A Comparative Texture Analysis Based on NECT and CECT Images to Differentiate Lung Adenocarcinoma from Squamous Cell Carcinoma
- 31 Downloads
The purpose of the study was to compare the texture based discriminative performances between non-contrast enhanced computed tomography (NECT) and contrast-enhanced computed tomography (CECT) images in differentiating lung adenocarcinoma (ADC) from squamous cell carcinoma (SCC) patients. Eighty-seven lung cancer subjects were enrolled in the study, including pathologically proved 47 ADC patients and 40 SCC patients, and 261 texture features were extracted from the manually delineated region of interests on CECT and NECT images respectively. Fisher score was then used to select the effective discriminative texture features between groups, and the selected texture features were adopted to differentiate ADC from SCC using Support Vector Machine and Leave-one-out cross-validation. Both NECT and CECT images could achieve the same best classification accuracy of 95.4%, and most of the informative features were from the gray-level co-occurrence matrix. In addition, CECT images were found with enhanced texture features compared with NECT images, and combining texture features of CECT and NECT images together could further improve the prediction accuracy. Besides the texture feature, the tumor location information also contributed to the differential diagnosis between ADC and SCC.
KeywordsTexture analysis Lung adenocarcinoma Squamous cell carcinoma Non-contrast enhanced computed tomography Contrast enhanced computed tomography
This work was supported by National Natural Science Foundation of China (grant numbers 81220108007), Beijing Natural Science Foundation (No. 4122018). Bin Jing was supported by Beijing Natural Science Foundation (No. 7174282).
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the national research committee.
For this type of study formal consent is not required.
- 6.Thunnissen, E., Noguchi, M., Aisner, S. et al., Reproducibility of histopathological diagnosis in poorly differentiated NSCLC: An international multiobserver study. J. Thorac. Oncol. 10(1):1354–1362, 2015.Google Scholar
- 8.Dilger, S. K., Uthoff, J., Judisch, A. et al., Improved pulmonary nodule classification utilizing quantitative lung parenchyma features. J. Med. Imaging 2(4):041004, 2015.Google Scholar
- 10.Orozco, H. M., OOV, V., VGC, S. et al., Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine. Biomed. Eng. Online 14(1):1–20, 2015.Google Scholar
- 12.Hwang, I. P., Park, C. M., Park, S. J. et al., Persistent pure ground-glass nodules larger than 5 mm: Differentiation of invasive pulmonary adenocarcinomas from preinvasive lesions or minimally invasive adenocarcinomas using texture analysis. Investig. Radiol. 50(11):798–804, 2015.Google Scholar
- 17.Emaminejad, N., Qian, W., Kang, Y. et al., Exploring new quantitative CT image features to improve assessment of lung cancer prognosis. In: SPIE Medical Imaging, 2015, 94141M.Google Scholar
- 18.Balaji, G., Sandra, A., RCD, Y. et al., Texture analysis of non-small cell lung cancer on unenhanced computed tomography: Initial evidence for a relationship with tumour glucose metabolism and stage. Cancer Imaging 10(1):137–143, 2010.Google Scholar
- 21.Materka, A., and Klepaczko, A., MaZda-A software package for image texture analysis. Comput. Methods Prog. Biomed. 94(1):66–76, 2009.Google Scholar
- 23.Haralick, R. M., Shanmugam, K., and Dinstein, I., Textural features for image classification. IEEE Trans. Syst. Man Cybern. smc. 3(6):610–621, 1973.Google Scholar
- 24.Szczypiński, P. M., Strzelecki, M., Materka, A. et al., MaZda – the software package for textural analysis of biomedical images. Berlin: Springer, 2009, 73–84.Google Scholar
- 25.Duda, R. O., Hart, P. E., and Stork, D. G., Pattern classification. 2nd edition, Wiley, New York, 2001.Google Scholar
- 27.Chang, C. C., and Lin, C. J., LIBSVM: A library for support vector machines. ACM Trans. Intell. Syst. Technol. 2(3):1–27, 2011.Google Scholar
- 29.Lubner, M. G., Smith, A. D., Sandrasegaran, K. et al., CT texture analysis: Definitions, applications, biologic correlates, and challenges. Radiographics A Review Publication of the Radiological Society of North America Inc. 37(5):1483, 2017.Google Scholar