A Kernel Density Estimation Based Quality Metric for Quality Assessment of Obstetric Ultrasound Video

Jong Kwon; Jianbo Jiao; Alice Self; Julia Alison Noble; Aris Papageorghiou

doi:10.1007/978-3-031-39539-0_12

A Kernel Density Estimation Based Quality Metric for Quality Assessment of Obstetric Ultrasound Video

Jong Kwon^*, Jianbo Jiao, Alice Self, Julia Alison Noble, Aris Papageorghiou

^*Corresponding author for this work

Computer Science

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

Abstract

Simplified ultrasound scanning protocols (sweeps) have been developed to reduce the high skill required to perform a regular obstetric ultrasound examination. However, without automated quality assessment of the video, the utility of such protocols in clinical practice is limited. An automated quality assessment algorithm is proposed that applies an object detector to detect fetal anatomies within ultrasound videos. Kernel density estimation is applied to the bounding box annotations to estimate a probability density function of certain bounding box properties such as the spatial and temporal position during the sweeps. This allows quantifying how well the spatio-temporal position of anatomies in a sweep agrees with previously seen data as a quality metric. The new quality metric is compared to other metrics of quality such as the confidence of the object detector model. The source code is available at: https://github.com/kwon-j/KDE-UltrasoundQA.

Original language	English
Title of host publication	Trustworthy Machine Learning for Healthcare
Subtitle of host publication	First International Workshop, TML4H 2023, Virtual Event, May 4, 2023, Proceedings
Editors	Hao Chen, Luyang Luo
Publisher	Springer
Pages	134-146
Number of pages	13
Edition	1
ISBN (Electronic)	9783031395390
ISBN (Print)	9783031395383
DOIs	https://doi.org/10.1007/978-3-031-39539-0_12
Publication status	Published - 31 Jul 2023
Event	Trustworthy Machine Learning for Healthcare - First International Workshop, TML4H 2023, Proceedings - Virtual, Online Duration: 4 May 2023 → 4 May 2023

Publication series

Name	Lecture Notes in Computer Science
Volume	13932
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	Trustworthy Machine Learning for Healthcare - First International Workshop, TML4H 2023, Proceedings
City	Virtual, Online
Period	4/05/23 → 4/05/23

Bibliographical note

Funding Information:
We thank the reviewers for their helpful feedback. Jong Kwon is supported by the EPSRC Center for Doctoral Training in Health Data Science (EP/S02428X/1). CALOPUS is supported by EPSRC GCRF grant (EP/R013853/1).

Publisher Copyright:
© 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

Keywords

kernel density estimation
Quality assessment
ultrasound

ASJC Scopus subject areas

Theoretical Computer Science
General Computer Science

Access to Document

10.1007/978-3-031-39539-0_12

https://jianbojiao.com/pdfs/tml4h.pdf

Cite this

Kwon, J., Jiao, J., Self, A., Alison Noble, J., & Papageorghiou, A. (2023). A Kernel Density Estimation Based Quality Metric for Quality Assessment of Obstetric Ultrasound Video. In H. Chen, & L. Luo (Eds.), Trustworthy Machine Learning for Healthcare: First International Workshop, TML4H 2023, Virtual Event, May 4, 2023, Proceedings (1 ed., pp. 134-146). (Lecture Notes in Computer Science; Vol. 13932). Springer. https://doi.org/10.1007/978-3-031-39539-0_12

Kwon, Jong ; Jiao, Jianbo ; Self, Alice et al. / A Kernel Density Estimation Based Quality Metric for Quality Assessment of Obstetric Ultrasound Video. Trustworthy Machine Learning for Healthcare: First International Workshop, TML4H 2023, Virtual Event, May 4, 2023, Proceedings. editor / Hao Chen ; Luyang Luo. 1. ed. Springer, 2023. pp. 134-146 (Lecture Notes in Computer Science).

@inproceedings{2220729bc30f47e2998d161ff6fad61d,

title = "A Kernel Density Estimation Based Quality Metric for Quality Assessment of Obstetric Ultrasound Video",

abstract = "Simplified ultrasound scanning protocols (sweeps) have been developed to reduce the high skill required to perform a regular obstetric ultrasound examination. However, without automated quality assessment of the video, the utility of such protocols in clinical practice is limited. An automated quality assessment algorithm is proposed that applies an object detector to detect fetal anatomies within ultrasound videos. Kernel density estimation is applied to the bounding box annotations to estimate a probability density function of certain bounding box properties such as the spatial and temporal position during the sweeps. This allows quantifying how well the spatio-temporal position of anatomies in a sweep agrees with previously seen data as a quality metric. The new quality metric is compared to other metrics of quality such as the confidence of the object detector model. The source code is available at: https://github.com/kwon-j/KDE-UltrasoundQA.",

keywords = "kernel density estimation, Quality assessment, ultrasound",

author = "Jong Kwon and Jianbo Jiao and Alice Self and {Alison Noble}, Julia and Aris Papageorghiou",

note = "Funding Information: We thank the reviewers for their helpful feedback. Jong Kwon is supported by the EPSRC Center for Doctoral Training in Health Data Science (EP/S02428X/1). CALOPUS is supported by EPSRC GCRF grant (EP/R013853/1). Publisher Copyright: {\textcopyright} 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.; Trustworthy Machine Learning for Healthcare - First International Workshop, TML4H 2023, Proceedings ; Conference date: 04-05-2023 Through 04-05-2023",

year = "2023",

month = jul,

day = "31",

doi = "10.1007/978-3-031-39539-0_12",

language = "English",

isbn = "9783031395383",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "134--146",

editor = "Hao Chen and Luyang Luo",

booktitle = "Trustworthy Machine Learning for Healthcare",

edition = "1",

}

Kwon, J, Jiao, J, Self, A, Alison Noble, J & Papageorghiou, A 2023, A Kernel Density Estimation Based Quality Metric for Quality Assessment of Obstetric Ultrasound Video. in H Chen & L Luo (eds), Trustworthy Machine Learning for Healthcare: First International Workshop, TML4H 2023, Virtual Event, May 4, 2023, Proceedings. 1 edn, Lecture Notes in Computer Science, vol. 13932, Springer, pp. 134-146, Trustworthy Machine Learning for Healthcare - First International Workshop, TML4H 2023, Proceedings, Virtual, Online, 4/05/23. https://doi.org/10.1007/978-3-031-39539-0_12

A Kernel Density Estimation Based Quality Metric for Quality Assessment of Obstetric Ultrasound Video. / Kwon, Jong; Jiao, Jianbo; Self, Alice et al.
Trustworthy Machine Learning for Healthcare: First International Workshop, TML4H 2023, Virtual Event, May 4, 2023, Proceedings. ed. / Hao Chen; Luyang Luo. 1. ed. Springer, 2023. p. 134-146 (Lecture Notes in Computer Science; Vol. 13932).

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

TY - GEN

T1 - A Kernel Density Estimation Based Quality Metric for Quality Assessment of Obstetric Ultrasound Video

AU - Kwon, Jong

AU - Jiao, Jianbo

AU - Self, Alice

AU - Alison Noble, Julia

AU - Papageorghiou, Aris

N1 - Funding Information: We thank the reviewers for their helpful feedback. Jong Kwon is supported by the EPSRC Center for Doctoral Training in Health Data Science (EP/S02428X/1). CALOPUS is supported by EPSRC GCRF grant (EP/R013853/1). Publisher Copyright: © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

PY - 2023/7/31

Y1 - 2023/7/31

N2 - Simplified ultrasound scanning protocols (sweeps) have been developed to reduce the high skill required to perform a regular obstetric ultrasound examination. However, without automated quality assessment of the video, the utility of such protocols in clinical practice is limited. An automated quality assessment algorithm is proposed that applies an object detector to detect fetal anatomies within ultrasound videos. Kernel density estimation is applied to the bounding box annotations to estimate a probability density function of certain bounding box properties such as the spatial and temporal position during the sweeps. This allows quantifying how well the spatio-temporal position of anatomies in a sweep agrees with previously seen data as a quality metric. The new quality metric is compared to other metrics of quality such as the confidence of the object detector model. The source code is available at: https://github.com/kwon-j/KDE-UltrasoundQA.

AB - Simplified ultrasound scanning protocols (sweeps) have been developed to reduce the high skill required to perform a regular obstetric ultrasound examination. However, without automated quality assessment of the video, the utility of such protocols in clinical practice is limited. An automated quality assessment algorithm is proposed that applies an object detector to detect fetal anatomies within ultrasound videos. Kernel density estimation is applied to the bounding box annotations to estimate a probability density function of certain bounding box properties such as the spatial and temporal position during the sweeps. This allows quantifying how well the spatio-temporal position of anatomies in a sweep agrees with previously seen data as a quality metric. The new quality metric is compared to other metrics of quality such as the confidence of the object detector model. The source code is available at: https://github.com/kwon-j/KDE-UltrasoundQA.

KW - kernel density estimation

KW - Quality assessment

KW - ultrasound

UR - http://www.scopus.com/inward/record.url?scp=85172236139&partnerID=8YFLogxK

U2 - 10.1007/978-3-031-39539-0_12

DO - 10.1007/978-3-031-39539-0_12

M3 - Conference contribution

AN - SCOPUS:85172236139

SN - 9783031395383

T3 - Lecture Notes in Computer Science

SP - 134

EP - 146

BT - Trustworthy Machine Learning for Healthcare

A2 - Chen, Hao

A2 - Luo, Luyang

PB - Springer

T2 - Trustworthy Machine Learning for Healthcare - First International Workshop, TML4H 2023, Proceedings

Y2 - 4 May 2023 through 4 May 2023

ER -

Kwon J, Jiao J, Self A, Alison Noble J, Papageorghiou A. A Kernel Density Estimation Based Quality Metric for Quality Assessment of Obstetric Ultrasound Video. In Chen H, Luo L, editors, Trustworthy Machine Learning for Healthcare: First International Workshop, TML4H 2023, Virtual Event, May 4, 2023, Proceedings. 1 ed. Springer. 2023. p. 134-146. (Lecture Notes in Computer Science). Epub 2023 Jul 30. doi: 10.1007/978-3-031-39539-0_12