Quality of Radiomic Features in Glioblastoma Multiforme: Impact of Semi-Automated Tumor Segmentation Software.
10.3348/kjr.2017.18.3.498
- Author:
Myungeun LEE
1
;
Boyeong WOO
;
Michael D KUO
;
Neema JAMSHIDI
;
Jong Hyo KIM
Author Information
1. Center for Medical-IT Convergence Technology Research, Advanced Institutes of Convergence Technology, Seoul National University, Suwon 16229, Korea. kimjhyo@snu.ac.kr
- Publication Type:Original Article
- Keywords:
Radiomics;
Semi-automated segmentation;
Feature quality;
Glioblastoma multiforme;
The Cancer Genome Atlas;
The Cancer Imaging Archive
- MeSH:
Archives;
Consensus;
Glioblastoma*;
Humans;
Male
- From:Korean Journal of Radiology
2017;18(3):498-509
- CountryRepublic of Korea
- Language:English
-
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.
