust enough to accurately segment out the body and the brain ventricle from the 3D data generated by the commercial scanner. These results show that there is no need to retrain the algorithm with hundreds of new manually segmented datasets.

KW - Automatic segmentation

KW - Convolutional network

KW - Mouse embryo

UR - http://www.scopus.com/inward/record.url?scp=85097872481&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85097872481&partnerID=8YFLogxK

U2 - 10.1109/IUS46767.2020.9251626

DO - 10.1109/IUS46767.2020.9251626

M3 - Conference contribution

AN - SCOPUS:85097872481

T3 - IEEE International Ultrasonics Symposium, IUS

BT - IUS 2020 - International Ultrasonics Symposium, Proceedings

PB - IEEE Computer Society

T2 - 2020 IEEE International Ultrasonics Symposium, IUS 2020

Y2 - 7 September 2020 through 11 September 2020

ER -

Scanner independent deep learning-based segmentation framework applied to mouse embryos

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Cite this