Radiomics-based differentiation of lung disease models generated by polluted air based on X-ray computed tomography data

Krisztián Szigeti, Tibor Szabó, Csaba Korom, Ilona Czibak, I. Horváth, Dániel S. Veres, Zoltán Gyöngyi, K. Karlinger, Ralf Bergmann, Márta Pócsik, Ferenc Budán, Domokos Máthé

Research output: Contribution to journalArticle

7 Citations (Scopus)

Abstract

Background: Lung diseases (resulting from air pollution) require a widely accessible method for risk estimation and early diagnosis to ensure proper and responsive treatment. Radiomics-based fractal dimension analysis of X-ray computed tomography attenuation patterns in chest voxels of mice exposed to different air polluting agents was performed to model early stages of disease and establish differential diagnosis. Methods: To model different types of air pollution, BALBc/ByJ mouse groups were exposed to cigarette smoke combined with ozone, sulphur dioxide gas and a control group was established. Two weeks after exposure, the frequency distributions of image voxel attenuation data were evaluated. Specific cut-off ranges were defined to group voxels by attenuation. Cut-off ranges were binarized and their spatial pattern was associated with calculated fractal dimension, then abstracted by the fractal dimension - cut-off range mathematical function. Nonparametric Kruskal-Wallis (KW) and Mann-Whitney post hoc (MWph) tests were used. Results: Each cut-off range versus fractal dimension function plot was found to contain two distinctive Gaussian curves. The ratios of the Gaussian curve parameters are considerably significant and are statistically distinguishable within the three exposure groups. Conclusions: A new radiomics evaluation method was established based on analysis of the fractal dimension of chest X-ray computed tomography data segments. The specific attenuation patterns calculated utilizing our method may diagnose and monitor certain lung diseases, such as chronic obstructive pulmonary disease (COPD), asthma, tuberculosis or lung carcinomas.

Original languageEnglish
Article number14
JournalBMC Medical Imaging
Volume16
Issue number1
DOIs
Publication statusPublished - Feb 11 2016

Fingerprint

Fractals
X Ray Computed Tomography
Lung Diseases
Air
Air Pollution
Thorax
Sulfur Dioxide
Ozone
Smoke
Tobacco Products
Chronic Obstructive Pulmonary Disease
Early Diagnosis
Tuberculosis
Differential Diagnosis
Asthma
Gases
Carcinoma
Lung
Control Groups

Keywords

  • Air pollution
  • Fractal dimension
  • In vivo micro-CT
  • Lung disease
  • Radiomics

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Radiomics-based differentiation of lung disease models generated by polluted air based on X-ray computed tomography data. / Szigeti, Krisztián; Szabó, Tibor; Korom, Csaba; Czibak, Ilona; Horváth, I.; Veres, Dániel S.; Gyöngyi, Zoltán; Karlinger, K.; Bergmann, Ralf; Pócsik, Márta; Budán, Ferenc; Máthé, Domokos.

In: BMC Medical Imaging, Vol. 16, No. 1, 14, 11.02.2016.

Research output: Contribution to journalArticle

Szigeti, K, Szabó, T, Korom, C, Czibak, I, Horváth, I, Veres, DS, Gyöngyi, Z, Karlinger, K, Bergmann, R, Pócsik, M, Budán, F & Máthé, D 2016, 'Radiomics-based differentiation of lung disease models generated by polluted air based on X-ray computed tomography data', BMC Medical Imaging, vol. 16, no. 1, 14. https://doi.org/10.1186/s12880-016-0118-z
Szigeti, Krisztián ; Szabó, Tibor ; Korom, Csaba ; Czibak, Ilona ; Horváth, I. ; Veres, Dániel S. ; Gyöngyi, Zoltán ; Karlinger, K. ; Bergmann, Ralf ; Pócsik, Márta ; Budán, Ferenc ; Máthé, Domokos. / Radiomics-based differentiation of lung disease models generated by polluted air based on X-ray computed tomography data. In: BMC Medical Imaging. 2016 ; Vol. 16, No. 1.
@article{2c6a5cd5ba054d0682b7dbfcf5d798f2,
title = "Radiomics-based differentiation of lung disease models generated by polluted air based on X-ray computed tomography data",
abstract = "Background: Lung diseases (resulting from air pollution) require a widely accessible method for risk estimation and early diagnosis to ensure proper and responsive treatment. Radiomics-based fractal dimension analysis of X-ray computed tomography attenuation patterns in chest voxels of mice exposed to different air polluting agents was performed to model early stages of disease and establish differential diagnosis. Methods: To model different types of air pollution, BALBc/ByJ mouse groups were exposed to cigarette smoke combined with ozone, sulphur dioxide gas and a control group was established. Two weeks after exposure, the frequency distributions of image voxel attenuation data were evaluated. Specific cut-off ranges were defined to group voxels by attenuation. Cut-off ranges were binarized and their spatial pattern was associated with calculated fractal dimension, then abstracted by the fractal dimension - cut-off range mathematical function. Nonparametric Kruskal-Wallis (KW) and Mann-Whitney post hoc (MWph) tests were used. Results: Each cut-off range versus fractal dimension function plot was found to contain two distinctive Gaussian curves. The ratios of the Gaussian curve parameters are considerably significant and are statistically distinguishable within the three exposure groups. Conclusions: A new radiomics evaluation method was established based on analysis of the fractal dimension of chest X-ray computed tomography data segments. The specific attenuation patterns calculated utilizing our method may diagnose and monitor certain lung diseases, such as chronic obstructive pulmonary disease (COPD), asthma, tuberculosis or lung carcinomas.",
keywords = "Air pollution, Fractal dimension, In vivo micro-CT, Lung disease, Radiomics",
author = "Kriszti{\'a}n Szigeti and Tibor Szab{\'o} and Csaba Korom and Ilona Czibak and I. Horv{\'a}th and Veres, {D{\'a}niel S.} and Zolt{\'a}n Gy{\"o}ngyi and K. Karlinger and Ralf Bergmann and M{\'a}rta P{\'o}csik and Ferenc Bud{\'a}n and Domokos M{\'a}th{\'e}",
year = "2016",
month = "2",
day = "11",
doi = "10.1186/s12880-016-0118-z",
language = "English",
volume = "16",
journal = "BMC Medical Imaging",
issn = "1471-2342",
publisher = "BioMed Central",
number = "1",

}

TY - JOUR

T1 - Radiomics-based differentiation of lung disease models generated by polluted air based on X-ray computed tomography data

AU - Szigeti, Krisztián

AU - Szabó, Tibor

AU - Korom, Csaba

AU - Czibak, Ilona

AU - Horváth, I.

AU - Veres, Dániel S.

AU - Gyöngyi, Zoltán

AU - Karlinger, K.

AU - Bergmann, Ralf

AU - Pócsik, Márta

AU - Budán, Ferenc

AU - Máthé, Domokos

PY - 2016/2/11

Y1 - 2016/2/11

N2 - Background: Lung diseases (resulting from air pollution) require a widely accessible method for risk estimation and early diagnosis to ensure proper and responsive treatment. Radiomics-based fractal dimension analysis of X-ray computed tomography attenuation patterns in chest voxels of mice exposed to different air polluting agents was performed to model early stages of disease and establish differential diagnosis. Methods: To model different types of air pollution, BALBc/ByJ mouse groups were exposed to cigarette smoke combined with ozone, sulphur dioxide gas and a control group was established. Two weeks after exposure, the frequency distributions of image voxel attenuation data were evaluated. Specific cut-off ranges were defined to group voxels by attenuation. Cut-off ranges were binarized and their spatial pattern was associated with calculated fractal dimension, then abstracted by the fractal dimension - cut-off range mathematical function. Nonparametric Kruskal-Wallis (KW) and Mann-Whitney post hoc (MWph) tests were used. Results: Each cut-off range versus fractal dimension function plot was found to contain two distinctive Gaussian curves. The ratios of the Gaussian curve parameters are considerably significant and are statistically distinguishable within the three exposure groups. Conclusions: A new radiomics evaluation method was established based on analysis of the fractal dimension of chest X-ray computed tomography data segments. The specific attenuation patterns calculated utilizing our method may diagnose and monitor certain lung diseases, such as chronic obstructive pulmonary disease (COPD), asthma, tuberculosis or lung carcinomas.

AB - Background: Lung diseases (resulting from air pollution) require a widely accessible method for risk estimation and early diagnosis to ensure proper and responsive treatment. Radiomics-based fractal dimension analysis of X-ray computed tomography attenuation patterns in chest voxels of mice exposed to different air polluting agents was performed to model early stages of disease and establish differential diagnosis. Methods: To model different types of air pollution, BALBc/ByJ mouse groups were exposed to cigarette smoke combined with ozone, sulphur dioxide gas and a control group was established. Two weeks after exposure, the frequency distributions of image voxel attenuation data were evaluated. Specific cut-off ranges were defined to group voxels by attenuation. Cut-off ranges were binarized and their spatial pattern was associated with calculated fractal dimension, then abstracted by the fractal dimension - cut-off range mathematical function. Nonparametric Kruskal-Wallis (KW) and Mann-Whitney post hoc (MWph) tests were used. Results: Each cut-off range versus fractal dimension function plot was found to contain two distinctive Gaussian curves. The ratios of the Gaussian curve parameters are considerably significant and are statistically distinguishable within the three exposure groups. Conclusions: A new radiomics evaluation method was established based on analysis of the fractal dimension of chest X-ray computed tomography data segments. The specific attenuation patterns calculated utilizing our method may diagnose and monitor certain lung diseases, such as chronic obstructive pulmonary disease (COPD), asthma, tuberculosis or lung carcinomas.

KW - Air pollution

KW - Fractal dimension

KW - In vivo micro-CT

KW - Lung disease

KW - Radiomics

UR - http://www.scopus.com/inward/record.url?scp=84957708144&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957708144&partnerID=8YFLogxK

U2 - 10.1186/s12880-016-0118-z

DO - 10.1186/s12880-016-0118-z

M3 - Article

C2 - 26864653

AN - SCOPUS:84957708144

VL - 16

JO - BMC Medical Imaging

JF - BMC Medical Imaging

SN - 1471-2342

IS - 1

M1 - 14

ER -