Skip to main content

Estimation of lung volume changes from frontal and lateral views of dynamic chest radiography using a convolutional neural network model: A computational phantom study

Publication ,  Conference
Ishihara, N; Tanaka, R; Segars, WP; Abadi, E; Samei, E
Published in: Progress in Biomedical Optics and Imaging - Proceedings of SPIE
January 1, 2021

TWe aimed to estimate respiratory changes in lung volumes (i"lung volume) using frontal and lateral dynamic chest radiography (DCR) by employing a convolutional neural network (CNN) learning approach trained and tested using the four-dimensional (4D) extended cardiac-torso (XCAT) phantom. Twenty XCAT phantoms of males (5 normal, 5 overweight, and 5 obese) and females (5 normal) were generated to obtain 4D computed tomography (CT) of a virtual patient. XCAT phantoms were projected in frontal and lateral directions. We estimated lung volumes of the XCAT phantoms using CNN learning techniques. One dataset consisted of a right- or left-half frontal view, a lateral view, and ground truth (GT) knowledge of each phantom in the same respiratory phase. i"lung volume were calculated by subtracting the lung volume estimated at the maximum exhale from that at the maximal inhale, and was compared with i"lung volume calculated from the known GT. i"lung volume was successfully estimated from frontal and lateral DCR images of XCAT phantoms by a CNN learning approach. There was a correlation for i"lung volume between GT and estimation in both lungs. There were no significant differences in the estimation error between the right and left lungs, males and females, and males having different physiques. We confirmed that DCR has potential use in the estimation of i"lung volume, which corresponds to vital capacity (VC) in pulmonary function tests (PFT). Pulmonary function could be assessed by DCR even in patients with infectious diseases who can't do PFT using a spirometer.

Duke Scholars

Published In

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

DOI

ISSN

1605-7422

ISBN

9781510640191

Publication Date

January 1, 2021

Volume

11595
 

Citation

APA
Chicago
ICMJE
MLA
NLM
Ishihara, N., Tanaka, R., Segars, W. P., Abadi, E., & Samei, E. (2021). Estimation of lung volume changes from frontal and lateral views of dynamic chest radiography using a convolutional neural network model: A computational phantom study. In Progress in Biomedical Optics and Imaging - Proceedings of SPIE (Vol. 11595). https://doi.org/10.1117/12.2579948
Ishihara, N., R. Tanaka, W. P. Segars, E. Abadi, and E. Samei. “Estimation of lung volume changes from frontal and lateral views of dynamic chest radiography using a convolutional neural network model: A computational phantom study.” In Progress in Biomedical Optics and Imaging - Proceedings of SPIE, Vol. 11595, 2021. https://doi.org/10.1117/12.2579948.
Ishihara N, Tanaka R, Segars WP, Abadi E, Samei E. Estimation of lung volume changes from frontal and lateral views of dynamic chest radiography using a convolutional neural network model: A computational phantom study. In: Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2021.
Ishihara, N., et al. “Estimation of lung volume changes from frontal and lateral views of dynamic chest radiography using a convolutional neural network model: A computational phantom study.” Progress in Biomedical Optics and Imaging - Proceedings of SPIE, vol. 11595, 2021. Scopus, doi:10.1117/12.2579948.
Ishihara N, Tanaka R, Segars WP, Abadi E, Samei E. Estimation of lung volume changes from frontal and lateral views of dynamic chest radiography using a convolutional neural network model: A computational phantom study. Progress in Biomedical Optics and Imaging - Proceedings of SPIE. 2021.

Published In

Progress in Biomedical Optics and Imaging - Proceedings of SPIE

DOI

ISSN

1605-7422

ISBN

9781510640191

Publication Date

January 1, 2021

Volume

11595