Automatic evaluation of fetal head biometry from ultrasound images using machine learning

Hwa Pyung Kim, Sung Min Lee, Ja Young Kwon, Yejin Park, Kang Cheol Kim, Jin Keun Seo

Research output: Contribution to journalArticle

Abstract

OBJECTIVE: Ultrasound-based fetal biometric measurements, such as head circumference (HC) and biparietal diameter (BPD), are frequently used to evaluate gestational age and diagnose fetal central nervous system pathology. Because manual measurements are operator-dependent and time-consuming, much research is being actively conducted on automated methods. However, the existing automated methods are still not satisfactory in terms of accuracy and reliability, owing to difficulties dealing with various artefacts in ultrasound images. APPROACH: Using the proposed method, a labeled dataset containing 102 ultrasound images was used for training, and validation was performed with 70 ultrasound images. MAIN RESULTS: A success rate of 91.43% and 100% for HC and BPD estimations, respectively, and an accuracy of 87.14% for the plane acceptance check. SIGNIFICANCE: This paper focuses on fetal head biometry and proposes a deep-learning-based method for estimating HC and BPD with a high degree of accuracy and reliability.

Original languageEnglish
Number of pages1
JournalPhysiological measurement
Volume40
Issue number6
DOIs
Publication statusPublished - 2019 Jul 1

Fingerprint

Biometry
Learning systems
Ultrasonics
Head
Neurology
Pathology
Biometrics
Artifacts
Gestational Age
Central Nervous System
Learning
Machine Learning
Research

All Science Journal Classification (ASJC) codes

  • Biophysics
  • Physiology
  • Biomedical Engineering
  • Physiology (medical)

Cite this

Kim, Hwa Pyung ; Lee, Sung Min ; Kwon, Ja Young ; Park, Yejin ; Kim, Kang Cheol ; Seo, Jin Keun. / Automatic evaluation of fetal head biometry from ultrasound images using machine learning. In: Physiological measurement. 2019 ; Vol. 40, No. 6.
@article{c63171f134f0466ba540b001c524166e,
title = "Automatic evaluation of fetal head biometry from ultrasound images using machine learning",
abstract = "OBJECTIVE: Ultrasound-based fetal biometric measurements, such as head circumference (HC) and biparietal diameter (BPD), are frequently used to evaluate gestational age and diagnose fetal central nervous system pathology. Because manual measurements are operator-dependent and time-consuming, much research is being actively conducted on automated methods. However, the existing automated methods are still not satisfactory in terms of accuracy and reliability, owing to difficulties dealing with various artefacts in ultrasound images. APPROACH: Using the proposed method, a labeled dataset containing 102 ultrasound images was used for training, and validation was performed with 70 ultrasound images. MAIN RESULTS: A success rate of 91.43{\%} and 100{\%} for HC and BPD estimations, respectively, and an accuracy of 87.14{\%} for the plane acceptance check. SIGNIFICANCE: This paper focuses on fetal head biometry and proposes a deep-learning-based method for estimating HC and BPD with a high degree of accuracy and reliability.",
author = "Kim, {Hwa Pyung} and Lee, {Sung Min} and Kwon, {Ja Young} and Yejin Park and Kim, {Kang Cheol} and Seo, {Jin Keun}",
year = "2019",
month = "7",
day = "1",
doi = "10.1088/1361-6579/ab21ac",
language = "English",
volume = "40",
journal = "Physiological Measurement",
issn = "0967-3334",
publisher = "IOP Publishing Ltd.",
number = "6",

}

Automatic evaluation of fetal head biometry from ultrasound images using machine learning. / Kim, Hwa Pyung; Lee, Sung Min; Kwon, Ja Young; Park, Yejin; Kim, Kang Cheol; Seo, Jin Keun.

In: Physiological measurement, Vol. 40, No. 6, 01.07.2019.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Automatic evaluation of fetal head biometry from ultrasound images using machine learning

AU - Kim, Hwa Pyung

AU - Lee, Sung Min

AU - Kwon, Ja Young

AU - Park, Yejin

AU - Kim, Kang Cheol

AU - Seo, Jin Keun

PY - 2019/7/1

Y1 - 2019/7/1

N2 - OBJECTIVE: Ultrasound-based fetal biometric measurements, such as head circumference (HC) and biparietal diameter (BPD), are frequently used to evaluate gestational age and diagnose fetal central nervous system pathology. Because manual measurements are operator-dependent and time-consuming, much research is being actively conducted on automated methods. However, the existing automated methods are still not satisfactory in terms of accuracy and reliability, owing to difficulties dealing with various artefacts in ultrasound images. APPROACH: Using the proposed method, a labeled dataset containing 102 ultrasound images was used for training, and validation was performed with 70 ultrasound images. MAIN RESULTS: A success rate of 91.43% and 100% for HC and BPD estimations, respectively, and an accuracy of 87.14% for the plane acceptance check. SIGNIFICANCE: This paper focuses on fetal head biometry and proposes a deep-learning-based method for estimating HC and BPD with a high degree of accuracy and reliability.

AB - OBJECTIVE: Ultrasound-based fetal biometric measurements, such as head circumference (HC) and biparietal diameter (BPD), are frequently used to evaluate gestational age and diagnose fetal central nervous system pathology. Because manual measurements are operator-dependent and time-consuming, much research is being actively conducted on automated methods. However, the existing automated methods are still not satisfactory in terms of accuracy and reliability, owing to difficulties dealing with various artefacts in ultrasound images. APPROACH: Using the proposed method, a labeled dataset containing 102 ultrasound images was used for training, and validation was performed with 70 ultrasound images. MAIN RESULTS: A success rate of 91.43% and 100% for HC and BPD estimations, respectively, and an accuracy of 87.14% for the plane acceptance check. SIGNIFICANCE: This paper focuses on fetal head biometry and proposes a deep-learning-based method for estimating HC and BPD with a high degree of accuracy and reliability.

UR - http://www.scopus.com/inward/record.url?scp=85069266515&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85069266515&partnerID=8YFLogxK

U2 - 10.1088/1361-6579/ab21ac

DO - 10.1088/1361-6579/ab21ac

M3 - Article

C2 - 31091515

AN - SCOPUS:85069266515

VL - 40

JO - Physiological Measurement

JF - Physiological Measurement

SN - 0967-3334

IS - 6

ER -