Assessing the Effects of Software Platforms on Volumetric Segmentation of Glioblastoma

• Type of Material: Article
• Authors: William D. Dunn, Emory University; Hugo J. W. L. Aerts, Harvard Medical School; Lee Cooper, Emory University; Chad A Holder, Emory University; Scott N. Hwang, St. Jude Children's Research Hospital; Carle C. Jaffe, Boston University School of Medicine; Daniel J Brat, Emory University; Rajan Jain, NYU School of Medicine; Adam E. Flanders, Thomas Jefferson University Hospitals; Pascal O. Zinn, The University of Texas MD Anderson Cancer Center; Rivka R. Colen, The University of Texas MD Anderson Cancer Center; David Andrew Gutman, Emory University
• Language: English
• Date: 2016
• Publisher: United Scientific Group
• Publication Version: Final Published Version
• Copyright Statement: © 2016 Dunn Jr et al.
• License: Creative Commons Attribution 4.0 International
• Final Published Version (URL): http://dx.doi.org/10.17756/jnpn.2016-008
• Title of Journal or Parent Work: Journal of Neuroimaging in Psychiatry and Neurology
• ISSN: 2474-0713
• Volume: 1
• Issue: 2
• Start Page: 64
• End Page: 72
• Grant/Funding Information: This work was supported by funding from the National Cancer Institute (NCI U24 CA194362 and NCI U24 CA194354).
• Keywords: 3D Slicer; GBM; Imaging-genomics; MRI; Computational science; Cancer
• Research Categories: Biology, Neuroscience; Biology, Bioinformatics

Abstract

Radiological assessments of biologically relevant regions in glioblastoma have been associated with genotypic characteristics, implying a potential role in personalized medicine. Here, we assess the reproducibility and association with survival of two volumetric segmentation platforms and explore how methodology could impact subsequent interpretation and analysis. Methods: Post-contrast T1- and T2-weighted FLAIR MR images of 67 TCGA patients were segmented into five distinct compartments (necrosis, contrast-enhancement, FLAIR, post contrast abnormal, and total abnormal tumor volumes) by two quantitative image segmentation platforms - 3D Slicer and a method based on Velocity AI and FSL. We investigated the internal consistency of each platform by correlation statistics, association with survival, and concordance with consensus neuroradiologist ratings using ordinal logistic regression. Results: We found high correlations between the two platforms for FLAIR, post contrast abnormal, and total abnormal tumor volumes (spearman's r(67) = 0.952, 0.959, and 0.969 respectively). Only modest agreement was observed for necrosis and contrast-enhancement volumes (r(67) = 0.693 and 0.773 respectively), likely arising from differences in manual and automated segmentation methods of these regions by 3D Slicer and Velocity AI/FSL, respectively. Survival analysis based on AUC revealed significant predictive power of both platforms for the following volumes: contrast-enhancement, post contrast abnormal, and total abnormal tumor volumes. Finally, ordinal logistic regression demonstrated correspondence to manual ratings for several features. Conclusion: Tumor volume measurements from both volumetric platforms produced highly concordant and reproducible estimates across platforms for general features. As automated or semi-automated volumetric measurements replace manual linear or area measurements, it will become increasingly important to keep in mind that measurement differences between segmentation platforms for more detailed features could influence downstream survival or radio genomic analyses.