Lung cancer subtype differentiation from positron emission tomography images

Lung cancer is one of the deadly cancer types, and almost 85% of lung cancers are nonsmall cell lung cancer NSCLC . In the present study we investigated classification and feature selection methods for the differentiation of two subtypes of NSCLC, namely adenocarcinoma ADC and squamous cell carcinoma SqCC . The major advances in understanding the effects of therapy agents suggest that future targeted therapies will be increasingly subtype specific. We obtained positron emission tomography PET images of 93 patients with NSCLC, 39 of which had ADC while the rest had SqCC. Random walk segmentation was applied to delineate three-dimensional tumor volume, and 39 texture features were extracted to grade the tumor subtypes. We examined 11 classifiers with two different feature selection methods and the effect of normalization on accuracy. The classifiers we used were the k-nearest-neighbor, logistic regression, support vector machine, Bayesian network, decision tree, radial basis function network, random forest, AdaBoostM1, and three stacking methods. To evaluate the prediction accuracy we performed a leave-one-out cross-validation experiment on the dataset. We also considered optimizing certain hyperparameters of these models by performing 10-fold cross-validation separately on each training set. We found that the stacking ensemble classifier, which combines a decision tree, AdaBoostM1, and logistic regression methods by a metalearner, was the most accurate method for detecting subtypes of NSCLC, and normalization of feature sets improved the accuracy of the classification method.

___

  • 1] Detterbeck FC, Boffa DJ, Tanoue LT. The new lung cancer staging system. Chest 2009; 136 (1): 260-271. doi: 10.1378/chest.08-0978
  • [2] Anagnostou VK, Dimou AT, Botsis T, Killiam EJ, Gustavson MD et al. Molecular classification of non-small cell lung cancer using a 4-protein quantitative assay. Cancer 2012; 118 (6): 1607-1618. doi:10.1002/cncr.26450.
  • [3] Travis WD, Brambilla E, Nicholson AG, Yatabe Y, Austin JHM et al. The 2015 World Health Organization classification of lung tumors: impact of genetic, clinical and radiologic advances since the 2004 classification. Journal of Thoracic Oncology 2015; 10 (9): 1243-1260. doi: 10.1097/JTO.0000000000000630
  • [4] Kumar V, Gu Y, Basu S, Berglund A, Eschrich SA et al. Radiomics: the process and the challenges. Magnetic Resonance Imaging 2012; 30 (9): 1234-1248. doi: 10.1016/j.mri.2012.06.010
  • [5] Orlhac F, Soussan M, Chouahnia K, Martinod E, Buvat I. 18F-FDG PET-derived textural indices reflect tissue-specific uptake pattern in non-small cell lung cancer. PloS One 2015; 10 (12): 1-16. doi: 10.1371/journal.pone.0145063
  • [6] Ypsilantis PP, Siddique M, Sohn HM, Davies A, Cook G et al. Predicting response to neoadjuvant chemotherapy with PET imaging using convolutional neural networks. PloS One 2015; 10 (9): e0137036. doi: 10.1371/journal.pone.0137036
  • [7] Aerts HJWL, Velazquez ER, Leijenaar RTH, Parmar C, Grossmann P et al. Decoding tumour phenotype by noninvasive imaging using a quantitative radiomics approach. Nature Communication 2014; 5: 4006. doi: 10.1038/ncomms5006
  • [8] Samala R, Moreno W, You Y, Qian W. A novel approach to nodule feature optimization on thin section thoracic CT. Academic Radiology 2009; 16 (4): 418-427. doi: 10.1016/j.acra.2008.10.009
  • [9] Balagurunathan Y, Gu Y, Wang H, Kumar V, Grove O et al. Reproducibility and prognosis of quantitative features extracted from CT images. Translational Oncology 2014; 7 (1): 72-87. doi: 10.1593/tlo.13844
  • [10] Hawkins SH, Korecki JN, Balagurunathan Y, Gu Y, Kumar V et al. Predicting outcomes of nonsmall cell lung cancer using CT image features. IEEE Access 2014; 2: 1418-1426. doi: 10.1109/ACCESS.2014.2373335
  • [11] Aerts HJWL, Grossmann P, Tan Y, Oxnard GR, Rizvi N et al. Defining a radiomic response phenotype: a pilot study using targeted therapy in NSCLC. Science Report 2016; 6: 33860. doi: 10.1038/srep33860
  • [12] Yu KH, Zhang C, Berry GJ, Altman RB, Re C et al. Predicting non-small cell lung cancer prognosis by fully automated microscopic pathology image features. Nature Communication 2016; 7: 12474. doi: 10.1038/ncomms12474
  • [13] Kourou K, Exarchos TP, Exarchos KP, Karamouzis MV, Fotiadis DI. Machine learning applications in cancer prognosis and prediction. Computational and Structural Biotechnology Journal 2015; 13: 8-17. doi: 10.1016/j.csbj.2014.11.005
  • [14] Parmar C, Grossmann P, Bussink J, Lambin P, Aerts HJWL. Machine learning methods for quantitative radiomic biomarkers. Scientific Report 2015; 5: 13087. doi: 10.1038/srep13087
  • [15] Menden MP, Iorio F, Garnett M, McDermott U, Benes CH et al. Machine learning prediction of cancer cell sensitivity to drugs based on genomic and chemical properties. PloS One 2013; 8 (4): e61318. doi: 10.1371/journal.pone.0061318
  • [16] Haury AC, Gestraud P, Vert JP. The influence of feature selection methods on accuracy, stability and interpretability of molecular signatures. PloS One 2011; 6 (12): 1-12. doi: 10.1371/journal.pone.0028210
  • [17] Ha S, Choi H, Cheon GJ, Kang KW, Chung JK et al. Autoclustering of non-small cell lung carcinoma subtypes on 18F-FDG PET using texture analysis: a preliminary result. Nuclear Medicine and Molecular Imaging 2014; 48 (4): 278-286. doi: 10.1007/s13139-014-0283-3
  • [18] Ju W, Xiang D, Zhang B, Wang L, Kopriva I et al. Random walk and graph cut for co-segmentation of lung tumor on PET-CT Images. IEEE Transactions on Image Processing 2015; 24 (12): 5854-5867. doi: 10.1109/TIP.2015.2488902
  • [19] Eset K, Icer K, Karacavus S, Yilmaz B, Kayaalti O et al. Comparison of lung tumor segmentation methods on PET images. In: Tiptekno 2015 Medical Technologies National Conference; Bodrum, Turkey; 2015. pp. 1-4 (in Turkish with an abstract in English).
  • [20] Leijenaar RTH, Nalbantov G, Carvalho S, Elmpt WJC, Troost EGC et al. The effect of SUV discretization in quantitative FDG-PET radiomics: the need for standardized methodology in tumor texture analysis. Scientific Report 2015; 5: 11075. doi: 10.1038/srep11075
  • [21] Vallières M, Freeman CR, Skamene SR, El Naqa I. A radiomics model from joint FDG-PET and MRI texture features for the prediction of lung metastases in soft-tissue sarcomas of the extremities. Physics in Medicine and Biology 2015; 60 (14): 5471-5496. doi: 10.1088/0031-9155/60/14/5471
  • [22] Hall M, Frank E, Holmes G, Pfahringer B, Reutemann P et al. The WEKA data mining software: an update. SIGKDD Explorations 2009; 11 (1): 10-18. doi: 10.1145/1656274.1656278
  • [23] Bishop CM, Nasrabadi N. Pattern Recognition and Machine Learning. New York, NY, USA: Springer, 2006. doi: 10.1117/1.2819119
  • [24] Cortes C, Vapnik V. Support-vector networks. Machine Learning 1995; 20 (3): 273-297. doi: 10.1023/A:1022627411411
  • [25] Chang C, Lin C. LIBSVM: a library for support vector machines. ACM Transactions Intelligent System Technology 2013; 2: 1-39. doi: 10.1145/1961189.1961199
  • [26] Salzberg SL. Book Review: C4.5: Programs for Machine Learning by J. Ross Quinlan. Morgan Kaufmann Publishers, Inc., 1993. Machine Learning 1994; 16: 235-240. doi: 10.1023/A:1022645310020
  • [27] Friedman N, Geiger D, Goldszmidt M. Bayesian network classifiers. Machine Learning 1997; 29: 131-163. doi: 10.1023/A:1007465528199
  • [28] Lowe D. Multivariable functional interpolation and adaptive networks. Complex System 1988; 2: 321-355.
  • [29] Breiman L. Random forests. Machine Learning 1999; 45 (5): 1-35. doi: 10.1023/A:1010933404324
  • [30] Freund Y, Schapire RRE. Experiments with a new boosting algorithm. In: Thirteenth International Conference on ML; Bari, Italy; 1996. pp. 148-156.
  • [31] Wolpert DH. Stacked generalization. Neural Networks 1992; 5 (2): 241-259.
  • [32] Feng PH, Chen TT, Lin YT, Chiang SY, Lo CM. Classification of lung cancer subtypes based on autofluorescence bronchoscopic pattern recognition: a preliminary study. Computer Methods and Programs in Biomedicine 2018; 163: 33–38. doi: 10.1016/j.cmpb.2018.05.016
  • [33] Hua KL, Hsu CH, Hidayati SC, Cheng WH, Chen YJ. Computer-aided classification of lung nodules on computed tomography images via deep learning technique. Onco Targets and Therapy 2015; 8: 2015-2022. doi: 10.2147/OTT.S80733