A predictive model for distinguishing radiation necrosis from tumour progression after gamma knife radiosurgery based on radiomic features from MR images
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.
• 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
KeywordsDelta radiomic features MRI Radiation necrosis Brain metastases Gamma Knife radiosurgery
Area under the curve
Concordance correlation coefficient
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.
Written informed consent was waived by the Institutional Review Board.
Institutional Review Board approval was obtained.
• performed at one institution
- 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
- 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
- 17.Burger W, Burge MJ (2013) Edge-Preserving Smoothing FiltersPrinciples of Digital Image Processing. Springer, pp 119-167Google Scholar
- 23.Basu S (2012) Developing predictive models for lung tumor analysis.Google Scholar
- 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.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. https://doi.org/10.3174/ajnr.A4931
- 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
- 29.Duda RO, Hart PE, Stork DG (2001) Pattern Classification. John Wiley and Sons, Inc.Google Scholar
- 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
- 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