Format

Send to

Choose Destination
Korean J Radiol. 2017 May-Jun;18(3):498-509. doi: 10.3348/kjr.2017.18.3.498. Epub 2017 Apr 3.

Quality of Radiomic Features in Glioblastoma Multiforme: Impact of Semi-Automated Tumor Segmentation Software.

Lee M1,2, Woo B3, Kuo MD4,5, Jamshidi N5, Kim JH1,2,3.

Author information

1
Center for Medical-IT Convergence Technology Research, Advanced Institutes of Convergence Technology, Seoul National University, Suwon 16229, Korea.
2
Department of Radiology, Seoul National University Hospital, Seoul 03080, Korea.
3
Department of Transdisciplinary Studies, Graduate School of Convergence Science and Technology, Seoul National University, Suwon 16229, Korea.
4
Department of Electronic and Computer Engineering, National Chiao Tung University, Hsinchu 300, Taiwan.
5
Department of Radiological Sciences, University of California, Los Angeles, Los Angeles, CA 90095, USA.

Abstract

OBJECTIVE:

The purpose of this study was to evaluate the reliability and quality of radiomic features in glioblastoma multiforme (GBM) derived from tumor volumes obtained with semi-automated tumor segmentation software.

MATERIALS AND METHODS:

MR images of 45 GBM patients (29 males, 16 females) were downloaded from The Cancer Imaging Archive, in which post-contrast T1-weighted imaging and fluid-attenuated inversion recovery MR sequences were used. Two raters independently segmented the tumors using two semi-automated segmentation tools (TumorPrism3D and 3D Slicer). Regions of interest corresponding to contrast-enhancing lesion, necrotic portions, and non-enhancing T2 high signal intensity component were segmented for each tumor. A total of 180 imaging features were extracted, and their quality was evaluated in terms of stability, normalized dynamic range (NDR), and redundancy, using intra-class correlation coefficients, cluster consensus, and Rand Statistic.

RESULTS:

Our study results showed that most of the radiomic features in GBM were highly stable. Over 90% of 180 features showed good stability (intra-class correlation coefficient [ICC] ≥ 0.8), whereas only 7 features were of poor stability (ICC < 0.5). Most first order statistics and morphometric features showed moderate-to-high NDR (4 > NDR ≥1), while above 35% of the texture features showed poor NDR (< 1). Features were shown to cluster into only 5 groups, indicating that they were highly redundant.

CONCLUSION:

The use of semi-automated software tools provided sufficiently reliable tumor segmentation and feature stability; thus helping to overcome the inherent inter-rater and intra-rater variability of user intervention. However, certain aspects of feature quality, including NDR and redundancy, need to be assessed for determination of representative signature features before further development of radiomics.

KEYWORDS:

Feature quality; Glioblastoma multiforme; Radiomics; Semi-automated segmentation; The Cancer Genome Atlas; The Cancer Imaging Archive

PMID:
28458602
PMCID:
PMC5390619
DOI:
10.3348/kjr.2017.18.3.498
[Indexed for MEDLINE]
Free PMC Article

Supplemental Content

Full text links

Icon for The Korean Radiological Society Icon for PubMed Central
Loading ...
Support Center