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 C. Dueck, Kris A. Smith, Peter Nakaji, Jonathan Plasencia, Sara Ranjbar, Stephen J. Price, Nhan Tran, Joseph Loftus, Robert Jenkins, Brian P. O'Neill, William Elmquist, Leslie C. Baxter, Fei Gao, David Frakes, John P. Karis, Christine ZwartKristin R. Swanson, Jann Sarkaria, Teresa Wu, J. Ross Mitchell, Jing Li

Research output: Contribution to journalArticlepeer-review

65 Scopus citations

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 <80% tumor nuclei) for corresponding samples. In a training set, we used three texture analysis algorithms and three ML methods to identify MRI-texture features that optimized model accuracy to distinguish tumor content. We confirmed model accuracy in a separate validation set. Results: We collected 82 biopsies from 18 GBMs throughout ENH and BAT. The MRI-based model achieved 85% cross-validated accuracy to diagnose high- vs low-tumor in the training set (60 biopsies, 11 patients). The model achieved 81.8% accuracy in the validation set (22 biopsies, 7 patients). Conclusion: Multi-parametric MRI and texture analysis can help characterize and visualize GBM's spatial histologic heterogeneity to identify regional tumor-rich biopsy targets.

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

Bibliographical note

Funding Information:
NATIONAL INSTITUTES OF HEALTH (NIH) - National Institute of Neurological Disorders and Stroke (NINDS) NS082609 (LSH): provided support for study design, data collection and analysis, preparation of the manuscript. Mayo Clinic Foundation (LSH): provided support for study design, data collection and analysis, preparation of the manuscript. National Science Foundation (NSF) DGE-1311230 (JP): provided support for data collection and analysis. We would like to thank Norissa Honea, PhD and Beth Hermes for their invaluable help in patient recruitment and tissue preparation.

Publisher Copyright:
© 2015 Hu et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

Fingerprint

Dive into the research topics of 'Multi-parametric MRI and texture analysis to visualize spatial histologic heterogeneity and tumor extent in glioblastoma'. Together they form a unique fingerprint.

Cite this