Quantification of image texture in X‐ray phase‐contrast‐enhanced projection images of in vivo mouse lungs observed at varied inflation pressures
Abstract To date, there are very limited noninvasive, regional assays of in vivo lung microstructure near the alveolar level. It has been suggested that x‐ray phase‐contrast enhanced imaging reveals information about the air volume of the lung; however, the image texture information in these images...
Main Authors: | , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
Wiley
2019-08-01
|
Series: | Physiological Reports |
Subjects: | |
Online Access: | https://doi.org/10.14814/phy2.14208 |
id |
doaj-8b2d0ac34448455994501ade7e50edaf |
---|---|
record_format |
Article |
spelling |
doaj-8b2d0ac34448455994501ade7e50edaf2020-11-25T01:19:24ZengWileyPhysiological Reports2051-817X2019-08-01716n/an/a10.14814/phy2.14208Quantification of image texture in X‐ray phase‐contrast‐enhanced projection images of in vivo mouse lungs observed at varied inflation pressuresFrank J. Brooks0Sean P. Gunsten1Sunil K. Vasireddi2Steven L. Brody3Mark A. Anastasio4Department of Bioengineering University of Illinois at Urbana‐Champaign Urbana IllinoisDepartment of Internal Medicine Washington University School of Medicine St. Louis MissouriHeart and Vascular Center MetroHealth Campus at Case Western Reserve University Cleveland OhioDepartment of Internal Medicine Washington University School of Medicine St. Louis MissouriDepartment of Bioengineering University of Illinois at Urbana‐Champaign Urbana IllinoisAbstract To date, there are very limited noninvasive, regional assays of in vivo lung microstructure near the alveolar level. It has been suggested that x‐ray phase‐contrast enhanced imaging reveals information about the air volume of the lung; however, the image texture information in these images remains underutilized. Projection images of in vivo mouse lungs were acquired via a tabletop, propagation‐based, X‐ray phase‐contrast imaging system. Anesthetized mice were mechanically ventilated in an upright position. Consistent with previously published studies, a distinct image texture was observed uniquely within lung regions. Lung regions were automatically identified using supervised machine learning applied to summary measures of the image texture data. It was found that an unsupervised clustering within predefined lung regions colocates with expected differences in anatomy along the cranial–caudal axis in upright mice. It was also found that specifically selected inflation pressures—here, a purposeful surrogate of distinct states of mechanical expansion—can be predicted from the lung image texture alone, that the prediction model itself varies from apex to base and that prediction is accurate regardless of overlap with nonpulmonary structures such as the ribs, mediastinum, and heart. Cross‐validation analysis indicated low inter‐animal variation in the image texture classifications. Together, these results suggest that the image texture observed in a single X‐ray phase‐contrast‐enhanced projection image could be used across a range of pressure states to study regional variations in regional lung function.https://doi.org/10.14814/phy2.14208image texturelung imagingstatistical learningX‐ray phase‐contrast imaging |
collection |
DOAJ |
language |
English |
format |
Article |
sources |
DOAJ |
author |
Frank J. Brooks Sean P. Gunsten Sunil K. Vasireddi Steven L. Brody Mark A. Anastasio |
spellingShingle |
Frank J. Brooks Sean P. Gunsten Sunil K. Vasireddi Steven L. Brody Mark A. Anastasio Quantification of image texture in X‐ray phase‐contrast‐enhanced projection images of in vivo mouse lungs observed at varied inflation pressures Physiological Reports image texture lung imaging statistical learning X‐ray phase‐contrast imaging |
author_facet |
Frank J. Brooks Sean P. Gunsten Sunil K. Vasireddi Steven L. Brody Mark A. Anastasio |
author_sort |
Frank J. Brooks |
title |
Quantification of image texture in X‐ray phase‐contrast‐enhanced projection images of in vivo mouse lungs observed at varied inflation pressures |
title_short |
Quantification of image texture in X‐ray phase‐contrast‐enhanced projection images of in vivo mouse lungs observed at varied inflation pressures |
title_full |
Quantification of image texture in X‐ray phase‐contrast‐enhanced projection images of in vivo mouse lungs observed at varied inflation pressures |
title_fullStr |
Quantification of image texture in X‐ray phase‐contrast‐enhanced projection images of in vivo mouse lungs observed at varied inflation pressures |
title_full_unstemmed |
Quantification of image texture in X‐ray phase‐contrast‐enhanced projection images of in vivo mouse lungs observed at varied inflation pressures |
title_sort |
quantification of image texture in x‐ray phase‐contrast‐enhanced projection images of in vivo mouse lungs observed at varied inflation pressures |
publisher |
Wiley |
series |
Physiological Reports |
issn |
2051-817X |
publishDate |
2019-08-01 |
description |
Abstract To date, there are very limited noninvasive, regional assays of in vivo lung microstructure near the alveolar level. It has been suggested that x‐ray phase‐contrast enhanced imaging reveals information about the air volume of the lung; however, the image texture information in these images remains underutilized. Projection images of in vivo mouse lungs were acquired via a tabletop, propagation‐based, X‐ray phase‐contrast imaging system. Anesthetized mice were mechanically ventilated in an upright position. Consistent with previously published studies, a distinct image texture was observed uniquely within lung regions. Lung regions were automatically identified using supervised machine learning applied to summary measures of the image texture data. It was found that an unsupervised clustering within predefined lung regions colocates with expected differences in anatomy along the cranial–caudal axis in upright mice. It was also found that specifically selected inflation pressures—here, a purposeful surrogate of distinct states of mechanical expansion—can be predicted from the lung image texture alone, that the prediction model itself varies from apex to base and that prediction is accurate regardless of overlap with nonpulmonary structures such as the ribs, mediastinum, and heart. Cross‐validation analysis indicated low inter‐animal variation in the image texture classifications. Together, these results suggest that the image texture observed in a single X‐ray phase‐contrast‐enhanced projection image could be used across a range of pressure states to study regional variations in regional lung function. |
topic |
image texture lung imaging statistical learning X‐ray phase‐contrast imaging |
url |
https://doi.org/10.14814/phy2.14208 |
work_keys_str_mv |
AT frankjbrooks quantificationofimagetextureinxrayphasecontrastenhancedprojectionimagesofinvivomouselungsobservedatvariedinflationpressures AT seanpgunsten quantificationofimagetextureinxrayphasecontrastenhancedprojectionimagesofinvivomouselungsobservedatvariedinflationpressures AT sunilkvasireddi quantificationofimagetextureinxrayphasecontrastenhancedprojectionimagesofinvivomouselungsobservedatvariedinflationpressures AT stevenlbrody quantificationofimagetextureinxrayphasecontrastenhancedprojectionimagesofinvivomouselungsobservedatvariedinflationpressures AT markaanastasio quantificationofimagetextureinxrayphasecontrastenhancedprojectionimagesofinvivomouselungsobservedatvariedinflationpressures |
_version_ |
1725138400946683904 |