Automated super-resolution image processing in ultrasound using machine learning

Kirsten Christensen Jeffries; Markus Schirmer; Jemma Brown; Sevan Harput; Meng Xing Tang; Christopher Dunsby; Paul Aljabar; Robert Eckersley

doi:10.1109/ULTSYM.2017.8091563

Automated super-resolution image processing in ultrasound using machine learning

Kirsten Christensen Jeffries, Markus Schirmer, Jemma Brown, Sevan Harput, Meng Xing Tang, Christopher Dunsby, Paul Aljabar, Robert Eckersley

Imaging and Biomedical Engineering

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

Abstract

Clinical implementation of super-resolution (SR) ultrasound imaging requires accurate single microbubble detection, and would benefit greatly from automation in order to minimize time requirements and user dependence. We present a machine learning based post-processing tool for the application of SR ultrasound imaging, where we utilize superpixelation and support vector machines (SVMs) for foreground detection and signal differentiation.

Original language	English
Title of host publication	2017 IEEE International Ultrasonics Symposium, IUS 2017
Publisher	IEEE Computer Society Press
ISBN (Electronic)	9781538633830
DOIs	https://doi.org/10.1109/ULTSYM.2017.8091563
Publication status	Published - 31 Oct 2017
Event	2017 IEEE International Ultrasonics Symposium, IUS 2017 - Washington, United States Duration: 6 Sept 2017 → 9 Sept 2017

Conference

Conference	2017 IEEE International Ultrasonics Symposium, IUS 2017
Country/Territory	United States
City	Washington
Period	6/09/2017 → 9/09/2017

Access to Document

10.1109/ULTSYM.2017.8091563

Cite this

@inbook{406b4c9651eb453fa979701da48d19b7,

title = "Automated super-resolution image processing in ultrasound using machine learning",

abstract = "Clinical implementation of super-resolution (SR) ultrasound imaging requires accurate single microbubble detection, and would benefit greatly from automation in order to minimize time requirements and user dependence. We present a machine learning based post-processing tool for the application of SR ultrasound imaging, where we utilize superpixelation and support vector machines (SVMs) for foreground detection and signal differentiation.",

author = "Jeffries, {Kirsten Christensen} and Markus Schirmer and Jemma Brown and Sevan Harput and Tang, {Meng Xing} and Christopher Dunsby and Paul Aljabar and Robert Eckersley",

year = "2017",

month = oct,

day = "31",

doi = "10.1109/ULTSYM.2017.8091563",

language = "English",

booktitle = "2017 IEEE International Ultrasonics Symposium, IUS 2017",

publisher = "IEEE Computer Society Press",

note = "2017 IEEE International Ultrasonics Symposium, IUS 2017 ; Conference date: 06-09-2017 Through 09-09-2017",

}

Jeffries, KC, Schirmer, M, Brown, J, Harput, S, Tang, MX, Dunsby, C, Aljabar, P & Eckersley, R 2017, Automated super-resolution image processing in ultrasound using machine learning. in 2017 IEEE International Ultrasonics Symposium, IUS 2017., 8091563, IEEE Computer Society Press, 2017 IEEE International Ultrasonics Symposium, IUS 2017, Washington, United States, 6/09/2017. https://doi.org/10.1109/ULTSYM.2017.8091563

TY - CHAP

T1 - Automated super-resolution image processing in ultrasound using machine learning

AU - Jeffries, Kirsten Christensen

AU - Schirmer, Markus

AU - Brown, Jemma

AU - Harput, Sevan

AU - Tang, Meng Xing

AU - Dunsby, Christopher

AU - Aljabar, Paul

AU - Eckersley, Robert

PY - 2017/10/31

Y1 - 2017/10/31

N2 - Clinical implementation of super-resolution (SR) ultrasound imaging requires accurate single microbubble detection, and would benefit greatly from automation in order to minimize time requirements and user dependence. We present a machine learning based post-processing tool for the application of SR ultrasound imaging, where we utilize superpixelation and support vector machines (SVMs) for foreground detection and signal differentiation.

AB - Clinical implementation of super-resolution (SR) ultrasound imaging requires accurate single microbubble detection, and would benefit greatly from automation in order to minimize time requirements and user dependence. We present a machine learning based post-processing tool for the application of SR ultrasound imaging, where we utilize superpixelation and support vector machines (SVMs) for foreground detection and signal differentiation.

UR - http://www.scopus.com/inward/record.url?scp=85039438683&partnerID=8YFLogxK

U2 - 10.1109/ULTSYM.2017.8091563

DO - 10.1109/ULTSYM.2017.8091563

M3 - Other chapter contribution

AN - SCOPUS:85039438683

BT - 2017 IEEE International Ultrasonics Symposium, IUS 2017

PB - IEEE Computer Society Press

T2 - 2017 IEEE International Ultrasonics Symposium, IUS 2017

Y2 - 6 September 2017 through 9 September 2017

ER -

Automated super-resolution image processing in ultrasound using machine learning

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this