Multi-parametric MRI and texture analysis to visualize spatial histologic heterogeneity and tumor extent in glioblastoma

Leland S Hu, Shuluo Ning, Jennifer M. Eschbacher, Nathan Gaw, Amylou Dueck, Kris A. Smith, Peter Nakaji, Jonathan Plasencia, Sara Ranjbar, Stephen J. Price, Nhan Tran, Joseph C Loftus, Robert Brian Jenkins, Brian Patrick O'Neill, William Elmquist, Leslie C. Baxter, Fei Gao, David Frakes, John P. Karis, Christine ZwartKristin Swanson, Jann N Sarkaria, Teresa Wu, Joseph Ross Mitchell, Jing Li

Research output: Contribution to journalArticle

41 Citations (Scopus)

Abstract

Background: Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ∼60%of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM. Methods: We recruited primary GBM patients undergoing image-guided biopsies and acquired preoperative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs

Original languageEnglish (US)
Article numbere0141506
JournalPLoS One
Volume10
Issue number11
DOIs
StatePublished - Nov 1 2015

Fingerprint

Glioblastoma
Magnetic resonance imaging
Tumors
Textures
texture
neoplasms
Biopsy
Neoplasms
biopsy
Image-Guided Biopsy
Diffusion tensor imaging
Diffusion Tensor Imaging
Oncology
artificial intelligence
Brain Neoplasms
Learning algorithms
genetic background
Learning systems
Brain
image analysis

ASJC Scopus subject areas

  • Agricultural and Biological Sciences(all)
  • Biochemistry, Genetics and Molecular Biology(all)
  • Medicine(all)

Cite this

Multi-parametric MRI and texture analysis to visualize spatial histologic heterogeneity and tumor extent in glioblastoma. / Hu, Leland S; Ning, Shuluo; Eschbacher, Jennifer M.; Gaw, Nathan; Dueck, Amylou; Smith, Kris A.; Nakaji, Peter; Plasencia, Jonathan; Ranjbar, Sara; Price, Stephen J.; Tran, Nhan; Loftus, Joseph C; Jenkins, Robert Brian; O'Neill, Brian Patrick; Elmquist, William; Baxter, Leslie C.; Gao, Fei; Frakes, David; Karis, John P.; Zwart, Christine; Swanson, Kristin; Sarkaria, Jann N; Wu, Teresa; Mitchell, Joseph Ross; Li, Jing.

In: PLoS One, Vol. 10, No. 11, e0141506, 01.11.2015.

Research output: Contribution to journalArticle

Hu, LS, Ning, S, Eschbacher, JM, Gaw, N, Dueck, A, Smith, KA, Nakaji, P, Plasencia, J, Ranjbar, S, Price, SJ, Tran, N, Loftus, JC, Jenkins, RB, O'Neill, BP, Elmquist, W, Baxter, LC, Gao, F, Frakes, D, Karis, JP, Zwart, C, Swanson, K, Sarkaria, JN, Wu, T, Mitchell, JR & Li, J 2015, 'Multi-parametric MRI and texture analysis to visualize spatial histologic heterogeneity and tumor extent in glioblastoma', PLoS One, vol. 10, no. 11, e0141506. https://doi.org/10.1371/journal.pone.0141506
Hu, Leland S ; Ning, Shuluo ; Eschbacher, Jennifer M. ; Gaw, Nathan ; Dueck, Amylou ; Smith, Kris A. ; Nakaji, Peter ; Plasencia, Jonathan ; Ranjbar, Sara ; Price, Stephen J. ; Tran, Nhan ; Loftus, Joseph C ; Jenkins, Robert Brian ; O'Neill, Brian Patrick ; Elmquist, William ; Baxter, Leslie C. ; Gao, Fei ; Frakes, David ; Karis, John P. ; Zwart, Christine ; Swanson, Kristin ; Sarkaria, Jann N ; Wu, Teresa ; Mitchell, Joseph Ross ; Li, Jing. / Multi-parametric MRI and texture analysis to visualize spatial histologic heterogeneity and tumor extent in glioblastoma. In: PLoS One. 2015 ; Vol. 10, No. 11.
@article{3e2e2e6870234b02b7ba94ed82ec4578,
title = "Multi-parametric MRI and texture analysis to visualize spatial histologic heterogeneity and tumor extent in glioblastoma",
abstract = "Background: Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ∼60{\%}of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM. Methods: We recruited primary GBM patients undergoing image-guided biopsies and acquired preoperative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80{\%} vs",
author = "Hu, {Leland S} and Shuluo Ning and Eschbacher, {Jennifer M.} and Nathan Gaw and Amylou Dueck and Smith, {Kris A.} and Peter Nakaji and Jonathan Plasencia and Sara Ranjbar and Price, {Stephen J.} and Nhan Tran and Loftus, {Joseph C} and Jenkins, {Robert Brian} and O'Neill, {Brian Patrick} and William Elmquist and Baxter, {Leslie C.} and Fei Gao and David Frakes and Karis, {John P.} and Christine Zwart and Kristin Swanson and Sarkaria, {Jann N} and Teresa Wu and Mitchell, {Joseph Ross} and Jing Li",
year = "2015",
month = "11",
day = "1",
doi = "10.1371/journal.pone.0141506",
language = "English (US)",
volume = "10",
journal = "PLoS One",
issn = "1932-6203",
publisher = "Public Library of Science",
number = "11",

}

TY - JOUR

T1 - Multi-parametric MRI and texture analysis to visualize spatial histologic heterogeneity and tumor extent in glioblastoma

AU - Hu, Leland S

AU - Ning, Shuluo

AU - Eschbacher, Jennifer M.

AU - Gaw, Nathan

AU - Dueck, Amylou

AU - Smith, Kris A.

AU - Nakaji, Peter

AU - Plasencia, Jonathan

AU - Ranjbar, Sara

AU - Price, Stephen J.

AU - Tran, Nhan

AU - Loftus, Joseph C

AU - Jenkins, Robert Brian

AU - O'Neill, Brian Patrick

AU - Elmquist, William

AU - Baxter, Leslie C.

AU - Gao, Fei

AU - Frakes, David

AU - Karis, John P.

AU - Zwart, Christine

AU - Swanson, Kristin

AU - Sarkaria, Jann N

AU - Wu, Teresa

AU - Mitchell, Joseph Ross

AU - Li, Jing

PY - 2015/11/1

Y1 - 2015/11/1

N2 - Background: Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ∼60%of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM. Methods: We recruited primary GBM patients undergoing image-guided biopsies and acquired preoperative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs

AB - Background: Genetic profiling represents the future of neuro-oncology but suffers from inadequate biopsies in heterogeneous tumors like Glioblastoma (GBM). Contrast-enhanced MRI (CE-MRI) targets enhancing core (ENH) but yields adequate tumor in only ∼60%of cases. Further, CE-MRI poorly localizes infiltrative tumor within surrounding non-enhancing parenchyma, or brain-around-tumor (BAT), despite the importance of characterizing this tumor segment, which universally recurs. In this study, we use multiple texture analysis and machine learning (ML) algorithms to analyze multi-parametric MRI, and produce new images indicating tumor-rich targets in GBM. Methods: We recruited primary GBM patients undergoing image-guided biopsies and acquired preoperative MRI: CE-MRI, Dynamic-Susceptibility-weighted-Contrast-enhanced-MRI, and Diffusion Tensor Imaging. Following image coregistration and region of interest placement at biopsy locations, we compared MRI metrics and regional texture with histologic diagnoses of high- vs low-tumor content (≥80% vs

UR - http://www.scopus.com/inward/record.url?scp=84957567984&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84957567984&partnerID=8YFLogxK

U2 - 10.1371/journal.pone.0141506

DO - 10.1371/journal.pone.0141506

M3 - Article

C2 - 26599106

AN - SCOPUS:84957567984

VL - 10

JO - PLoS One

JF - PLoS One

SN - 1932-6203

IS - 11

M1 - e0141506

ER -