|
|
|
| Correlation between lung cancer EGFR mutation status and CT texture GLCM |
| LV Chang-sheng, WANG Jin, XU Zhi-jie, WANG Jin-guang |
| The First Affiliated Hospital of Dalian Medical University, Dalian Liaoning 116011, China |
|
|
|
|
Abstract Objective: To investigate correlation between CT gray-level texture features and epidermal growth factor receptor mutation status in lung adenocarcinoma. Methods: Sixty-four adenocarcinoma patients’ clinical and imaging data were studied retrospectively and which were classified into exon 21 mutation group, exon 19 mutation group and wild type group. Using ImageJ software to extract the values of the five characteristics(energy, contrast, inverse difference moment, entropy, autocorrelation) of tumor with axial maximum diameter in chest CT with lung window, then perform single factor analysis of variance of variance and t test for statistic analysis. Results: Wild-type adenocarcinomas had high scores for contrast(mean: 1 027.734) compared with exon 19 mutants(mean:560.127) and exon 21 mutants(mean:331.987). The differences in contrast, inverse difference moment, correlation between exon 21 mutation group, exon 19 mutation group and wild type group all had statistically significant differences(P＜0.05). The difference in contrast between exon 21 mutation group, exon 19 mutation group had statistical significant difference(P=0.007). The solid nodules accounted for 57.8% of EGFR mutant patients, accounting for 47.3% of wild type patients, while the age, lobulation sign, irregular margin and air bronchograms, were not correlated with EGFR mutation rate. Conclusion: Using GLCM to extract texture feature from lung CT images and find Contrast, Correlation, Inverse difference moment to describe EGFR mutations in lung cancer have better results, which could provide some reference value for predicting lung cancer patients with EGFR mutations through quantitative analysis from CT. And there can be as quantitative imaging biomarkers to establish contact between lung cancer imaging and gene mutation.
|
|
Received: 24 December 2016
|
|
|
|
|
|
[1]Torre LA, Bray F, Siegel RL, et al. Global cancer statistics, 2012[J]. CA Cancer J Clin, 2015, 65(2): 87-108.
[2]Kuo MD, Jamshidi N, et al. Behind the numbers: Decoding molecular phenotypes with radiogenomics-guiding principles and technical considerations[J]. Radiology, 2014, 70(2): 320-325.
[3]Hsu JS, Huang MS, Chen CY et al. Correlation between EGFR mutation status and computed tomography features in patients with advanced pulmonary adenocarcinoma[J]. J Thorac Imaging, 2014, 29(6): 357-363.
[4]Krishnaraj A, Weinreb JC, Ellenbogen PH, et al. The future of imaging biomarkers in radiologic practice: proceedings of the thirteenth annual ACR forum[J]. J Am Coll Radiol, 2014, 11(1): 20-23.
[5]Haralick R, Shanmugam K, Dinstein I. Textural features for image classification[J]. IEEE Trans Syst Man Cybern, 1973, 3(6): 610-621.
[6]Hsu KH, Chen KC, Yang TY, et al. Epidermal growth factor receptor mutation status in stage I lung adenocarcinoma with different image patterns[J]. J Thorac Oncol, 2011, 6(6): 1066-1072.
[7]Usuda K, Sagawa M, Motono N, et al. Relationships between EGFR mutation status of lung cancer and preoperative factors-are they predictive?[J]. Asian Pac J Cancer Prev, 2014, 15(2): 657-662.
[8]Park EA, Lee HJ, Kim YT, et al. EGFR gene copy number in adenocarcinoma of the lung by FISH analysis: investigation of significantly related factors on CT, FDG-PET, and histopathology[J]. Lung Cancer, 2009, 64(2): 179-186.
[9]Sugano M, Shimizu K, Nakano T, et al. Correlation between computed tomography findings and epidermal growth factor receptor and KRAS gene mutations in patients with pulmonary adenocarcinoma[J]. Oncol Rep, 2011, 26(5): 1205-1211.
[10]Gevaert O, Xu J, Hoang CD, et al. Non-small cell lung cancer: identifying prognostic imaging biomarkers by leveraging public gene expression microarray data—methods and preliminary results[J]. Radiology, 2012, 264(2): 387-396.
[11]Ashraf AB, Daye D, Gavenonis S, et al. Identification of intrinsic imaging phenotypes for breast cancer tumors: preliminary associations with gene expression profiles[J]. Radiology, 2014, 272(2): 374-384.
[12]王瓛，郭秀花，李坤成，等. 良恶性肺小结节CT图像基于灰度共生矩阵10种纹理特征研究[J]. 北京生物医学工程，2008，27（6）：561-564. |
|
|
|
2017, Vol. 28 
