Korean Journal of Radiology

The Korean Society of Radiology (대한영상의학회)
권호 표지
DOI QR코드

DOI QR Code

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

  • Lee, Myungeun (Center for Medical-IT Convergence Technology Research, Advanced Institutes of Convergence Technology, Seoul National University) ;
  • Woo, Boyeong (Department of Transdisciplinary Studies, Graduate School of Convergence Science and Technology, Seoul National University) ;
  • Kuo, Michael D. (Department of Electronic and Computer Engineering, National Chiao Tung University) ;
  • Jamshidi, Neema (Department of Radiological Sciences, University of California) ;
  • Kim, Jong Hyo (Center for Medical-IT Convergence Technology Research, Advanced Institutes of Convergence Technology, Seoul National University)
  • Received : 2016.07.28
  • Accepted : 2016.12.27
  • Published : 2017.06.01
⟨ Previous Next ⟩

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] ${\geq}0.8$), 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 ${\geq}1$), 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

Acknowledgement

Supported by : National Research Foundation of Korea (NRF), Korea Health Technology R&D Project through the Korea Health Industry Development Institute (KHIDI)

References

  1. Ohgaki H, Kleihues P. Epidemiology and etiology of gliomas. Acta Neuropathol 2005;109:93-108 https://doi.org/10.1007/s00401-005-0991-y
  2. Verhaak RG, Hoadley KA, Purdom E, Wang V, Qi Y, Wilkerson MD, et al. Integrated genomic analysis identifies clinically relevant subtypes of glioblastoma characterized by abnormalities in PDGFRA, IDH1, EGFR, and NF1. Cancer Cell 2010;17:98-110 https://doi.org/10.1016/j.ccr.2009.12.020
  3. Aerts HJ, Velazquez ER, Leijenaar RT, Parmar C, Grossmann P, Carvalho S, et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nat Commun 2014;5:4006 https://doi.org/10.1038/ncomms5006
  4. Parmar C, Rios Velazquez E, Leijenaar R, Jermoumi M, Carvalho S, Mak RH, et al. Robust radiomics feature quantification using semiautomatic volumetric segmentation. PLoS One 2014;9:e102107 https://doi.org/10.1371/journal.pone.0102107
  5. Kim M, Kim HS. Emerging techniques in brain tumor imaging: what radiologists need to know. Korean J Radiol 2016;17:598-619 https://doi.org/10.3348/kjr.2016.17.5.598
  6. Tixier F, Le Rest CC, Hatt M, Albarghach N, Pradier O, Metges JP, et al. Intratumor heterogeneity characterized by textural features on baseline 18F-FDG PET images predicts response to concomitant radiochemotherapy in esophageal cancer. J Nucl Med 2011;52:369-378 https://doi.org/10.2967/jnumed.110.082404
  7. El Naqa I, Grigsby P, Apte A, Kidd E, Donnelly E, Khullar D, et al. Exploring feature-based approaches in PET images for predicting cancer treatment outcomes. Pattern Recognit 2009;42:1162-1171 https://doi.org/10.1016/j.patcog.2008.08.011
  8. Diehn M, Nardini C, Wang DS, McGovern S, Jayaraman M, Liang Y, et al. Identification of noninvasive imaging surrogates for brain tumor gene-expression modules. Proc Natl Acad Sci U S A 2008;105:5213-5218 https://doi.org/10.1073/pnas.0801279105
  9. Zinn PO, Mahajan B, Sathyan P, Singh SK, Majumder S, Jolesz FA, et al. Radiogenomic mapping of edema/cellular invasion MRI-phenotypes in glioblastoma multiforme. PLoS One 2011;6:e25451 https://doi.org/10.1371/journal.pone.0025451
  10. Cancer Genome Atlas Research Network. Comprehensive genomic characterization defines human glioblastoma genes and core pathways. Nature 2008;455:1061-1068 https://doi.org/10.1038/nature07385
  11. Gevaert O, Mitchell LA, Achrol AS, Xu J, Echegaray S, Steinberg GK, et al. Glioblastoma multiforme: exploratory radiogenomic analysis by using quantitative image features. Radiology 2014;273:168-174 https://doi.org/10.1148/radiol.14131731
  12. Gutman DA, Cooper LA, Hwang SN, Holder CA, Gao J, Aurora TD, et al. MR imaging predictors of molecular profile and survival: multi-institutional study of the TCGA glioblastoma data set. Radiology 2013;267:560-569 https://doi.org/10.1148/radiol.13120118
  13. Yang D, Rao G, Martinez J, Veeraraghavan A, Rao A. Evaluation of tumor-derived MRI-texture features for discrimination of molecular subtypes and prediction of 12-month survival status in glioblastoma. Med Phys 2015;42:6725-6735 https://doi.org/10.1118/1.4934373
  14. Itakura H, Achrol AS, Mitchell LA, Loya JJ, Liu T, Westbroek EM, et al. Magnetic resonance image features identify glioblastoma phenotypic subtypes with distinct molecular pathway activities. Sci Transl Med 2015;7:303ra138 https://doi.org/10.1126/scitranslmed.aaa7582
  15. The Cancer Imaging Archive (TCIA). Web site. http://www.cancerimagingarchive.net/. Accessed March 5, 2016
  16. 3D Slicer. Web site. http://www.slicer.org/. Accessed March 15, 2016
  17. Lee M, Cho W, Kim S, Park S, Kim JH. Segmentation of interest region in medical volume images using geometric deformable model. Comput Biol Med 2012;42:523-537 https://doi.org/10.1016/j.compbiomed.2012.01.005
  18. Balagurunathan Y, Gu Y, Wang H, Kumar V, Grove O, Hawkins S, et al. Reproducibility and prognosis of quantitative features extracted from CT images. Transl Oncol 2014;7:72-87 https://doi.org/10.1593/tlo.13844
  19. Kim H, Park CM, Lee SM, Lee HJ, Goo JM. A comparison of two commercial volumetry software programs in the analysis of pulmonary ground-glass nodules: segmentation capability and measurement accuracy. Korean J Radiol 2013;14:683-691 https://doi.org/10.3348/kjr.2013.14.4.683
  20. Egger J, Kapur T, Fedorov A, Pieper S, Miller JV, Veeraraghavan H, et al. GBM volumetry using the 3D Slicer medical image computing platform. Sci Rep 2013;3:1364 https://doi.org/10.1038/srep01364
  21. Zhu Y, Young GS, Xue Z, Huang RY, You H, Setayesh K, et al. Semi-automatic segmentation software for quantitative clinical brain glioblastoma evaluation. Acad Radiol 2012;19:977-985 https://doi.org/10.1016/j.acra.2012.03.026
  22. Wilkerson MD. ConsensusClusterPlus (Tutorial). 2016. Available at: https://www.bioconductor.org/packages/devel/bioc/vignettes/ConsensusClusterPlus/inst/doc/ConsensusClusterPlus.pdf. Accessed July 1, 2016
  23. de Hoop B, Gietema H, van Ginneken B, Zanen P, Groenewegen G, Prokop M. A comparison of six software packages for evaluation of solid lung nodules using semiautomated volumetry: what is the minimum increase in size to detect growth in repeated CT examinations. Eur Radiol 2009;19:800-808 https://doi.org/10.1007/s00330-008-1229-x
  24. Jung SC, Choi SH, Yeom JA, Kim JH, Ryoo I, Kim SC, et al. Cerebral blood volume analysis in glioblastomas using dynamic susceptibility contrast-enhanced perfusion MRI: a comparison of manual and semiautomatic segmentation methods. PLoS One 2013;8:e69323 https://doi.org/10.1371/journal.pone.0069323
  25. Zou KH, Warfield SK, Bharatha A, Tempany CM, Kaus MR, Haker SJ, et al. Statistical validation of image segmentation quality based on a spatial overlap index. Acad Radiol 2004;11:178-189 https://doi.org/10.1016/S1076-6332(03)00671-8
  26. Balagurunathan Y, Kumar V, Gu Y, Kim J, Wang H, Liu Y, et al. Test-retest reproducibility analysis of lung CT image features. J Digit Imaging 2014;27:805-823 https://doi.org/10.1007/s10278-014-9716-x
  27. Parmar C, Leijenaar RT, Grossmann P, Rios Velazquez E, Bussink J, Rietveld D, et al. Radiomic feature clusters and prognostic signatures specific for Lung and Head & Neck cancer. Sci Rep 2015;5:11044 https://doi.org/10.1038/srep11044

Cited by

  1. Lung tumor segmentation methods: Impact on the uncertainty of radiomics features for non-small cell lung cancer vol.13, pp.10, 2017, https://doi.org/10.1371/journal.pone.0205003
  2. A Glimpse on Trends and Characteristics of Recent Articles Published in the Korean Journal of Radiology vol.20, pp.12, 2019, https://doi.org/10.3348/kjr.2019.0928
  3. Imaging Informatics: A New Horizon for Radiology in the Era of Artificial Intelligence, Big Data, and Data Science vol.80, pp.2, 2017, https://doi.org/10.3348/jksr.2019.80.2.176
  4. Radiomics and radiogenomics of primary liver cancers vol.25, pp.1, 2017, https://doi.org/10.3350/cmh.2018.1007
  5. Volumetric assessment of glioblastoma and its predictive value for survival vol.161, pp.8, 2017, https://doi.org/10.1007/s00701-019-03966-6
  6. Radiomics MRI Phenotyping with Machine Learning to Predict the Grade of Lower-Grade Gliomas: A Study Focused on Nonenhancing Tumors vol.20, pp.9, 2017, https://doi.org/10.3348/kjr.2018.0814
  7. Characteristics of Recent Articles Published in the Korean Journal of Radiology Based on the Citation Frequency vol.21, pp.12, 2020, https://doi.org/10.3348/kjr.2020.1322
  8. Radiographic imaging assessment of prognosis of intrahepatic cholangiocarcinoma vol.3, pp.2, 2017, https://doi.org/10.1007/s42058-020-00040-4
  9. Radiomics nomogram of contrast-enhanced spectral mammography for prediction of axillary lymph node metastasis in breast cancer: a multicenter study vol.30, pp.12, 2017, https://doi.org/10.1007/s00330-020-07016-z
  10. Standardization of imaging methods for machine learning in neuro-oncology vol.2, pp.suppl4, 2017, https://doi.org/10.1093/noajnl/vdaa054
  11. Computed Tomography-Based Radiomics Model to Predict Central Cervical Lymph Node Metastases in Papillary Thyroid Carcinoma: A Multicenter Study vol.12, pp.None, 2021, https://doi.org/10.3389/fendo.2021.741698
  12. Assessment of liver metastases radiomic feature reproducibility with deep-learning-based semi-automatic segmentation software vol.62, pp.3, 2017, https://doi.org/10.1177/0284185120922822
  13. Fully convolutional network-based multi-output model for automatic segmentation of organs at risk in thorax vol.104, pp.2, 2017, https://doi.org/10.1177/00368504211020161
  14. Preoperative prediction of histologic grade in invasive breast cancer by using contrast-enhanced spectral mammography-based radiomics vol.29, pp.5, 2017, https://doi.org/10.3233/xst-210886