Radiomic biomarkers informative of cancerous transformation in neurofibromatosis-1 plexiform tumors

J. Uthoff, F. A. De Stefano, K. Panzer, B. W. Darbro, T. S. Sato, Rajesh Khanna, D. E. Quelle, D. K. Meyerholz, J. Weimer, J. C. Sieren

Research output: Contribution to journalArticle

1 Citation (Scopus)

Abstract

Background: This study explores whether objective, quantitative radiomic biomarkers derived from magnetic resonance (MR), positron emission tomography (PET), and computed tomography (CT) may be useful in reliably distinguishing malignant peripheral nerve sheath tumors (MPNST) from benign plexiform neurofibromas (PN). Methods: A registration and segmentation pipeline was established using a cohort of NF1 patients with histopathological diagnosis of PN or MPNST, and medical imaging of the PN including MR and PET-CT. The corrected MR datasets were registered to the corresponding PET-CT via landmark-based registration. PET standard-uptake value (SUV) thresholds were used to guide segmentation of volumes of interest: MPNST-associated PET-hot regions (SUV ≥ 3.5) and PN-associated PET-elevated regions (2.0 < SUV < 3.5). Quantitative imaging features were extracted from the MR, PET, and CT data and compared for statistical differences. Intensity histogram features included (mean, media, maximum, variance, full width at half maximum, entropy, kurtosis, and skewness), while image texture was quantified using Law's texture energy measures, grey-level co-occurrence matrices, and neighborhood grey-tone difference matrices. Results: For each of the 20 NF1 subjects, a total of 320 features were extracted from the image data. Feature reduction and statistical testing identified 9 independent radiomic biomarkers from the MR data (4 intensity and 5 texture) and 4 PET (2 intensity and 2 texture) were different between the PET-hot versus PET-elevated volumes of interest. Conclusions: Our data suggests imaging features can be used to distinguish malignancy in NF1-realted tumors, which could improve MPNST risk assessment and positively impact clinical management of NF1 patients.

Original languageEnglish (US)
JournalJournal of Neuroradiology
DOIs
StateAccepted/In press - Jan 1 2018

Fingerprint

Neurofibromatosis 1
Plexiform Neurofibroma
Positron-Emission Tomography
Biomarkers
Neurilemmoma
Magnetic Resonance Spectroscopy
Neoplasms
Entropy
Diagnostic Imaging
Positron Emission Tomography Computed Tomography

Keywords

  • Magnetic resonance imaging
  • Malignant peripheral nerve sheath tumor
  • Plexiform neurofibroma
  • Positron emission tomography
  • Quantitative feature extraction

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Clinical Neurology

Cite this

Radiomic biomarkers informative of cancerous transformation in neurofibromatosis-1 plexiform tumors. / Uthoff, J.; De Stefano, F. A.; Panzer, K.; Darbro, B. W.; Sato, T. S.; Khanna, Rajesh; Quelle, D. E.; Meyerholz, D. K.; Weimer, J.; Sieren, J. C.

In: Journal of Neuroradiology, 01.01.2018.

Research output: Contribution to journalArticle

Uthoff, J, De Stefano, FA, Panzer, K, Darbro, BW, Sato, TS, Khanna, R, Quelle, DE, Meyerholz, DK, Weimer, J & Sieren, JC 2018, 'Radiomic biomarkers informative of cancerous transformation in neurofibromatosis-1 plexiform tumors', Journal of Neuroradiology. https://doi.org/10.1016/j.neurad.2018.05.006
Uthoff, J. ; De Stefano, F. A. ; Panzer, K. ; Darbro, B. W. ; Sato, T. S. ; Khanna, Rajesh ; Quelle, D. E. ; Meyerholz, D. K. ; Weimer, J. ; Sieren, J. C. / Radiomic biomarkers informative of cancerous transformation in neurofibromatosis-1 plexiform tumors. In: Journal of Neuroradiology. 2018.
@article{1a156ff2ff6541e581f8dd612302a56d,
title = "Radiomic biomarkers informative of cancerous transformation in neurofibromatosis-1 plexiform tumors",
abstract = "Background: This study explores whether objective, quantitative radiomic biomarkers derived from magnetic resonance (MR), positron emission tomography (PET), and computed tomography (CT) may be useful in reliably distinguishing malignant peripheral nerve sheath tumors (MPNST) from benign plexiform neurofibromas (PN). Methods: A registration and segmentation pipeline was established using a cohort of NF1 patients with histopathological diagnosis of PN or MPNST, and medical imaging of the PN including MR and PET-CT. The corrected MR datasets were registered to the corresponding PET-CT via landmark-based registration. PET standard-uptake value (SUV) thresholds were used to guide segmentation of volumes of interest: MPNST-associated PET-hot regions (SUV ≥ 3.5) and PN-associated PET-elevated regions (2.0 < SUV < 3.5). Quantitative imaging features were extracted from the MR, PET, and CT data and compared for statistical differences. Intensity histogram features included (mean, media, maximum, variance, full width at half maximum, entropy, kurtosis, and skewness), while image texture was quantified using Law's texture energy measures, grey-level co-occurrence matrices, and neighborhood grey-tone difference matrices. Results: For each of the 20 NF1 subjects, a total of 320 features were extracted from the image data. Feature reduction and statistical testing identified 9 independent radiomic biomarkers from the MR data (4 intensity and 5 texture) and 4 PET (2 intensity and 2 texture) were different between the PET-hot versus PET-elevated volumes of interest. Conclusions: Our data suggests imaging features can be used to distinguish malignancy in NF1-realted tumors, which could improve MPNST risk assessment and positively impact clinical management of NF1 patients.",
keywords = "Magnetic resonance imaging, Malignant peripheral nerve sheath tumor, Plexiform neurofibroma, Positron emission tomography, Quantitative feature extraction",
author = "J. Uthoff and {De Stefano}, {F. A.} and K. Panzer and Darbro, {B. W.} and Sato, {T. S.} and Rajesh Khanna and Quelle, {D. E.} and Meyerholz, {D. K.} and J. Weimer and Sieren, {J. C.}",
year = "2018",
month = "1",
day = "1",
doi = "10.1016/j.neurad.2018.05.006",
language = "English (US)",
journal = "Journal of Neuroradiology",
issn = "0150-9861",
publisher = "Elsevier Masson",

}

TY - JOUR

T1 - Radiomic biomarkers informative of cancerous transformation in neurofibromatosis-1 plexiform tumors

AU - Uthoff, J.

AU - De Stefano, F. A.

AU - Panzer, K.

AU - Darbro, B. W.

AU - Sato, T. S.

AU - Khanna, Rajesh

AU - Quelle, D. E.

AU - Meyerholz, D. K.

AU - Weimer, J.

AU - Sieren, J. C.

PY - 2018/1/1

Y1 - 2018/1/1

N2 - Background: This study explores whether objective, quantitative radiomic biomarkers derived from magnetic resonance (MR), positron emission tomography (PET), and computed tomography (CT) may be useful in reliably distinguishing malignant peripheral nerve sheath tumors (MPNST) from benign plexiform neurofibromas (PN). Methods: A registration and segmentation pipeline was established using a cohort of NF1 patients with histopathological diagnosis of PN or MPNST, and medical imaging of the PN including MR and PET-CT. The corrected MR datasets were registered to the corresponding PET-CT via landmark-based registration. PET standard-uptake value (SUV) thresholds were used to guide segmentation of volumes of interest: MPNST-associated PET-hot regions (SUV ≥ 3.5) and PN-associated PET-elevated regions (2.0 < SUV < 3.5). Quantitative imaging features were extracted from the MR, PET, and CT data and compared for statistical differences. Intensity histogram features included (mean, media, maximum, variance, full width at half maximum, entropy, kurtosis, and skewness), while image texture was quantified using Law's texture energy measures, grey-level co-occurrence matrices, and neighborhood grey-tone difference matrices. Results: For each of the 20 NF1 subjects, a total of 320 features were extracted from the image data. Feature reduction and statistical testing identified 9 independent radiomic biomarkers from the MR data (4 intensity and 5 texture) and 4 PET (2 intensity and 2 texture) were different between the PET-hot versus PET-elevated volumes of interest. Conclusions: Our data suggests imaging features can be used to distinguish malignancy in NF1-realted tumors, which could improve MPNST risk assessment and positively impact clinical management of NF1 patients.

AB - Background: This study explores whether objective, quantitative radiomic biomarkers derived from magnetic resonance (MR), positron emission tomography (PET), and computed tomography (CT) may be useful in reliably distinguishing malignant peripheral nerve sheath tumors (MPNST) from benign plexiform neurofibromas (PN). Methods: A registration and segmentation pipeline was established using a cohort of NF1 patients with histopathological diagnosis of PN or MPNST, and medical imaging of the PN including MR and PET-CT. The corrected MR datasets were registered to the corresponding PET-CT via landmark-based registration. PET standard-uptake value (SUV) thresholds were used to guide segmentation of volumes of interest: MPNST-associated PET-hot regions (SUV ≥ 3.5) and PN-associated PET-elevated regions (2.0 < SUV < 3.5). Quantitative imaging features were extracted from the MR, PET, and CT data and compared for statistical differences. Intensity histogram features included (mean, media, maximum, variance, full width at half maximum, entropy, kurtosis, and skewness), while image texture was quantified using Law's texture energy measures, grey-level co-occurrence matrices, and neighborhood grey-tone difference matrices. Results: For each of the 20 NF1 subjects, a total of 320 features were extracted from the image data. Feature reduction and statistical testing identified 9 independent radiomic biomarkers from the MR data (4 intensity and 5 texture) and 4 PET (2 intensity and 2 texture) were different between the PET-hot versus PET-elevated volumes of interest. Conclusions: Our data suggests imaging features can be used to distinguish malignancy in NF1-realted tumors, which could improve MPNST risk assessment and positively impact clinical management of NF1 patients.

KW - Magnetic resonance imaging

KW - Malignant peripheral nerve sheath tumor

KW - Plexiform neurofibroma

KW - Positron emission tomography

KW - Quantitative feature extraction

UR - http://www.scopus.com/inward/record.url?scp=85049883293&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=85049883293&partnerID=8YFLogxK

U2 - 10.1016/j.neurad.2018.05.006

DO - 10.1016/j.neurad.2018.05.006

M3 - Article

C2 - 29958847

AN - SCOPUS:85049883293

JO - Journal of Neuroradiology

JF - Journal of Neuroradiology

SN - 0150-9861

ER -