European Radiology

, Volume 28, Issue 6, pp 2255–2263 | Cite as

A predictive model for distinguishing radiation necrosis from tumour progression after gamma knife radiosurgery based on radiomic features from MR images

  • Zijian Zhang
  • Jinzhong Yang
  • Angela Ho
  • Wen Jiang
  • Jennifer Logan
  • Xin Wang
  • Paul D. Brown
  • Susan L. McGovern
  • Nandita Guha-Thakurta
  • Sherise D. Ferguson
  • Xenia Fave
  • Lifei Zhang
  • Dennis Mackin
  • Laurence E. Court
  • Jing Li



To develop a model using radiomic features extracted from MR images to distinguish radiation necrosis from tumour progression in brain metastases after Gamma Knife radiosurgery.


We retrospectively identified 87 patients with pathologically confirmed necrosis (24 lesions) or progression (73 lesions) and calculated 285 radiomic features from four MR sequences (T1, T1 post-contrast, T2, and fluid-attenuated inversion recovery) obtained at two follow-up time points per lesion per patient. Reproducibility of each feature between the two time points was calculated within each group to identify a subset of features with distinct reproducible values between two groups. Changes in radiomic features from one time point to the next (delta radiomics) were used to build a model to classify necrosis and progression lesions.


A combination of five radiomic features from both T1 post-contrast and T2 MR images were found to be useful in distinguishing necrosis from progression lesions. Delta radiomic features with a RUSBoost ensemble classifier had an overall predictive accuracy of 73.2% and an area under the curve value of 0.73 in leave-one-out cross-validation.


Delta radiomic features extracted from MR images have potential for distinguishing radiation necrosis from tumour progression after radiosurgery for brain metastases.

Key points

• Some radiomic features showed better reproducibility for progressive lesions than necrotic ones

• Delta radiomic features can help to distinguish radiation necrosis from tumour progression

• Delta radiomic features had better predictive value than did traditional radiomic features


Delta radiomic features MRI Radiation necrosis Brain metastases Gamma Knife radiosurgery 



Area under the curve


Concordance correlation coefficient


Co-occurrence matrix


Fluid-attenuated inversion recovery


Histogram of oriented gradients


Imaging Biomarker Explorer


Magnetic resonance imaging


Neighbourhood grey-tone difference matrix


Run length matrix


Receiver operating characteristic


T1 weighted post-contrast



The authors would like to thank Christine Wogan for reviewing this manuscript.

This work was presented in part at the 2016 American Association of Physicists in Medicine Annual Meeting.

Compliance with ethical standards


The scientific guarantor of this publication is Jing Li.

Conflict of interest

The authors of this manuscript declare no relationships with any companies, whose products or services may be related to the subject matter of the article.


This study has received funding by National Institutes of Health through Cancer Center Support Grant P30CA016672.

Statistics and biometry

No complex statistical methods were necessary for this paper.

Informed consent

Written informed consent was waived by the Institutional Review Board.

Ethical approval

Institutional Review Board approval was obtained.


• retrospective

• experimental

• performed at one institution


  1. 1.
    Nayak L, Lee EQ, Wen PY (2012) Epidemiology of brain metastases. Current Oncology Reports 14:48–54CrossRefPubMedGoogle Scholar
  2. 2.
    Kondziolka D, Martin JJ, Flickinger JC et al (2005) Long-term survivors after gamma knife radiosurgery for brain metastases. Cancer 104:2784–2791CrossRefPubMedGoogle Scholar
  3. 3.
    Elaimy AL, Mackay AR, Lamoreaux WT et al (2011) Clinical outcomes of stereotactic radiosurgery in the treatment of patients with metastatic brain tumors. World Neurosurg 75:673–683CrossRefPubMedGoogle Scholar
  4. 4.
    Minniti G, Clarke E, Lanzetta G et al (2011) Stereotactic radiosurgery for brain metastases: analysis of outcome and risk of brain radionecrosis. Radiation Oncology 6:48CrossRefPubMedPubMedCentralGoogle Scholar
  5. 5.
    Shaw E, Scott C, Souhami L et al (2000) Single dose radiosurgical treatment of recurrent previously irradiated primary brain tumors and brain metastases: Final report of RTOG protocol 90-05. International Journal of Radiation Oncology Biology Physics 47:291–298CrossRefGoogle Scholar
  6. 6.
    Chuang MT, Liu YS, Tsai YS, Chen YC, Wang CK (2016) Differentiating Radiation-Induced Necrosis from Recurrent Brain Tumor Using MR Perfusion and Spectroscopy: A Meta-Analysis. PLoS ONE 11Google Scholar
  7. 7.
    Lai G, Mahadevan A, Hackney D et al (2015) Diagnostic Accuracy of PET, SPECT, and Arterial Spin-Labeling in Differentiating Tumor Recurrence from Necrosis in Cerebral Metastasis after Stereotactic Radiosurgery. American Journal of Neuroradiology 36:2250–2255CrossRefPubMedGoogle Scholar
  8. 8.
    Aerts HJWL, Velazquez ER, Leijenaar RTH et al (2014) Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature Communications 5Google Scholar
  9. 9.
    Fehr D, Veeraraghavan H, Wibmer A et al (2015) Automatic classification of prostate cancer Gleason scores from multiparametric magnetic resonance images. Proceedings of the National Academy of Sciences 112:E6265–E6273CrossRefGoogle Scholar
  10. 10.
    Gevaert O, Mitchell LA, Achrol AS et al (2014) Glioblastoma multiforme: exploratory radiogenomic analysis by using quantitative image features. Radiology 273:168–174CrossRefPubMedPubMedCentralGoogle Scholar
  11. 11.
    Gillies RJ, Kinahan PE, Hricak H (2015) Radiomics: images are more than pictures, they are data. Radiology 278:563–577CrossRefPubMedPubMedCentralGoogle Scholar
  12. 12.
    Itakura H, Achrol AS, Mitchell LA et al (2015) Magnetic resonance image features identify glioblastoma phenotypic subtypes with distinct molecular pathway activities. Science translational medicine 7:303ra138–303ra138CrossRefPubMedPubMedCentralGoogle Scholar
  13. 13.
    Yamamoto S, Han W, Kim Y et al (2015) Breast cancer: radiogenomic biomarker reveals associations among dynamic contrast-enhanced MR imaging, long noncoding RNA, and metastasis. Radiology 275:384–392CrossRefPubMedGoogle Scholar
  14. 14.
    Mattes D, Haynor DR, Vesselle H, Lewellen TK, Eubank W (2003) PET-CT image registration in the chest using free-form deformations. IEEE Transactions On Medical Imaging 22:120–128CrossRefPubMedGoogle Scholar
  15. 15.
    Zhang L, Fried DV, Fave XJ, Hunter LA, Yang J, Court LE (2015) IBEX: An open infrastructure software platform to facilitate collaborative work in radiomics. Medical Physics 42:1341–1353CrossRefPubMedPubMedCentralGoogle Scholar
  16. 16.
    Yang J, Zhang L, Fave XJ et al (2016) Uncertainty analysis of quantitative imaging features extracted from contrast-enhanced CT in lung tumors. Comput Med Imaging Graph 48:1–8CrossRefPubMedGoogle Scholar
  17. 17.
    Burger W, Burge MJ (2013) Edge-Preserving Smoothing FiltersPrinciples of Digital Image Processing. Springer, pp 119-167Google Scholar
  18. 18.
    Cunliffe AR, Armato Iii SG, Fei XM, Tuohy RE, Al-Hallaq HA (2013) Lung texture in serial thoracic CT scans: Registration-based methods to compare anatomically matched regionsa. Medical Physics 40:061906CrossRefPubMedPubMedCentralGoogle Scholar
  19. 19.
    Fried DV, Tucker SL, Zhou S et al (2014) Prognostic value and reproducibility of pretreatment CT texture features in stage III non-small cell lung cancer. Int J Radiat Oncol Biol Phys 90:834–842CrossRefPubMedPubMedCentralGoogle Scholar
  20. 20.
    Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE T. Syst. Man Cyb. 3:610–621CrossRefGoogle Scholar
  21. 21.
    Tang X (1998) Texture information in run-length matrices. IEEE Transactions on Image Processing 7:1602–1609CrossRefPubMedGoogle Scholar
  22. 22.
    Legland D, Kiêu K, Devaux M-F (2007) Computation of Minkowski measures on 2D and 3D binary images. Image Anal Stereol 26:83–92CrossRefGoogle Scholar
  23. 23.
    Basu S (2012) Developing predictive models for lung tumor analysis.Google Scholar
  24. 24.
    Amadasun M, King R (1989) Textural Features Corresponding to Textural Properties. Ieee Transactions on Systems Man and Cybernetics 19:1264–1274CrossRefGoogle Scholar
  25. 25.
    Dalal N, Triggs B (2005) Histograms of oriented gradients for human detection IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR) pp 886-893Google Scholar
  26. 26.
    Tiwari P, Prasanna P, Wolansky L et al (2016) Computer-Extracted Texture Features to Distinguish Cerebral Radionecrosis from Recurrent Brain Tumors on Multiparametric MRI: A Feasibility Study. AJNR Am J Neuroradiol.
  27. 27.
    Galizia MS, Töre HG, Chalian H, McCarthy R, Salem R, Yaghmai V (2012) MDCT necrosis quantification in the assessment of hepatocellular carcinoma response to yttrium 90 radioembolization therapy: comparison of two-dimensional and volumetric techniques. Academic Radiology 19:48–54CrossRefPubMedGoogle Scholar
  28. 28.
    Lin LIK (1989) A Concordance Correlation Coefficient to Evaluate Reproducibility. Biometrics 45:255–268CrossRefPubMedGoogle Scholar
  29. 29.
    Duda RO, Hart PE, Stork DG (2001) Pattern Classification. John Wiley and Sons, Inc.Google Scholar
  30. 30.
    Seiffert C, Khoshgoftaar TM, Van Hulse J, Napolitano A (2010) RUSBoost: A Hybrid Approach to Alleviating Class Imbalance. Ieee Transactions on Systems Man and Cybernetics Part a-Systems and Humans 40:185-197Google Scholar
  31. 31.
    Barajas RF, Chang JS, Segal MR et al (2009) Differentiation of Recurrent Glioblastoma Multiforme from Radiation Necrosis after External Beam Radiation Therapy with Dynamic Susceptibility-weighted Contrast-enhanced Perfusion MR Imaging. Radiology 253:486–496CrossRefPubMedPubMedCentralGoogle Scholar
  32. 32.
    Kickingereder P, Burth S, Wick A et al (2016) Radiomic Profiling of Glioblastoma: Identifying an Imaging Predictor of Patient Survival with Improved Performance over Established Clinical and Radiologic Risk Models. Radiology 280:880–889CrossRefPubMedGoogle Scholar
  33. 33.
    Li H, Zhu Y, Burnside ES et al (2016) MR Imaging Radiomics Signatures for Predicting the Risk of Breast Cancer Recurrence as Given by Research Versions of MammaPrint, Oncotype DX, and PAM50 Gene Assays. Radiology:152110Google Scholar
  34. 34.
    Larroza A, Moratal D, Paredes-Sánchez A et al (2015) Support vector machine classification of brain metastasis and radiation necrosis based on texture analysis in MRI. Journal of Magnetic Resonance Imaging 42:1362–1368CrossRefPubMedGoogle Scholar
  35. 35.
    Shinohara RT, Sweeney EM, Goldsmith J et al (2014) Statistical normalization techniques for magnetic resonance imaging. NeuroImage: Clinical 6:9–19CrossRefGoogle Scholar

Copyright information

© European Society of Radiology 2017
corrected publication January 2018

Authors and Affiliations

  • Zijian Zhang
    • 1
    • 2
  • Jinzhong Yang
    • 2
  • Angela Ho
    • 2
    • 3
  • Wen Jiang
    • 4
  • Jennifer Logan
    • 4
  • Xin Wang
    • 2
  • Paul D. Brown
    • 4
  • Susan L. McGovern
    • 4
  • Nandita Guha-Thakurta
    • 5
  • Sherise D. Ferguson
    • 6
  • Xenia Fave
    • 2
  • Lifei Zhang
    • 2
  • Dennis Mackin
    • 2
  • Laurence E. Court
    • 2
  • Jing Li
    • 4
  1. 1.Central South University Xiangya HospitalChangshaChina
  2. 2.Department of Radiation PhysicsThe University of Texas MD Anderson Cancer CenterHoustonUSA
  3. 3.University of HoustonHoustonUSA
  4. 4.Department of Radiation OncologyThe University of Texas MD Anderson Cancer CenterHoustonUSA
  5. 5.Department of Diagnostic RadiologyThe University of Texas MD Anderson Cancer CenterHoustonUSA
  6. 6.Department of NeurosurgeryThe University of Texas MD Anderson Cancer CenterHoustonUSA

Personalised recommendations