Quantitative Radiomics: Impact of Pulse Sequence Parameter Selection on MRI-Based Textural Features of the Brain

John Ford, Nesrin Dogan, Lori Young, Fei Yang

Research output: Contribution to journalArticle

12 Citations (Scopus)

Abstract

Radiomic features extracted from diverse MRI modalities have been investigated regarding their predictive and/or prognostic value in a variety of cancers. With the aid of a 3D realistic digital MRI phantom of the brain, the aim of this study was to examine the impact of pulse sequence parameter selection on MRI-based textural parameters of the brain. Methods. MR images of the employed digital phantom were realized with SimuBloch, a simulation package made for fast generation of image sequences based on the Bloch equations. Pulse sequences being investigated consisted of spin echo (SE), gradient echo (GRE), spoiled gradient echo (SP-GRE), inversion recovery spin echo (IR-SE), and inversion recovery gradient echo (IR-GRE). Twenty-nine radiomic textural features related, respectively, to gray-level intensity histograms (GLIH), cooccurrence matrices (GLCOM), zone size matrices (GLZSM), and neighborhood difference matrices (GLNDM) were evaluated for the obtained MR realizations, and differences were identified. Results. It was found that radiomic features vary considerably among images generated by the five different T1-weighted pulse sequences, and the deviations from those measured on the T1 map vary among features, from a few percent to over 100%. Radiomic features extracted from T1-weighted spin-echo images with TR varying from 360 ms to 620 ms and TE = 3.4 ms showed coefficients of variation (CV) up to 45%, while up to 70%, for T2-weighted spin-echo images with TE varying over the range 60-120 ms and TR = 6400 ms. Conclusion. Variability of radiologic textural appearance on MR realizations with respect to the choice of pulse sequence and imaging parameters is feature-dependent and can be substantial. It calls for caution in employing MRI-derived radiomic features especially when pooling imaging data from multiple institutions with intention of correlating with clinical endpoints.

Original languageEnglish (US)
Article number1729071
JournalContrast Media and Molecular Imaging
Volume2018
DOIs
StatePublished - Jan 1 2018

Fingerprint

Brain
Meta-Analysis
Neoplasms

ASJC Scopus subject areas

  • Radiology Nuclear Medicine and imaging

Cite this

Quantitative Radiomics : Impact of Pulse Sequence Parameter Selection on MRI-Based Textural Features of the Brain. / Ford, John; Dogan, Nesrin; Young, Lori; Yang, Fei.

In: Contrast Media and Molecular Imaging, Vol. 2018, 1729071, 01.01.2018.

Research output: Contribution to journalArticle

@article{9ad9e202e3e142bcaad6f80beba1b954,
title = "Quantitative Radiomics: Impact of Pulse Sequence Parameter Selection on MRI-Based Textural Features of the Brain",
abstract = "Radiomic features extracted from diverse MRI modalities have been investigated regarding their predictive and/or prognostic value in a variety of cancers. With the aid of a 3D realistic digital MRI phantom of the brain, the aim of this study was to examine the impact of pulse sequence parameter selection on MRI-based textural parameters of the brain. Methods. MR images of the employed digital phantom were realized with SimuBloch, a simulation package made for fast generation of image sequences based on the Bloch equations. Pulse sequences being investigated consisted of spin echo (SE), gradient echo (GRE), spoiled gradient echo (SP-GRE), inversion recovery spin echo (IR-SE), and inversion recovery gradient echo (IR-GRE). Twenty-nine radiomic textural features related, respectively, to gray-level intensity histograms (GLIH), cooccurrence matrices (GLCOM), zone size matrices (GLZSM), and neighborhood difference matrices (GLNDM) were evaluated for the obtained MR realizations, and differences were identified. Results. It was found that radiomic features vary considerably among images generated by the five different T1-weighted pulse sequences, and the deviations from those measured on the T1 map vary among features, from a few percent to over 100{\%}. Radiomic features extracted from T1-weighted spin-echo images with TR varying from 360 ms to 620 ms and TE = 3.4 ms showed coefficients of variation (CV) up to 45{\%}, while up to 70{\%}, for T2-weighted spin-echo images with TE varying over the range 60-120 ms and TR = 6400 ms. Conclusion. Variability of radiologic textural appearance on MR realizations with respect to the choice of pulse sequence and imaging parameters is feature-dependent and can be substantial. It calls for caution in employing MRI-derived radiomic features especially when pooling imaging data from multiple institutions with intention of correlating with clinical endpoints.",
author = "John Ford and Nesrin Dogan and Lori Young and Fei Yang",
year = "2018",
month = "1",
day = "1",
doi = "10.1155/2018/1729071",
language = "English (US)",
volume = "2018",
journal = "Contrast Media and Molecular Imaging",
issn = "1555-4309",
publisher = "John Wiley and Sons Ltd",

}

TY - JOUR

T1 - Quantitative Radiomics

T2 - Impact of Pulse Sequence Parameter Selection on MRI-Based Textural Features of the Brain

AU - Ford, John

AU - Dogan, Nesrin

AU - Young, Lori

AU - Yang, Fei

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Radiomic features extracted from diverse MRI modalities have been investigated regarding their predictive and/or prognostic value in a variety of cancers. With the aid of a 3D realistic digital MRI phantom of the brain, the aim of this study was to examine the impact of pulse sequence parameter selection on MRI-based textural parameters of the brain. Methods. MR images of the employed digital phantom were realized with SimuBloch, a simulation package made for fast generation of image sequences based on the Bloch equations. Pulse sequences being investigated consisted of spin echo (SE), gradient echo (GRE), spoiled gradient echo (SP-GRE), inversion recovery spin echo (IR-SE), and inversion recovery gradient echo (IR-GRE). Twenty-nine radiomic textural features related, respectively, to gray-level intensity histograms (GLIH), cooccurrence matrices (GLCOM), zone size matrices (GLZSM), and neighborhood difference matrices (GLNDM) were evaluated for the obtained MR realizations, and differences were identified. Results. It was found that radiomic features vary considerably among images generated by the five different T1-weighted pulse sequences, and the deviations from those measured on the T1 map vary among features, from a few percent to over 100%. Radiomic features extracted from T1-weighted spin-echo images with TR varying from 360 ms to 620 ms and TE = 3.4 ms showed coefficients of variation (CV) up to 45%, while up to 70%, for T2-weighted spin-echo images with TE varying over the range 60-120 ms and TR = 6400 ms. Conclusion. Variability of radiologic textural appearance on MR realizations with respect to the choice of pulse sequence and imaging parameters is feature-dependent and can be substantial. It calls for caution in employing MRI-derived radiomic features especially when pooling imaging data from multiple institutions with intention of correlating with clinical endpoints.

AB - Radiomic features extracted from diverse MRI modalities have been investigated regarding their predictive and/or prognostic value in a variety of cancers. With the aid of a 3D realistic digital MRI phantom of the brain, the aim of this study was to examine the impact of pulse sequence parameter selection on MRI-based textural parameters of the brain. Methods. MR images of the employed digital phantom were realized with SimuBloch, a simulation package made for fast generation of image sequences based on the Bloch equations. Pulse sequences being investigated consisted of spin echo (SE), gradient echo (GRE), spoiled gradient echo (SP-GRE), inversion recovery spin echo (IR-SE), and inversion recovery gradient echo (IR-GRE). Twenty-nine radiomic textural features related, respectively, to gray-level intensity histograms (GLIH), cooccurrence matrices (GLCOM), zone size matrices (GLZSM), and neighborhood difference matrices (GLNDM) were evaluated for the obtained MR realizations, and differences were identified. Results. It was found that radiomic features vary considerably among images generated by the five different T1-weighted pulse sequences, and the deviations from those measured on the T1 map vary among features, from a few percent to over 100%. Radiomic features extracted from T1-weighted spin-echo images with TR varying from 360 ms to 620 ms and TE = 3.4 ms showed coefficients of variation (CV) up to 45%, while up to 70%, for T2-weighted spin-echo images with TE varying over the range 60-120 ms and TR = 6400 ms. Conclusion. Variability of radiologic textural appearance on MR realizations with respect to the choice of pulse sequence and imaging parameters is feature-dependent and can be substantial. It calls for caution in employing MRI-derived radiomic features especially when pooling imaging data from multiple institutions with intention of correlating with clinical endpoints.

UR - http://www.scopus.com/inward/record.url?scp=85051461796&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85051461796&partnerID=8YFLogxK

U2 - 10.1155/2018/1729071

DO - 10.1155/2018/1729071

M3 - Article

C2 - 30154684

AN - SCOPUS:85051461796

VL - 2018

JO - Contrast Media and Molecular Imaging

JF - Contrast Media and Molecular Imaging

SN - 1555-4309

M1 - 1729071

ER -