Detection of lung cancer on chest CT images using minimum redundancy maximum relevance feature selection method with convolutional neural networks

• Autorzy: Togaçar Mesut , Ergen Burhan , Cömert Zafer

Identyfikatory

DOI

10.1016/j.bbe.2019.11.004

• Języki publikacji: EN

Abstrakty

EN

Lung cancer is a disease caused by the involuntary increase of cells in the lung tissue. Early detection of cancerous cells is of vital importance in the lungs providing oxygen to the human body and excretion of carbon dioxide in the body as a result of vital activities. In this study, the detection of lung cancers is realized using LeNet, AlexNet and VGG-16 deep learning models. The experiments were carried out on an open dataset composed of Computed Tomography (CT) images. In the experiment, convolutional neural networks (CNNs) were used for feature extraction and classification purposes. In order to increase the success rate of the classification, the image augmentation techniques, such as cutting, zooming, horizontal turning and filling, were applied to the dataset during the training of the models. Because of the outstanding success of AlexNet model, the features obtained from the last fully-connected layer of the model were separately applied as the input to linear regression (LR), linear discriminant analysis (LDA), decision tree (DT), support vector ma-chine (SVM), k -nearest neighbor (kNN) and softmax classifiers. A combination of AlexNet model and k NN classifier achieved the most efficient classification accuracy as 98.74 %. Then, the minimum redundancy maximum relevance (mRMR) feature selection method was applied to the deep feature set to choose the most efficient features. Consequently, the success rate was yielded as 99.51 % by reclassifying the dataset with the selected features and k NN model. The proposed model is consistent diagnosis model for lung cancer detection using chest CT images.

Słowa kluczowe

EN

biomedical image processing; diagnosis system; lung cancer; convolutional neural network; machine learning

PL

przetwarzanie obrazów biomedycznych; system diagnostyczny; rak płuca; konwolucyjna sieć neuronowa; uczenie maszynowe

• Wydawca: Nałęcz Institute of Biocybernetics and Biomedical Engineering of the Polish Academy of Sciences ; Elsevier
• Czasopismo: Biocybernetics and Biomedical Engineering
• Rocznik: 2020
• Tom: Vol. 40, no. 1
• Strony: 23--39
• Opis fizyczny: Bibliogr. 61 poz., rys., tab., wykr.

Twórcy

autor

Togaçar Mesut

• Department of Computer Technology, Firat University Elazig, Turkey

autor

Ergen Burhan

• Department of Computer Engineering, Faculty of Engineering, Firat University Elazig, Turkey

autor

Cömert Zafer

• Department of Software Engineering, Faculty of Engineering and Architecture, Samsun University Samsun, Turkey

Bibliografia

• [1] Fribert P, Paulová L, Patáková P, Rychtera M, Melzoch K. Alternativní metody separace kapalných biopaliv z média pri fermentaci. Chem List 2013;107:843–7. http://dx.doi.org/10.3322/caac.21492.
• [2] World Health Organization. World health statistics; 2018.
• [3] Guo Y, Shang X, Li Z. Identification of cancer subtypes by integrating multiple types of transcriptomics data with deep learning in breast cancer. Neurocomputing 2019;324:20–30. http://dx.doi.org/10.1016/j.neucom.2018.03.072.
• [4] Torre LA, Bray F, Siegel RL, Ferlay J, Lortet-Tieulent J, Jemal A. Global cancer statistics, 2012. CA Cancer J Clin 2015;65:87–108. http://dx.doi.org/10.3322/caac.21262.
• [5] Koike W, Iwano S, Matsuo K, Kitano M, Kawakami K, Naganawa S. Doubling time calculations for lung cancer by three-dimensional computer-aided volumetry: effects of inter-observer differences and nodule characteristics. J Med Imaging Radiat Oncol 2014;58:82–8. http://dx.doi.org/10.1111/1754-9485.12128.
• [6] Wilson AC, Roelofs R, Stern M, Srebro N, Recht B. The Marginal Value of Adaptive Gradient Methods in Machine Learning arXiv : 1705. 08292v2 [stat. ML] 22 May 2018; 2017.
• [7] Liao Q, Ding Y, Jiang ZL, Wang X, Zhang C, Zhang Q. Multi- task deep convolutional neural network for cancer diagnosis. Neurocomputing 2018. http://dx.doi.org/10.1016/j.neucom.2018.06.084.
• [8] Ye X, Lin X, Dehmeshki J, Slabaugh G, Beddoe G. Shape-based computer-aided detection of lung nodules in thoracic CT images. IEEE Trans Biomed Eng 2009;56:1810–20. http://dx.doi.org/10.1109/TBME.2009.2017027.
• [9] Albertina B, Watson M, Holback C, Jarosz R, Kirk S, Lee Y. Radiology data from the Cancer genome atlas lung adenocarcinoma [TCGA-LUAD] collection. Cancer Imaging Arch 2016. http://dx.doi.org/10.7937/K9/TCIA.2016.JGNIHEP5.
• [10] Potghan S. Multi-layer perceptron based lung tumor classification. 2018 second int conf Electron commun aerosp technol; 2018;499–502.
• [11] Lynch CM, Berkel VH, Van, Frieboes HB. Application of unsupervised analysis techniques to lung cancer patient data; 2017;1–18.
• [12] Wang H, Zhou Z, Li Y, Chen Z, Lu P, Wang W, et al. Comparison of machine learning methods for classifying mediastinal lymph node metastasis of non- small cell lung cancer from 18 F-FDG PET / CT images. EJNMMI Res 2017. http://dx.doi.org/10.1186/s13550-017-0260-9.
• [13] Wu W, Parmar C, Grossmann P, Quackenbush J, Lambin P, Bussink J, et al. Exploratory study to identify radiomics classifiers for lung Cancer histology. Front Oncol 2016;6:71. http://dx.doi.org/10.3389/fonc.2016.00071.
• [14] Samir P, Bandyopadhyay K. Edge detection from ct images of lung; 2012;34–7.
• [15] Aggarwal T, Furqan A, Kalra K. Feature extraction and LDA based classification of lung nodules in chest CT scan images. 2015 Int Conf Adv Comput Commun Informatics, ICACCI 2015; 2015;1189–93. http://dx.doi.org/10.1109/ICACCI.2015.7275773.
• [16] Teramoto A, Tsukamoto T, Kiriyama Y, Fujita H. Automated classification of lung Cancer types from cytological images using deep convolutional neural networks. Biomed Res Int 2017;2017. http://dx.doi.org/10.1155/2017/4067832.
• [17] Song QZ, Zhao L, Luo XK, Dou XC. Using deep learning for classification of lung nodules on computed tomography images. J Healthc Eng 2017;2017. http://dx.doi.org/10.1155/2017/8314740.
• [18] Liu K, Kang G. Multiview convolutional neural networks for lung nodule classification. Int J Imaging Syst Technol 2017;27:12–22. http://dx.doi.org/10.1002/ima.22206.
• [19] Pandey N. A novel approach of cancerous cells detection from lungs CT scan images. Int J Adv Res Comput Sci Software Eng 2012;2:316–20.
• [20] Margarita K, Martina S, Giorgia S, Serena M, Emanuele V, Lidija A, et al. Convolutional neural networks promising in lung Cancer t-parameter assessment on baseline FDG-PET/ CT. Contrast Media Mol Imaging 2018;2018:1–6.
• [21] Thomas A, Pattanayak P, Szabo E, Pinsky P. Characteristics and Outcomes of Small Cell Lung Cancer Detected by CT Screening. Chest 2018;154:1284–90. http://dx.doi.org/10.1016/j.chest.2018.07.029.
• [22] Wang X, Janowczyk A, Zhou Y, Thawani R, Fu P, Schalper K, et al. Prediction of recurrence in early stage non-small cell lung cancer using computer extracted nuclear features from digital H&E images. Sci Rep 2017;7:13543. http://dx.doi.org/10.1038/s41598-017-13773-7.
• [23] Han D, Heuvelmans MA, Oudkerk M. Volume versus diameter assessment of small pulmonary nodules in CT lung cancer screening. Transl Lung Cancer Res 2017;6:52–61. http://dx.doi.org/10.21037/tlcr.2017.01.05.
• [24] Toney LK, Vesselle HJ. Neural networks for nodal staging of non–small cell lung Cancer with FDG PET and CT: importance of combining uptake values and sizes of nodes and primary tumor. Radiology 2014;270:91–8. http://dx.doi.org/10.1148/radiol.13122427.
• [25] Kulkarni A, Panditrao A. Classification of lung cancer stages on CT scan images using image processing. Proc 2014 IEEE Int Conf Adv Commun Control Comput Technol ICACCCT 2014; 2015;1384–8. http://dx.doi.org/10.1109/icaccct.2014.7019327.
• [26] Shashi B, Rana S. A review of medical image enhancement techniques for image processing. Int J Curr Eng Technol 2011;5:1282–6. http://dx.doi.org/10.14741/Ijcet/22774106/5.2.2015.121.
• [27] Building powerful image classification models using very little data n.d. https://blog.keras.io/building-powerful-image- classification-models-using-very-little-data.html (accessed December 15, 2018).
• [28] Lecun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. Proc IEEE 1998;86:2278–324. http://dx.doi.org/10.1109/5.726791.
• [29] Cömert Z, Kocamaz AF. Fetal hypoxia detection based on deep convolutional neural network with transfer learning approach. In: Silhavy R, editor. Softw. Eng. Algorithms intell. Syst.. Cham: Springer International Publishing; 2019. p. 239–48.
• [30] Krizhevsky A, Sutskever I, Hinton GE. ImageNet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ, editors. Proc 25th int Conf Neural inf Process Syst, Vol. 1. USA: Curran Associates, Inc.; 2012. p. 1097–105.
• [31] Daldal N, Cömert Z, Polat K. Automatic determination of digital modulation types with different noises using Convolutional Neural Network based on time-frequency information. Appl Soft Comput 2019105834. http://dx.doi.org/10.1016/j.asoc.2019.105834.
• [32] Koushik J. Understanding convolutional neural networks; 2016. http://dx.doi.org/10.1016/j.jvcir.2016.11.003.
• [33] O'Shea K, Nash R. An introduction to convolutional neural networks; 2015. http://dx.doi.org/10.1007/978-3-642-28661-2-5.
• [34] Budak Ü, Cömert Z, Çibuk M, Sengür A. DCCMED-Net: densely connected and concatenated multi Encoder-Decoder CNNs for retinal vessel extraction from fundus images. Med Hypotheses 2020;134109426. http://dx.doi.org/10.1016/j.mehy.2019.109426.
• [35] Passalis N, Tefas A. Learning bag-of-Features pooling for deep convolutional neural networks. Proc IEEE Int Conf Comput Vis 2017. http://dx.doi.org/10.1109/iccv.2017.614. 2017-Octob:5766–74.
• [36] Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. ArXiv Prepr ArXiv14091556; 2014.
• [37] Altuntas Y, Cömert Z, Kocamaz AF. Identification of haploid and diploid maize seeds using convolutional neural networks and a transfer learning approach. Comput Electron Agric 2019;163104874. http://dx.doi.org/10.1016/j.compag.2019.104874.
• [38] Ruder S. An overview of gradient descent optimization algorithms. CoRR 2016. abs/1609.0.
• [39] Zeiler MD. ADADELTA: an adaptive learning rate method; 2012. http://dx.doi.org/10.1145/1830483.1830503.
• [40] Shindjalova R, Prodanova K, Svechtarov V. Modeling data for tilted implants in grafted with bio-oss maxillary sinuses using logistic regression. AIP Conf Proc 2014;1631:58–62. http://dx.doi.org/10.1063/1.4902458.
• [41] Hasan AM. Linear regression based feature selection for microarray data classification; 2015. http://dx.doi.org/10.1504/ijdmb.2015.066776.
• [42] Tharwat A, Gaber T, Ibrahim A, Hassanien AE. Linear discriminant analysis: a detailed tutorial; 2017. http://dx.doi.org/10.3233/aic-170729.
• [43] Rokach L, Maimon O. Decision trees; 2005. http://dx.doi.org/10.1007/0-387-25465-X.
• [44] Burges CJC. A tutorial on support vector machines for pattern recognition. Data Min Knowl Discov 1998;2:121–67. http://dx.doi.org/10.1023/A:1009715923555.
• [45] Cömert Z, Kocamaz AF. Comparison of machine learning techniques for fetal heart rate classification. Acta Phys Pol A 2017;132:451–4. http://dx.doi.org/10.12693/APhysPolA.131.451.
• [46] Suguna N, Thanushkodi K. An improved k-Nearest neighbor classification using genetic algorithm. IJCSI Int J Comput Sci 2010;7:7–10.
• [47] Zhang S, Li X, Zong M, Zhu X, Wang R. Efficient kNN classification with different numbers of nearest neighbors. IEEE Trans Neural Networks Learn Syst 2018;29:1774–85. http://dx.doi.org/10.1109/tnnls.2017.2673241.
• [48] Sertkaya ME, Ergen B, Togacar M. Diagnosis of eye retinal diseases based on convolutional neural networks using optical coherence images. 2019 23rd int. Conf. Electron.. 2019;1–5. http://dx.doi.org/10.1109/electronics.2019.8765579.
• [49] Cömert Z, Kocamaz AF, Subha V. Prognostic model based on image-based time-frequency features and genetic algorithm for fetal hypoxia assessment. Comput Biol Med 2018. http://dx.doi.org/10.1016/j.compbiomed.2018.06.003.
• [50] Guo G, Wang H, Bell D, Bi Y, Greer K. KNN model-based approach in classification KNN model-based approach in classification; 2004.
• [51] Zeng R, Wu J, Shao Z, Senhadji L, Shu H. Quaternion softmax classifier HAL Id : inserm-01101207; 2014. http://dx.doi.org/10.1049/el.2014.2526.
• [52] Gupta A, Barbu A. Parameterized principal component analysis. Pattern Recognit 2018;78:215–27. http://dx.doi.org/10.1016/j.patcog.2018.01.018.
• [53] Cibuk M, Budak U, Guo Y, Ince MC, Sengur A. Efficient deep features selections and classification for flower species recognition. Measurement 2019;137:7–13. http://dx.doi.org/10.1016/j.measurement.2019.01.041.
• [54] Togaçar M, Ergen B, Sertkaya ME. Zatürre Hastaliginin Derin Ögrenme Modeli ile tespiti detection of pneumonia with deep learning model. Firat Univ J Eng Sci 2019;31:223–30.
• [55] Powers David MW. Evaluation: from precision, recall and F-Measure to roc, informedness, markedness & correlation. J Mach Learn Technol 2011;2:37–63. doi:10.1.1.214.9232.
• [56] Cömert Z, Kocamaz AF. Open-access software for analysis of fetal heart rate signals. Biomed Signal Process Control 2018;45:98–108. http://dx.doi.org/10.1016/j.bspc.2018.05.016.
• [57] Togacar M, Ergen B, Sertkaya ME. Subclass separation of white blood cell images using convolutional neural network models. Elektron Ir Elektrotechnika 2019;25:63–8. http://dx.doi.org/10.5755/j01.eie.25.5.24358.
• [58] Nanni L, Ghidoni S, Brahnam S. Handcrafted vs. Non-handcrafted features for computer vision classification. Pattern Recognit 2017;71:158–72. http://dx.doi.org/10.1016/j.patcog.2017.05.025.
• [59] Nanni L, Brahnam S, Ghidoni S, Maguolo G. General purpose (GenP) bioimage ensemble of handcrafted and learned features with data augmentation; 2019;1–23.
• [60] Cömert Z, Kocamaz AF. A study based on gray level Co-occurrence matrix and neural network community for determination of hypoxic fetuses. Int Artif Intell Data Process Symp TR 2016;569–73. http://dx.doi.org/10.13140/RG.2.2.23901.00489.
• [61] Singh N, Asuntha A. Lung cancer detection using medical images through image Processing. J Chem Pharm Sci 2016;9:1558–61.

Uwagi

PL

Opracowanie rekordu ze środków MNiSW, umowa Nr 461252 w ramach programu "Społeczna odpowiedzialność nauki" - moduł: Popularyzacja nauki i promocja sportu (2020).