CT Gray-Level Texture Analysis as a Quantitative Imaging Biomarker of Epidermal Growth Factor Receptor Mutation Status in Adenocarcinoma of the Lung.

OBJECTIVE The purpose of this study was to investigate the radiogenomic correlation between CT gray-level texture features and epidermal growth factor receptor (EGFR) mutation status in adenocarcinoma of the lung. MATERIALS AND METHODS This retrospective study included 25 patients with exon 19 short inframe deletion (exon 19) and 21 patients with exon 21 L858R point (exon 21) EGFR mutations among 125 patients with EGFR mutant adenocarcinoma of the lung. The randomly formed control group consisted of 20 patients selected from 126 patients with EGFR mutation-negative (wild-type) adenocarcinomas. Five gray-level texture features (contrast, correlation, inverse difference moment, angular second moment, and entropy) were analyzed. RESULTS Contrast differentiated both exon 19 (p = 0.00027) and exon 21 (p = 0.00001) mutants from the wild type. Wild-type adenocarcinomas had high scores for contrast (mean, 1598.547) compared with EGFR mutants (mean, 679.463). Correlation differentiated both exon 19 (p = 0.017) and exon 21 (p = 0.0015) mutants from wild-type adenocarcinomas. Inverse difference moment differentiated exon 19 mutants from exon 21 mutants (p = 0.019) and both exon 19 (p = 0.044) and exon 21 (p = 0.00001) mutants from wild-type adenocarcinomas. Angular second moment and entropy were not associated with statistically significant differences between mutation statuses. CONCLUSION Contrast, correlation, and inverse difference moment texture features correlate with EGFR mutation status in adenocarcinoma of the lung. Further investigation with larger prospective studies is needed to validate the role of CT gray-level texture analysis as a quantitative imaging biomarker.

[1]  M. Meyerson,et al.  Exon 19 Deletion Mutations of Epidermal Growth Factor Receptor Are Associated with Prolonged Survival in Non–Small Cell Lung Cancer Patients Treated with Gefitinib or Erlotinib , 2006, Clinical Cancer Research.

[2]  York Springer,et al.  Ajcc Cancer Staging Manual. 7th Ed. New , 2010 .

[3]  Jin Mo Goo,et al.  Computerized texture analysis of persistent part-solid ground-glass nodules: differentiation of preinvasive lesions from invasive pulmonary adenocarcinomas. , 2014, Radiology.

[4]  Urs Ramer,et al.  An iterative procedure for the polygonal approximation of plane curves , 1972, Comput. Graph. Image Process..

[5]  Raúl San José Estépar,et al.  Kurtosis and Skewness of Density Histograms on Inspiratory and Expiratory CT Scans in Smokers , 2011, COPD.

[6]  Chaya S Moskowitz,et al.  Are there imaging characteristics associated with lung adenocarcinomas harboring ALK rearrangements? , 2014, Lung cancer.

[7]  Song Wang,et al.  Model-based reconstruction of multiple circular and elliptical objects from a limited number of projections , 1996, IEEE Trans. Image Process..

[8]  M. Victor Wickerhauser,et al.  Wavelets: Algorithms and Applications (Yves Meyer) , 1994, SIAM Rev..

[9]  Asadollah Shahbahrami,et al.  Parallel implementation of Gray Level Co-occurrence Matrices and Haralick texture features on cell architecture , 2011, The Journal of Supercomputing.

[10]  X. Chen,et al.  Comparative analysis of clinicoradiologic characteristics of lung adenocarcinomas with ALK rearrangements or EGFR mutations , 2015, European Radiology.

[11]  William E. Higgins,et al.  Efficient Gabor filter design for texture segmentation , 1996, Pattern Recognit..

[12]  D. Haber,et al.  Molecular predictors of response to epidermal growth factor receptor antagonists in non-small-cell lung cancer. , 2007, Journal of clinical oncology : official journal of the American Society of Clinical Oncology.

[13]  Kenji Suzuki,et al.  Prognostic Significance of the Standardized Uptake Value on Positron Emission Tomography in Patients with Multiple Clinical-N0 Lung Cancers , 2014, Thoracic and Cardiovascular Surgeon.

[14]  Jitendra Malik,et al.  Scale-Space and Edge Detection Using Anisotropic Diffusion , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[15]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[16]  Chien-Jen Chen,et al.  Epidermal Growth Factor Receptor Mutation Status in Stage I Lung Adenocarcinoma with Different Image Patterns , 2011, Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer.

[17]  Joel H. Saltz,et al.  Parallel four‐dimensional Haralick texture analysis for disk‐resident image datasets , 2007, Concurr. Comput. Pract. Exp..

[18]  Dong ping Tian,et al.  A Review on Image Feature Extraction and Representation Techniques , 2013 .

[19]  Robert M. Haralick,et al.  Textural Features for Image Classification , 1973, IEEE Trans. Syst. Man Cybern..

[20]  T. Mok,et al.  Better survival with EGFR exon 19 than exon 21 mutations in gefitinib-treated non-small cell lung cancer patients is due to differential inhibition of downstream signals. , 2008, Cancer letters.

[21]  Dorin Comaniciu,et al.  Mean Shift: A Robust Approach Toward Feature Space Analysis , 2002, IEEE Trans. Pattern Anal. Mach. Intell..

[22]  Q. M. Jonathan Wu,et al.  Face recognition using curvelet based PCA , 2008, 2008 19th International Conference on Pattern Recognition.

[23]  C. Mathers,et al.  GLOBOCAN 2012 v1.0, Cancer Incidence and Mortality Worldwide: IARC CancerBase No. 11 [Internet]. Lyon, France: International Agency for Research on Cancer , 2013 .

[24]  Apichat Suratanee,et al.  Haralick's Texture Features Computation Accelerated by GPUs for Biological Applications , 2009, HPSC.

[25]  Olivier Gevaert,et al.  Non-small cell lung cancer: identifying prognostic imaging biomarkers by leveraging public gene expression microarray data--methods and preliminary results. , 2012, Radiology.

[26]  Siamak Khorram,et al.  A feature-based image registration algorithm using improved chain-code representation combined with invariant moments , 1999, IEEE Trans. Geosci. Remote. Sens..

[27]  P. Granone,et al.  EGFR-Targeted Therapy for Non-Small Cell Lung Cancer: Focus on EGFR Oncogenic Mutation , 2013, International journal of medical sciences.

[28]  M. Takagi,et al.  Clinical impact of the new IASLC/ATS/ERS lung adenocarcinoma classification for chest surgeons , 2015, Surgery Today.

[29]  Dinesh Manocha,et al.  Efficient computation of a simplified medial axis , 2003, SM '03.

[30]  C. Compton,et al.  AJCC Cancer Staging Manual , 2002, Springer New York.

[31]  Alexander Norbash,et al.  The future of imaging biomarkers in radiologic practice: proceedings of the thirteenth annual ACR Forum. , 2014, Journal of the American College of Radiology : JACR.

[32]  Md. Monirul Islam,et al.  A review on automatic image annotation techniques , 2012, Pattern Recognit..

[33]  A. M. Andrew,et al.  Another Efficient Algorithm for Convex Hulls in Two Dimensions , 1979, Inf. Process. Lett..

[34]  P. Lambin,et al.  Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach , 2014, Nature Communications.

[35]  B. N. Chatterji,et al.  An FFT-based technique for translation, rotation, and scale-invariant image registration , 1996, IEEE Trans. Image Process..

[36]  Jacques Ferlay,et al.  GLOBOCAN 2012: Estimated cancer incidence, mortality and prevalence worldwide in 2012 , 2013 .

[37]  Guojun Lu,et al.  Review of shape representation and description techniques , 2004, Pattern Recognit..

[38]  Ho Yun Lee,et al.  Quantitative CT Analysis of Pulmonary Ground-Glass Opacity Nodules for the Distinction of Invasive Adenocarcinoma from Pre-Invasive or Minimally Invasive Adenocarcinoma , 2014, PloS one.

[39]  Carlota Costa,et al.  Pharmacogenetics of EGFR in lung cancer: perspectives and clinical applications. , 2012, Pharmacogenomics.

[40]  Ruzena Bajcsy,et al.  Multiresolution elastic matching , 1989, Comput. Vis. Graph. Image Process..

[41]  Alireza Khotanzad,et al.  Invariant Image Recognition by Zernike Moments , 1990, IEEE Trans. Pattern Anal. Mach. Intell..

[42]  Masaki Hara,et al.  Epidermal Growth Factor Receptor Gene Mutation and Computed Tomographic Findings in Peripheral Pulmonary Adenocarcinoma , 2006, Journal of thoracic oncology : official publication of the International Association for the Study of Lung Cancer.

[43]  Tahsin Kurc,et al.  Malignant‐lesion segmentation using 4D co‐occurrence texture analysis applied to dynamic contrast‐enhanced magnetic resonance breast image data , 2007, Journal of magnetic resonance imaging : JMRI.