Automating cardiothoracic ratio measurements in chest X-rays
Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Standard
Automating cardiothoracic ratio measurements in chest X-rays. / Kiselev, Semen; Maksudov, Bulat; Mustafaev, Tamerlan; Kuleev, Ramil; Ibragimov, Bulat.
2021 International Conference "Nonlinearity, Information and Robotics", NIR 2021. IEEE, 2021.Research output: Chapter in Book/Report/Conference proceeding › Article in proceedings › Research › peer-review
Harvard
APA
Vancouver
Author
Bibtex
}
RIS
TY - GEN
T1 - Automating cardiothoracic ratio measurements in chest X-rays
AU - Kiselev, Semen
AU - Maksudov, Bulat
AU - Mustafaev, Tamerlan
AU - Kuleev, Ramil
AU - Ibragimov, Bulat
N1 - Publisher Copyright: © 2021 IEEE.
PY - 2021
Y1 - 2021
N2 - The analysis of the positions, shapes, and sizes of thoracic organs is an internationally established practice for radiologists. The considerable amount of time spent on manual measurements of roentgenographic features reveals the need for a computerized approach for the automation of these measurements. In this work, we introduce a new way for the annotation of the chest x-ray data and evaluation of the most commonly-calculated morphometric parameter - cardiothoracic ratio. The measurement of interest was defined as ratio of line segments outlining the heart and the distance between two most lateral landmarks on lung fields. Using a manually annotated dataset, we developed a hourglass-based deep learning-based model to detect these landmarks and perform the measurement. We found that the predictions of the proposed solution differ from the annotation of an expert radiologist in 9.8mm error measured in terms of the mean Euclidean distance.
AB - The analysis of the positions, shapes, and sizes of thoracic organs is an internationally established practice for radiologists. The considerable amount of time spent on manual measurements of roentgenographic features reveals the need for a computerized approach for the automation of these measurements. In this work, we introduce a new way for the annotation of the chest x-ray data and evaluation of the most commonly-calculated morphometric parameter - cardiothoracic ratio. The measurement of interest was defined as ratio of line segments outlining the heart and the distance between two most lateral landmarks on lung fields. Using a manually annotated dataset, we developed a hourglass-based deep learning-based model to detect these landmarks and perform the measurement. We found that the predictions of the proposed solution differ from the annotation of an expert radiologist in 9.8mm error measured in terms of the mean Euclidean distance.
U2 - 10.1109/NIR52917.2021.9666142
DO - 10.1109/NIR52917.2021.9666142
M3 - Article in proceedings
AN - SCOPUS:85124700087
BT - 2021 International Conference "Nonlinearity, Information and Robotics", NIR 2021
PB - IEEE
T2 - 2021 International Conference "Nonlinearity, Information and Robotics", NIR 2021
Y2 - 26 August 2021 through 29 August 2021
ER -
ID: 306987473