Lung mass density analysis using deep neural network and lung ultrasound surface wave elastography

Boran Zhou, Xiaoming Zhang

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Lung mass density is directly associated with lung pathology. Computed Tomography (CT) evaluates lung pathology using the Hounsfield unit (HU) but not lung density directly. We have developed a lung ultrasound surface wave elastography (LUSWE) technique to measure the surface wave speed of superficial lung tissue. The objective of this study was to develop a method for analyzing lung mass density of superficial lung tissue using a deep neural network (DNN) and synthetic data of wave speed measurements with LUSWE. The synthetic training dataset of surface wave speed, excitation frequency, lung mass density, and viscoelasticity from LUSWE (788,000 in total) was used to train the DNN model. The DNN was composed of 3 hidden layers of 1024 neurons for each layer and trained for 10 epochs with a batch size of 4096 and a learning rate of 0.001 with three types of optimizers. The test dataset (4000) of wave speeds at three excitation frequencies (100, 150, and 200 Hz) and shear elasticity of superficial lung tissue was used to predict the lung density and evaluate its accuracy compared with predefined lung mass densities. This technique was then validated on a sponge phantom experiment. The obtained results showed that predictions matched well with test dataset (validation accuracy is 0.992) and experimental data in the sponge phantom experiment. This method may be useful to analyze lung mass density by using the DNN model together with the surface wave speed and lung stiffness measurements.

Original languageEnglish (US)
Pages (from-to)173-177
Number of pages5
JournalUltrasonics
Volume89
DOIs
StatePublished - Sep 1 2018

Fingerprint

lungs
surface waves
pathology
viscoelasticity
neurons
learning
excitation
stiffness
education
elastic properties
tomography

Keywords

  • Deep neural network
  • Lung density
  • Lung disease
  • Lung ultrasound surface wave elastography

ASJC Scopus subject areas

  • Acoustics and Ultrasonics

Cite this

Lung mass density analysis using deep neural network and lung ultrasound surface wave elastography. / Zhou, Boran; Zhang, Xiaoming.

In: Ultrasonics, Vol. 89, 01.09.2018, p. 173-177.

Research output: Contribution to journalArticle

@article{9f9c86afa59744bda2f972a85d333697,
title = "Lung mass density analysis using deep neural network and lung ultrasound surface wave elastography",
abstract = "Lung mass density is directly associated with lung pathology. Computed Tomography (CT) evaluates lung pathology using the Hounsfield unit (HU) but not lung density directly. We have developed a lung ultrasound surface wave elastography (LUSWE) technique to measure the surface wave speed of superficial lung tissue. The objective of this study was to develop a method for analyzing lung mass density of superficial lung tissue using a deep neural network (DNN) and synthetic data of wave speed measurements with LUSWE. The synthetic training dataset of surface wave speed, excitation frequency, lung mass density, and viscoelasticity from LUSWE (788,000 in total) was used to train the DNN model. The DNN was composed of 3 hidden layers of 1024 neurons for each layer and trained for 10 epochs with a batch size of 4096 and a learning rate of 0.001 with three types of optimizers. The test dataset (4000) of wave speeds at three excitation frequencies (100, 150, and 200 Hz) and shear elasticity of superficial lung tissue was used to predict the lung density and evaluate its accuracy compared with predefined lung mass densities. This technique was then validated on a sponge phantom experiment. The obtained results showed that predictions matched well with test dataset (validation accuracy is 0.992) and experimental data in the sponge phantom experiment. This method may be useful to analyze lung mass density by using the DNN model together with the surface wave speed and lung stiffness measurements.",
keywords = "Deep neural network, Lung density, Lung disease, Lung ultrasound surface wave elastography",
author = "Boran Zhou and Xiaoming Zhang",
year = "2018",
month = "9",
day = "1",
doi = "10.1016/j.ultras.2018.05.011",
language = "English (US)",
volume = "89",
pages = "173--177",
journal = "Ultrasonics",
issn = "0041-624X",
publisher = "Elsevier",

}

TY - JOUR

T1 - Lung mass density analysis using deep neural network and lung ultrasound surface wave elastography

AU - Zhou, Boran

AU - Zhang, Xiaoming

PY - 2018/9/1

Y1 - 2018/9/1

N2 - Lung mass density is directly associated with lung pathology. Computed Tomography (CT) evaluates lung pathology using the Hounsfield unit (HU) but not lung density directly. We have developed a lung ultrasound surface wave elastography (LUSWE) technique to measure the surface wave speed of superficial lung tissue. The objective of this study was to develop a method for analyzing lung mass density of superficial lung tissue using a deep neural network (DNN) and synthetic data of wave speed measurements with LUSWE. The synthetic training dataset of surface wave speed, excitation frequency, lung mass density, and viscoelasticity from LUSWE (788,000 in total) was used to train the DNN model. The DNN was composed of 3 hidden layers of 1024 neurons for each layer and trained for 10 epochs with a batch size of 4096 and a learning rate of 0.001 with three types of optimizers. The test dataset (4000) of wave speeds at three excitation frequencies (100, 150, and 200 Hz) and shear elasticity of superficial lung tissue was used to predict the lung density and evaluate its accuracy compared with predefined lung mass densities. This technique was then validated on a sponge phantom experiment. The obtained results showed that predictions matched well with test dataset (validation accuracy is 0.992) and experimental data in the sponge phantom experiment. This method may be useful to analyze lung mass density by using the DNN model together with the surface wave speed and lung stiffness measurements.

AB - Lung mass density is directly associated with lung pathology. Computed Tomography (CT) evaluates lung pathology using the Hounsfield unit (HU) but not lung density directly. We have developed a lung ultrasound surface wave elastography (LUSWE) technique to measure the surface wave speed of superficial lung tissue. The objective of this study was to develop a method for analyzing lung mass density of superficial lung tissue using a deep neural network (DNN) and synthetic data of wave speed measurements with LUSWE. The synthetic training dataset of surface wave speed, excitation frequency, lung mass density, and viscoelasticity from LUSWE (788,000 in total) was used to train the DNN model. The DNN was composed of 3 hidden layers of 1024 neurons for each layer and trained for 10 epochs with a batch size of 4096 and a learning rate of 0.001 with three types of optimizers. The test dataset (4000) of wave speeds at three excitation frequencies (100, 150, and 200 Hz) and shear elasticity of superficial lung tissue was used to predict the lung density and evaluate its accuracy compared with predefined lung mass densities. This technique was then validated on a sponge phantom experiment. The obtained results showed that predictions matched well with test dataset (validation accuracy is 0.992) and experimental data in the sponge phantom experiment. This method may be useful to analyze lung mass density by using the DNN model together with the surface wave speed and lung stiffness measurements.

KW - Deep neural network

KW - Lung density

KW - Lung disease

KW - Lung ultrasound surface wave elastography

UR - http://www.scopus.com/inward/record.url?scp=85047599288&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85047599288&partnerID=8YFLogxK

U2 - 10.1016/j.ultras.2018.05.011

DO - 10.1016/j.ultras.2018.05.011

M3 - Article

C2 - 29852466

AN - SCOPUS:85047599288

VL - 89

SP - 173

EP - 177

JO - Ultrasonics

JF - Ultrasonics

SN - 0041-624X

ER -