Asian Pacific Journal of Cancer Prevention

Asian Pacific Journal of Cancer Prevention (아시아태평양암예방학회)
권호 표지
DOI QR코드

DOI QR Code

Prediction Models for Solitary Pulmonary Nodules Based on Curvelet Textural Features and Clinical Parameters

  • Wang, Jing-Jing (Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University) ;
  • Wu, Hai-Feng (Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University) ;
  • Sun, Tao (Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University) ;
  • Li, Xia (Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University) ;
  • Wang, Wei (Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University) ;
  • Tao, Li-Xin (Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University) ;
  • Huo, Da (Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University) ;
  • Lv, Ping-Xin (Department of Radiology, Beijing Chest Hospital, Capital Medical University) ;
  • He, Wen (Department of Radiology, Friendship Hospital, Capital Medical University) ;
  • Guo, Xiu-Hua (Department of Epidemiology and Health Statistics, School of Public Health, Capital Medical University)
  • Published : 2013.10.30
Download PDF
⟨ Previous Next ⟩

Abstract

Lung cancer, one of the leading causes of cancer-related deaths, usually appears as solitary pulmonary nodules (SPNs) which are hard to diagnose using the naked eye. In this paper, curvelet-based textural features and clinical parameters are used with three prediction models [a multilevel model, a least absolute shrinkage and selection operator (LASSO) regression method, and a support vector machine (SVM)] to improve the diagnosis of benign and malignant SPNs. Dimensionality reduction of the original curvelet-based textural features was achieved using principal component analysis. In addition, non-conditional logistical regression was used to find clinical predictors among demographic parameters and morphological features. The results showed that, combined with 11 clinical predictors, the accuracy rates using 12 principal components were higher than those using the original curvelet-based textural features. To evaluate the models, 10-fold cross validation and back substitution were applied. The results obtained, respectively, were 0.8549 and 0.9221 for the LASSO method, 0.9443 and 0.9831 for SVM, and 0.8722 and 0.9722 for the multilevel model. All in all, it was found that using curvelet-based textural features after dimensionality reduction and using clinical predictors, the highest accuracy rate was achieved with SVM. The method may be used as an auxiliary tool to differentiate between benign and malignant SPNs in CT images.

Keywords

References

  1. Acharya UR, Faust O, Sree SV, et al (2012). ThyroScreen system: high resolution ultrasound thyroid image characterization into benign and malignant classes using novel combination of texture and discrete wavelet transform. Comput Methods Programs Biomed, 107, 233-41. https://doi.org/10.1016/j.cmpb.2011.10.001
  2. Alzubi S, Islam N, Abbod M (2011). Multiresolution analysis using wavelet, ridgelet, and curvelet transforms for medical image segmentation. Int J Biomed Imaging, 2011, 136034.
  3. Arebey M, Hannan MA, Begum RA, et al (2012). Solid waste bin level detection using gray level co-occurrence matrix feature extraction approach. J Environ Manage, 104, 9-18. https://doi.org/10.1016/j.jenvman.2012.03.035
  4. Beadsmoore CJ, Screaton NJ (2003). Classification, staging and prognosis of lung cancer. Eur J Radiol, 45, 8-17. https://doi.org/10.1016/S0720-048X(02)00287-5
  5. Borrajo L, Romero R, Iglesias EL, et al (2011). Improving imbalanced scientific text classification using sampling strategies and dictionaries. J Integr Bioinform, 8, 176.
  6. Dettori L, Semler L (2007). A comparison of wavelet, ridgelet, and curvelet-based texture classification algorithms in computed tomography. Comput Biol Med, 37, 486-98. https://doi.org/10.1016/j.compbiomed.2006.08.002
  7. Dua S., Acharya UR, Chowriappa P, et al (2012). Wavelet-based energy features for glaucomatous image classification. IEEE Trans Inf Technol Biomed, 16, 80-7. https://doi.org/10.1109/TITB.2011.2176540
  8. Eltoukhy MM, Faye I, Samir BB (2010). Breast cancer diagnosis in digital mammogram using multiscale curvelet transform. Comput Med Imaging Graph, 34, 269-76. https://doi.org/10.1016/j.compmedimag.2009.11.002
  9. Erasmus JJ, Connolly JE., McAdams HP, et al (2000). Solitary pulmonary nodules: Part I. Morphologic evaluation for differentiation of benign and malignant lesions. Radiographics, 20, 43-58. https://doi.org/10.1148/radiographics.20.1.g00ja0343
  10. Gould MK, Ananth L, Barnett PG (2007). A clinical model to estimate the pretest probability of lung cancer in patients with solitary pulmonary nodules. Chest, 131, 383-8. https://doi.org/10.1378/chest.06-1261
  11. Guo L, Dai M, Zhu M (2012). Multifocus color image fusion based on quaternion curvelet transform. Opt Express, 20, 18846-60. https://doi.org/10.1364/OE.20.018846
  12. Gurney JW (1993). Determining the likelihood of malignancy in solitary pulmonary nodules with Bayesian analysis. Part I. Theory. Radiology, 186, 405-13. https://doi.org/10.1148/radiology.186.2.8421743
  13. Hart J (2011). Lung cancer in Oregon. Dose Response, 9, 410-5. https://doi.org/10.2203/dose-response.10-005.Hart
  14. Henschke CI, Yankelevitz DF, Mateescu I, et al (1997). Neural networks for the analysis of small pulmonary nodules. Clin Imaging 21, 390-9. https://doi.org/10.1016/S0899-7071(97)81731-7
  15. Herder GJ, van Tinteren H, Golding RP, et al (2005). Clinical prediction model to characterize pulmonary nodules: validation and added value of 18F-fluorodeoxyglucose positron emission tomography. Chest, 128, 2490-6. https://doi.org/10.1378/chest.128.4.2490
  16. Khan A, Herman PG, Vorwerk P, et al (1991). Solitary pulmonary nodules: comparison of classification with standard, thin-section, and reference phantom CT. Radiology, 179, 477-81. https://doi.org/10.1148/radiology.179.2.2014295
  17. Khorasani A, Daliri MR (2013). Estimation of neural firing rate: the wavelet density estimation approach. Biomed Tech (Berl), 58, 377-86.
  18. Ko JP, Berman EJ, Kaur M, et al (2012). Pulmonary Nodules: growth rate assessment in patients by using serial CT and three-dimensional volumetry. Radiology, 262, 662-71. https://doi.org/10.1148/radiol.11100878
  19. Li Y, Chen KZ, Wang J (2011). Development and validation of a clinical prediction model to estimate the probability of malignancy in solitary pulmonary nodules in Chinese people. Clin Lung Cancer, 12, 313-9. https://doi.org/10.1016/j.cllc.2011.06.005
  20. Ma X, Zhang Z, Hu Y, et al (2012). Combined surgical intervention treatments for lung cancer and coronary heart disease patients. Zhongguo Fei Ai Za Zhi, 15, 602-5.
  21. Matsuki Y, Nakamura K, Watanabe H, et al (2002). Usefulness of an artificial neural network for differentiating benign from malignant pulmonary nodules on high-resolution CT: evaluation with receiver operating characteristic analysis. AJR Am J Roentgenol, 178, 657-63. https://doi.org/10.2214/ajr.178.3.1780657
  22. Meselhy Eltoukhy M, Faye I, Belhaouari Samir B (2010). A comparison of wavelet and curvelet for breast cancer diagnosis in digital mammogram. Comput Biol Med, 40, 384-91. https://doi.org/10.1016/j.compbiomed.2010.02.002
  23. Nakamura K., Yoshida H, Engelmann R, et al (2000). Computerized analysis of the likelihood of malignancy in solitary pulmonary nodules with use of artificial neural networks. Radiology, 214, 823-30. https://doi.org/10.1148/radiology.214.3.r00mr22823
  24. Schultz EM, Sanders GD, Trotter PR, et al (2008). Validation of two models to estimate the probability of malignancy in patients with solitary pulmonary nodules. Thorax, 63, 335-41. https://doi.org/10.1136/thx.2007.084731
  25. Soerjomataram I, Lortet-Tieulent J, Parkin DM, et al (2012). Global burden of cancer in 2008: a systematic analysis of disability-adjusted life-years in 12 world regions. Lancet 380, 1840-50. https://doi.org/10.1016/S0140-6736(12)60919-2
  26. Sun T, Wang J, Li X, et al (2013a). Comparative evaluation of support vector machines for computer aided diagnosis of lung cancer in CT based on a multi-dimensional data set. Comput Methods Programs Biomed.
  27. Sun T, Zhang R, Wang J, et al (2013b). Computer-aided diagnosis for early-stage lung cancer based on longitudinal and balanced data. PLoS One, 8, e63559. https://doi.org/10.1371/journal.pone.0063559
  28. Swensen SJ, Silverstein MD, Ilstrup DM, et al (1997). The probability of malignancy in solitary pulmonary nodules. Application to small radiologically indeterminate nodules. Arch Intern Med, 157, 849-55. https://doi.org/10.1001/archinte.1997.00440290031002
  29. Wang H, Guo XH, Jia ZW, et al (2010). Multilevel binomial logistic prediction model for malignant pulmonary nodules based on texture features of CT image. Eur J Radiol, 74, 124-9. https://doi.org/10.1016/j.ejrad.2009.01.024
  30. Way TW, Sahiner B, Chan HP, et al (2009). Computer-aided diagnosis of pulmonary nodules on CT scans: improvement of classification performance with nodule surface features. Med Phys, 36, 3086-98. https://doi.org/10.1118/1.3140589
  31. Wu H, Sun T, Wang J, et al (2013). Combination of radiological and gray level co-occurrence matrix textural features used to distinguish solitary pulmonary nodules by computed tomography. J Digit Imaging, 26, 797-802. https://doi.org/10.1007/s10278-012-9547-6
  32. Zhu L, Gao Y, Appia V, et al (2013). Automatic Delineation of the Myocardial Wall from CT Images via Shape Segmentation and Variational Region Growing. IEEE Trans Biomed Eng, 60, 2887-95. https://doi.org/10.1109/TBME.2013.2266118

Cited by

  1. Contourlet Textual Features: Improving the Diagnosis of Solitary Pulmonary Nodules in Two Dimensional CT Images vol.9, pp.9, 2014, https://doi.org/10.1371/journal.pone.0108465
  2. Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine vol.14, pp.1, 2015, https://doi.org/10.1186/s12938-015-0003-y
  3. Evaluation of Machine Learning Algorithm Utilization for Lung Cancer Classification Based on Gene Expression Levels vol.17, pp.2, 2016, https://doi.org/10.7314/APJCP.2016.17.2.835
  4. Effects of contrast-enhancement, reconstruction slice thickness and convolution kernel on the diagnostic performance of radiomics signature in solitary pulmonary nodule vol.6, pp.1, 2016, https://doi.org/10.1038/srep34921