Computational quantitative MR image features: a potential useful tool in differentiating glioblastoma from solitary brain metastasis

Katarina Petrujkić, Nebojša Milošević, Nemanja Rajković, Dejana Stanisavljević, Svetlana Gavrilović, Dragana Dželebdžić, Rosanda Ilić, Antonio Di Ieva, Ružica Maksimović

Research output: Contribution to journalArticleResearchpeer-review

Abstract

Purpose: Glioblastomas (GBM) and metastases are the most frequent malignant brain tumors in the adult population. Their presentation on conventional MRI is quite similar, but treatment strategy and prognosis are substantially different. Even with advanced MR techniques, in some cases diagnostic uncertainty remains. The main objective of this study was to determine whether fractal, texture, or both MR image analyses could aid in differentiating glioblastoma from solitary brain metastasis. Method: In a retrospective study of 55 patients (30 glioblastomas and 25 solitary metastases) who underwent T2W/SWI/CET1 MRI, quantitative parameters of fractal and texture analysis were estimated, using box-counting and gray level co-occurrence matrix (GLCM) methods. Results: All five GLCM parameters obtained from T2W images showed significant difference between glioblastomas and solitary metastases, as well as on CET1 images except correlation (SCOR), contrary to SWI images which showed different values of two parameters (angular second moment-SASM and contrast-SCON). Only three fractal features (binary box dimension-Dbin, normalized box dimension-Dnorm and lacunarity-λ) measured on T2W and Dnorm measured on CET1 images significantly differed GBMs from solitary metastases. The highest sensitivity and specificity were obtained from inverse difference moment (SIDM) on T2W and SIDM on CET1 images, respectively. Combination of several GLCM parameters yielded better results. The processing of T2W images provided the most significantly different parameters between the groups, followed by CET1 and SWI images. Conclusions: Computational-aided quantitative image analysis may potentially improve diagnostic accuracy. According to our results texture features are more significant than fractal-based features in differentiation glioblastoma from solitary metastasis.

LanguageEnglish
Article number108634
Pages1-8
Number of pages8
JournalEuropean Journal of Radiology
Volume119
DOIs
Publication statusPublished - 1 Oct 2019

Fingerprint

Glioblastoma
Fractals
Neoplasm Metastasis
Brain
Brain Neoplasms
Uncertainty
Retrospective Studies
Sensitivity and Specificity
Population

Keywords

  • Fractal analysis
  • Glioblastoma
  • Metastasis
  • MRI
  • Texture analysis

Cite this

Petrujkić, K., Milošević, N., Rajković, N., Stanisavljević, D., Gavrilović, S., Dželebdžić, D., ... Maksimović, R. (2019). Computational quantitative MR image features: a potential useful tool in differentiating glioblastoma from solitary brain metastasis. European Journal of Radiology, 119, 1-8. [108634]. https://doi.org/10.1016/j.ejrad.2019.08.003
Petrujkić, Katarina ; Milošević, Nebojša ; Rajković, Nemanja ; Stanisavljević, Dejana ; Gavrilović, Svetlana ; Dželebdžić, Dragana ; Ilić, Rosanda ; Di Ieva, Antonio ; Maksimović, Ružica. / Computational quantitative MR image features : a potential useful tool in differentiating glioblastoma from solitary brain metastasis. In: European Journal of Radiology. 2019 ; Vol. 119. pp. 1-8.
@article{2f8f8c39af3a48ef831f4438549347de,
title = "Computational quantitative MR image features: a potential useful tool in differentiating glioblastoma from solitary brain metastasis",
abstract = "Purpose: Glioblastomas (GBM) and metastases are the most frequent malignant brain tumors in the adult population. Their presentation on conventional MRI is quite similar, but treatment strategy and prognosis are substantially different. Even with advanced MR techniques, in some cases diagnostic uncertainty remains. The main objective of this study was to determine whether fractal, texture, or both MR image analyses could aid in differentiating glioblastoma from solitary brain metastasis. Method: In a retrospective study of 55 patients (30 glioblastomas and 25 solitary metastases) who underwent T2W/SWI/CET1 MRI, quantitative parameters of fractal and texture analysis were estimated, using box-counting and gray level co-occurrence matrix (GLCM) methods. Results: All five GLCM parameters obtained from T2W images showed significant difference between glioblastomas and solitary metastases, as well as on CET1 images except correlation (SCOR), contrary to SWI images which showed different values of two parameters (angular second moment-SASM and contrast-SCON). Only three fractal features (binary box dimension-Dbin, normalized box dimension-Dnorm and lacunarity-λ) measured on T2W and Dnorm measured on CET1 images significantly differed GBMs from solitary metastases. The highest sensitivity and specificity were obtained from inverse difference moment (SIDM) on T2W and SIDM on CET1 images, respectively. Combination of several GLCM parameters yielded better results. The processing of T2W images provided the most significantly different parameters between the groups, followed by CET1 and SWI images. Conclusions: Computational-aided quantitative image analysis may potentially improve diagnostic accuracy. According to our results texture features are more significant than fractal-based features in differentiation glioblastoma from solitary metastasis.",
keywords = "Fractal analysis, Glioblastoma, Metastasis, MRI, Texture analysis",
author = "Katarina Petrujkić and Nebojša Milošević and Nemanja Rajković and Dejana Stanisavljević and Svetlana Gavrilović and Dragana Dželebdžić and Rosanda Ilić and {Di Ieva}, Antonio and Ružica Maksimović",
year = "2019",
month = "10",
day = "1",
doi = "10.1016/j.ejrad.2019.08.003",
language = "English",
volume = "119",
pages = "1--8",
journal = "European Journal of Radiology",
issn = "0720-048X",
publisher = "Elsevier",

}

Petrujkić, K, Milošević, N, Rajković, N, Stanisavljević, D, Gavrilović, S, Dželebdžić, D, Ilić, R, Di Ieva, A & Maksimović, R 2019, 'Computational quantitative MR image features: a potential useful tool in differentiating glioblastoma from solitary brain metastasis', European Journal of Radiology, vol. 119, 108634, pp. 1-8. https://doi.org/10.1016/j.ejrad.2019.08.003

Computational quantitative MR image features : a potential useful tool in differentiating glioblastoma from solitary brain metastasis. / Petrujkić, Katarina; Milošević, Nebojša; Rajković, Nemanja; Stanisavljević, Dejana; Gavrilović, Svetlana; Dželebdžić, Dragana; Ilić, Rosanda; Di Ieva, Antonio; Maksimović, Ružica.

In: European Journal of Radiology, Vol. 119, 108634, 01.10.2019, p. 1-8.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - Computational quantitative MR image features

T2 - European Journal of Radiology

AU - Petrujkić, Katarina

AU - Milošević, Nebojša

AU - Rajković, Nemanja

AU - Stanisavljević, Dejana

AU - Gavrilović, Svetlana

AU - Dželebdžić, Dragana

AU - Ilić, Rosanda

AU - Di Ieva, Antonio

AU - Maksimović, Ružica

PY - 2019/10/1

Y1 - 2019/10/1

N2 - Purpose: Glioblastomas (GBM) and metastases are the most frequent malignant brain tumors in the adult population. Their presentation on conventional MRI is quite similar, but treatment strategy and prognosis are substantially different. Even with advanced MR techniques, in some cases diagnostic uncertainty remains. The main objective of this study was to determine whether fractal, texture, or both MR image analyses could aid in differentiating glioblastoma from solitary brain metastasis. Method: In a retrospective study of 55 patients (30 glioblastomas and 25 solitary metastases) who underwent T2W/SWI/CET1 MRI, quantitative parameters of fractal and texture analysis were estimated, using box-counting and gray level co-occurrence matrix (GLCM) methods. Results: All five GLCM parameters obtained from T2W images showed significant difference between glioblastomas and solitary metastases, as well as on CET1 images except correlation (SCOR), contrary to SWI images which showed different values of two parameters (angular second moment-SASM and contrast-SCON). Only three fractal features (binary box dimension-Dbin, normalized box dimension-Dnorm and lacunarity-λ) measured on T2W and Dnorm measured on CET1 images significantly differed GBMs from solitary metastases. The highest sensitivity and specificity were obtained from inverse difference moment (SIDM) on T2W and SIDM on CET1 images, respectively. Combination of several GLCM parameters yielded better results. The processing of T2W images provided the most significantly different parameters between the groups, followed by CET1 and SWI images. Conclusions: Computational-aided quantitative image analysis may potentially improve diagnostic accuracy. According to our results texture features are more significant than fractal-based features in differentiation glioblastoma from solitary metastasis.

AB - Purpose: Glioblastomas (GBM) and metastases are the most frequent malignant brain tumors in the adult population. Their presentation on conventional MRI is quite similar, but treatment strategy and prognosis are substantially different. Even with advanced MR techniques, in some cases diagnostic uncertainty remains. The main objective of this study was to determine whether fractal, texture, or both MR image analyses could aid in differentiating glioblastoma from solitary brain metastasis. Method: In a retrospective study of 55 patients (30 glioblastomas and 25 solitary metastases) who underwent T2W/SWI/CET1 MRI, quantitative parameters of fractal and texture analysis were estimated, using box-counting and gray level co-occurrence matrix (GLCM) methods. Results: All five GLCM parameters obtained from T2W images showed significant difference between glioblastomas and solitary metastases, as well as on CET1 images except correlation (SCOR), contrary to SWI images which showed different values of two parameters (angular second moment-SASM and contrast-SCON). Only three fractal features (binary box dimension-Dbin, normalized box dimension-Dnorm and lacunarity-λ) measured on T2W and Dnorm measured on CET1 images significantly differed GBMs from solitary metastases. The highest sensitivity and specificity were obtained from inverse difference moment (SIDM) on T2W and SIDM on CET1 images, respectively. Combination of several GLCM parameters yielded better results. The processing of T2W images provided the most significantly different parameters between the groups, followed by CET1 and SWI images. Conclusions: Computational-aided quantitative image analysis may potentially improve diagnostic accuracy. According to our results texture features are more significant than fractal-based features in differentiation glioblastoma from solitary metastasis.

KW - Fractal analysis

KW - Glioblastoma

KW - Metastasis

KW - MRI

KW - Texture analysis

UR - http://www.scopus.com/inward/record.url?scp=85071461062&partnerID=8YFLogxK

U2 - 10.1016/j.ejrad.2019.08.003

DO - 10.1016/j.ejrad.2019.08.003

M3 - Article

VL - 119

SP - 1

EP - 8

JO - European Journal of Radiology

JF - European Journal of Radiology

SN - 0720-048X

M1 - 108634

ER -