The utility of quantitative CT radiomics features for improved prediction of radiation pneumonitis

PURPOSE The purpose of this study was to explore gains in predictive model performance for radiation pneumonitis (RP) using pretreatment CT radiomics features extracted from the normal lung volume. METHODS A total of 192 patients treated for nonsmall cell lung cancer with definitive radiotherapy were considered in the current study. In addition to clinical and dosimetric data, CT radiomics features were extracted from the total lung volume defined using the treatment planning scan. A total of 6851 features (15 clinical, 298 total lung and heart dosimetric, and 6538 image features) were gathered and considered candidate predictors for modeling of RP grade ≥3. Models were built with the least absolute shrinkage and selection operator (LASSO) logistic regression and applied to the set of candidate predictors with 50 iterations of tenfold nested cross-validation. RESULTS In the current cohort, 30 of 192 patients (15.6%) presented with RP grade ≥3. Average cross-validated AUC (CV-AUC) using only the clinical and dosimetric parameters was 0.51. CV-AUC was 0.68 when total lung CT radiomics features were added. Analysis with the entire set of available predictors revealed seven different image features selected in at least 40% of the model fits. CONCLUSIONS We have successfully incorporated CT radiomics features into a framework for building predictive RP models via LASSO logistic regression. Addition of normal lung image features produced superior model performance relative to traditional dosimetric and clinical predictors of RP, suggesting that pretreatment CT radiomics features should be considered in the context of RP prediction.

[1]  R. Mohan,et al.  Impact of toxicity grade and scoring system on the relationship between mean lung dose and risk of radiation pneumonitis in a large cohort of patients with non-small cell lung cancer. , 2010, International journal of radiation oncology, biology, physics.

[2]  Y. Benjamini,et al.  Controlling the false discovery rate: a practical and powerful approach to multiple testing , 1995 .

[3]  Trevor Hastie,et al.  Regularization Paths for Generalized Linear Models via Coordinate Descent. , 2010, Journal of statistical software.

[4]  Johannes A Langendijk,et al.  The impact of heart irradiation on dose-volume effects in the rat lung. , 2007, International journal of radiation oncology, biology, physics.

[5]  E. Kunieda,et al.  Severe COPD is correlated with mild radiation pneumonitis following stereotactic body radiotherapy. , 2012, Chest.

[6]  K P Whittall,et al.  Selection of patients for lung volume reduction surgery using a power law analysis of the computed tomographic scan , 2003, Thorax.

[7]  J. Deasy,et al.  Predicting radiation-induced valvular heart damage , 2015, Acta oncologica.

[8]  R M Slone,et al.  Patient selection for lung volume reduction surgery: An objective model based on prior clinical decisions and quantitative CT analysis. , 2000, Chest.

[9]  Patrick Granton,et al.  Radiomics: extracting more information from medical images using advanced feature analysis. , 2012, European journal of cancer.

[10]  S. Roberts,et al.  Stabilizing the lasso against cross-validation variability , 2014, Comput. Stat. Data Anal..

[11]  E. V. van Beek,et al.  Computer-aided classification of interstitial lung diseases via MDCT: 3D adaptive multiple feature method (3D AMFM). , 2006, Academic radiology.

[12]  Shulian Wang,et al.  Nondosimetric risk factors for radiation-induced lung toxicity. , 2015, Seminars in radiation oncology.

[13]  H. Zou,et al.  Regularization and variable selection via the elastic net , 2005 .

[14]  Zhongxing Liao,et al.  Investigation of the relationship between gross tumor volume location and pneumonitis rates using a large clinical database of non-small-cell lung cancer patients. , 2012, International journal of radiation oncology, biology, physics.

[15]  Joseph O Deasy,et al.  The lessons of QUANTEC: recommendations for reporting and gathering data on dose-volume dependencies of treatment outcome. , 2010, International journal of radiation oncology, biology, physics.

[16]  Issam El Naqa,et al.  Heart irradiation as a risk factor for radiation pneumonitis , 2011, Acta oncologica.

[17]  Paul Kinahan,et al.  Radiomics: Images Are More than Pictures, They Are Data , 2015, Radiology.

[18]  K. Hayakawa,et al.  Risk factors for severe radiation pneumonitis in lung cancer. , 1999, Japanese journal of clinical oncology.

[19]  R. Castillo,et al.  Pre-Radiation Therapy Fluorine 18 Fluorodeoxyglucose PET Helps Identify Patients with Esophageal Cancer at High Risk for Radiation Pneumonitis. , 2015, Radiology.

[20]  Kurt Hornik,et al.  The Design and Analysis of Benchmark Experiments , 2005 .

[21]  Max Kuhn,et al.  Building Predictive Models in R Using the caret Package , 2008 .

[22]  N. Sanuki,et al.  Association of computed tomography-detected pulmonary interstitial changes with severe radiation pneumonitis for patients treated with thoracic radiotherapy. , 2012, Journal of radiation research.

[23]  Radhe Mohan,et al.  Analysis of radiation pneumonitis risk using a generalized Lyman model. , 2008, International journal of radiation oncology, biology, physics.

[24]  M. Martel,et al.  A novel method to incorporate the spatial location of the lung dose distribution into predictive radiation pneumonitis modeling. , 2012, International journal of radiation oncology, biology, physics.

[25]  M. Martel,et al.  Radiation dose-volume effects in the lung. , 2010, International journal of radiation oncology, biology, physics.

[26]  Jinzhong Yang,et al.  Measuring Computed Tomography Scanner Variability of Radiomics Features , 2015, Investigative radiology.

[27]  Y. Nishiyama,et al.  Radiation pneumonitis in patients with lung and mediastinal tumours: a retrospective study of risk factors focused on pulmonary emphysema. , 2012, The British journal of radiology.

[28]  P. Lambin,et al.  Predicting outcomes in radiation oncology—multifactorial decision support systems , 2013, Nature Reviews Clinical Oncology.

[29]  J. Deasy,et al.  Modeling radiation pneumonitis risk with clinical, dosimetric, and spatial parameters. , 2006, International journal of radiation oncology, biology, physics.

[30]  I. Vogelius,et al.  A literature-based meta-analysis of clinical risk factors for development of radiation induced pneumonitis , 2012, Acta oncologica.

[31]  E. Hoffman,et al.  Characterization of the interstitial lung diseases via density-based and texture-based analysis of computed tomography images of lung structure and function. , 2003, Academic radiology.

[32]  M. Martel,et al.  High quality machine-robust image features: identification in nonsmall cell lung cancer computed tomography images. , 2013, Medical physics.

[33]  R. Mohan,et al.  Is there an impact of heart exposure on the incidence of radiation pneumonitis? Analysis of data from a large clinical cohort , 2014, Acta oncologica.

[34]  Radhe Mohan,et al.  Influence of technologic advances on outcomes in patients with unresectable, locally advanced non-small-cell lung cancer receiving concomitant chemoradiotherapy. , 2010, International journal of radiation oncology, biology, physics.

[35]  Trevor J. Hastie,et al.  Genome-wide association analysis by lasso penalized logistic regression , 2009, Bioinform..

[36]  L. Marks,et al.  Challenges in defining radiation pneumonitis in patients with lung cancer. , 2005, International journal of radiation oncology, biology, physics.

[37]  D. Hansell,et al.  Obstructive lung diseases: texture classification for differentiation at CT. , 2003, Radiology.

[38]  H. Zou.  The Adaptive Lasso and Its Oracle Properties , 2006 .

[39]  S. Armato,et al.  Lung texture in serial thoracic computed tomography scans: correlation of radiomics-based features with radiation therapy dose and radiation pneumonitis development. , 2015, International journal of radiation oncology, biology, physics.

[40]  R. Mohan,et al.  Dose-volume thresholds and smoking status for the risk of treatment-related pneumonitis in inoperable non-small cell lung cancer treated with definitive radiotherapy. , 2009, Radiotherapy and oncology : journal of the European Society for Therapeutic Radiology and Oncology.

[41]  R. Tibshirani.  Regression Shrinkage and Selection via the Lasso , 1996 .

[42]  A. van der Schaaf,et al.  Statistical validation of normal tissue complication probability models. , 2012, International journal of radiation oncology, biology, physics.

[43]  Lawrence B Marks,et al.  Regional lung density changes after radiation therapy for tumors in and around thorax. , 2010, International journal of radiation oncology, biology, physics.