Automated AJCC (7th edition) staging of non-small cell lung cancer (NSCLC) using deep convolutional neural network (CNN) and recurrent neural network (RNN)
- 156 Downloads
A large chunk of lung cancers are of the type non-small cell lung cancer (NSCLC). Both the treatment planning and patients’ prognosis depend greatly on factors like AJCC staging which is an abstraction over TNM staging. Many significant efforts have so far been made towards automated staging of NSCLC, but the groundbreaking application of a deep neural networks (DNNs) is yet to be observed in this domain of study. DNN is capable of achieving higher level of accuracy than the traditional artificial neural networks (ANNs) as it uses deeper layers of convolutional neural network (CNN). The objective of the present study is to propose a simple yet fast CNN model combined with recurrent neural network (RNN) for automated AJCC staging of NSCLC and to compare the outcome with a few standard machine learning algorithms along with a few similar studies.
The NSCLC radiogenomics collection from the cancer imaging archive (TCIA) dataset was considered for the study. The tumor images were refined and filtered by resizing, enhancing, de-noising, etc. The initial image processing phase was followed by texture based image segmentation. The segmented images were fed into a hybrid feature detection and extraction model which was comprised of two sequential phases: maximally stable extremal regions (MSER) and the speeded up robust features (SURF). After a prolonged experiment, the desired CNN-RNN model was derived and the extracted features were fed into the model.
The proposed CNN-RNN model almost outperformed the other machine learning algorithms under consideration. The accuracy remained steadily higher than the other contemporary studies.
The proposed CNN-RNN model performed commendably during the study. Further studies may be carried out to refine the model and develop an improved auxiliary decision support system for oncologists and radiologists.
KeywordsLung cancer Deep learning Neural network Staging AJCC Recurrent
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
For this type of study formal consent is not required.
- 2.Horn L, Eisenberg R, Gius DR, Kimmelshue KN, Massion PP, Putnam JB, Robinson CG, Carbone DP. Cancer of the lung: non-small cell lung cancer and small cell lung Cancer. In: Abeloff’s Clinical Oncology: fifth edition. Elsevier Inc; 2013. pp. 1143–1192. https://doi.org/10.1016/B978-1-4557-2865-7.00072-2.
- 4.Nivetha P, Manickavasagam R. Lung cancer detection at early stage using PET/CT imaging technique. Int J Innov Res Comput Commun Eng. 2014;2(3):358–3363.Google Scholar
- 5.Brierley JD, Gospodarowicz MK, Wittekind Ch, editors. TNM classification of malignant tumours. 8th ed. Chichester: Wiley-Blackwell; 2017. ISBN 978-1-4443-3241-4.Google Scholar
- 6.Zahoor H, Luketich JD, Weksler B, Winger DG, Christie NA, Levy RM, Gibson MK, Davison JM, Nason KS. The revised American Joint Committee on Cancer staging system improves prognostic stratification after minimally invasive esophagectomy for esophagogastric adenocarcinoma. Am J Surg. 2015;210(4):610–7. https://doi.org/10.1016/j.amjsurg.2015.05.010.CrossRefGoogle Scholar
- 7.AJCC Cancer Stating Manual 7th Edition, American Joint Committee on Cancer, ISBN 978-0-387-88440-0. Springer, New York, Dordrecht, Heidelberg, London.Google Scholar
- 10.Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition; 2015. pp. 1–9.Google Scholar
- 13.Rossetto AM, Zhou W. Deep learning for categorization of lung cancer CT images. In: 2017 IEEE/ACM international conference on connected health: applications, systems and engineering technologies (CHASE), Philadelphia, PA; 2017. pp. 272–273. https://doi.org/10.1109/chase.2017.98
- 18.Kuan K, Ravaut M, Manek G, Chen H, Lin J, Nazir B, Chen C, Howe TC, Zeng Z, Chandrasekhar V. Deep learning for lung cancer detection: tackling the kaggle data science bowl 2017 challenge; 2017. arXiv:1705.09435.
- 19.Serj MF, Lavi B, Hoff G, Valls DP. A deep convolutional neural network for lung cancer diagnostic; 2018. arXiv:1804.08170.Google Scholar
- 21.The MathWorks Inc. MATLAB and statistics toolbox release. Natick: The MathWorks Inc; 2015.Google Scholar
- 22.Waikato Environment for Knowledge Analysis version 3.7.2, The University of Waikato, Hamilton, New Zealand.Google Scholar
- 23.Vesselle H, Turcotte E, Wiens L, Haynor D. Application of a neural network to improve nodal staging accuracy with 18F-FDG PET in non-small cell lung cancer. J Nucl Med. 2003;44(12):1918–26.Google Scholar
- 25.Chung J, Gulcehre C, Cho K, Bengio Y. Empirical evaluation of gated recurrent neural networks on sequence modeling. 2014. arXiv:1412.3555.
- 29.Moitra Dipanjan. Segmentation strategy of pet brain tumor image. Indian J Comput Sci Eng. 2017;0976–5166(8):575–7.Google Scholar
- 30.Moitra D. Review of brain tumor detection using pattern recognition techniques. Int J Comput Sci Eng. 2017;5(2):2347–693.Google Scholar
- 33.Gevaert O, Xu J, Hoang CD, Leung AN, Xu Y, Quon A, Rubin DL, Napel S, Plevritis SK. Non–small cell lung cancer: identifying prognostic imaging biomarkers by leveraging public gene expression microarray data—methods and preliminary results. Radiology. 2012;264(2):387–96. https://doi.org/10.1148/radiol.12111607.CrossRefGoogle Scholar
- 36.Matas J, Chum O, Urba M, Pajdla T. Robust wide-baseline stereo from maximally stable extremal regions. Proceedings of British Machine Vision Conference; 2002, pp. 384–396.Google Scholar
- 38.Donoser M, Bischof H. Efficient maximally stable extremal region (MSER) tracking. In: Proceedings of the 2006 IEEE computer society conference on computer vision and pattern recognition; 2006, pp. 553–560. https://doi.org/10.1109/cvpr.2006.107].
- 42.Collobert R, Bengio S. Links between perceptrons, MLPs and SVMs. In: Proceedings of international conference on machine learning (ICML); 2004.Google Scholar
- 46.Chollet F. Deep learning with python. Manning Publications, New York. ISBN: 9781617294433.Google Scholar
- 47.Nurtiyasari D, Rosadi D, Abdurakhman. The application of wavelet recurrent neural network for lung cancer classification. 2017 3rd International Conference on Science and Technology - Computer (lCST). https://doi.org/10.1109/ICSTC.2017.8011865.
- 48.Mobiny A, Moulik S, Van Nguyen H. Lung cancer screening using adaptive memory-augmented recurrent networks. arXiv:1710.05719.
- 49.Orozco H, Villegas O, Dominguez H, Sanchez V. Lung nodule classification in CT thorax images using support vector machines. 2013 12th Mexican International Conference on Artificial Intelligence (MICAI), pp. 277–283. https://doi.org/10.1109/MICAI.2013.38.
- 51.Sivakumar S, Chandrasekar C. Lung nodule detection using fuzzy clustering and support vector machines. Int J Eng Tech. 2013;5(1):179–185.Google Scholar
- 52.Taher F, Werghi N, Al-Ahmad H. Bayesian classification and artificial neural network methods for lung cancer early diagnosis. 2012 19th IEEE International Conference on Electronics, Circuits, and Systems (ICECS 2012), Seville, 2012, pp. 773-776. https://doi.org/10.1109/ICECS.2012.6463545.