Classification of lung cancer histology using CT images based on convolutional neural network-CNN

Document Type : Research Paper


1 Ministry of Education, The General Directorate for Education of Diyala, Iraq

2 Computer of Science, College of Medicine, Diyala University, Diyala, Iraq

3 College of Agriculture, University of Diyala, Diyala, Iraq


In the field of medical imaging, interest in deep learning as a talented new discipline and a key component is growing rapidly. In lung cancer, the histology of tumours is a key predictor of therapy response and outcome. The most accurate way to classify histologies is through a pathologist's examination of tissue samples. Early tumour detection and therapy are essential for patients' recovery. For the purpose of identifying illness signs and risk stratification, recent developments in machine learning, medical image processing, and the use of radiologic data are highlighted. Regarding lung cancer and its various subtypes, it is error-prone and time-consuming to identify and differentiate. Convolutional Neural Networks can more accurately and quickly diagnose different types of lung cancer, which is essential for choosing the best treatment plan and patient survival rate. This research is concerned with both malignant (tumour) and benign tissue cell carcinomas. A training accuracy of 98.60 percent is obtained for the classification system of the suggested system, which is superior to that of both classic neural networks and the CNN model.


[1] A. Asuntha and A. Srinivasan, Deep learning for lung cancer detection and classification, Multimedia Tools Appl. 79 (2020), no. 11, 7731–7762.
[2] R.M. Azawi, D.A. Abdulah, J.M. Abbas and I.T. Ibrahim, Brain tumors classification by using gray level cooccurrence matrix, genetic algorithm and probabilistic neural network, Diyala J. Med. 14 (2018), no. 2.
[3] R.M. Azawi, D.A. Abdulah, J.M. Abbas and I.T. Ibrahim, A hybrid approach for classification of MRI brain tumors using genetic algorithm, K-nearest neighbor and probabilistic neural network, Int. J. Comput. Sci. Inf. Secur. 16 (2018), no. 5.
[4] D. Bazazeh and R. Shubair, Comparative study of machine learning algorithms for breast cancer detection and diagnosis, Int. Conf. Electronic Devices Syst. Appl., 2016, pp. 1–4.
[5] K. Bijaya and C. Himal, Lung cancer detection using convolutional neural network histopathological images, Int. J. Comput. Trends Techn. 68 (2020), no. 10.
[6] T.L. Chaunzwa, A. Hosny, Y. Xu, A. Shafer, N.Diao, M. Lanuti, D.C. Christiani, R.H. Mak and H.J. Aerts, Deep learning classification of lung cancer histology using CT images, Sci. Rep. 11 (2021), no. 1–12.
[7] M.R. Davidson, A.F. Gazdar and B.E. Clarke, The pivotal role of pathology in the management of lung cancer, J. Thoracic Disease 5 (2013), no. Suppl 5, p. S463.
[8] M. Heba, A. Sayed, M. Sayed and M. Abdel Badeeh, Classification using deep learning neural networks for brain tumors, Future Comput. Inf. J. 3 (2018), no. 1, 68–71.
[9] T. Huang, Distinguishing lung adenocarcinoma from lung squamous cell carcinoma by two hypo methylated and three hyper methylated genes: A meta-analysis, PLoS ONE 11 (2016).
[10] T. Ibrahim, M. Sabah, Z. Anmar and Al-M Emad, The evaluation of calcium score validity in the diagnosis of patients with coronary artery disease by using CT angiography, Diyala J. Med. 9 (2015), no. 1.
[11] P.M. Krishnammal and S.S. Raja, Convolutional neural network-based image classification and detection of abnormalities in MRI brain images, Int. Conf. Commun. Signal Process., 2019, pp. 548–553.
[12] X. Li, S. Luo, Q. Hu, J. Li, D. Wang and F. Chion, Automatic lung field segmentation in X-ray radiographs using statistical shape and appearance models, J. Med. Image Health Inf. 6 (2016), 338–348.
[13] J. Liu and L. Guo, A new brain MRI image segmentation strategy based on wavelet transform and K-means clustering, IEEE Int. Conf. Signal Process. Commun. Comput., 2015, pp. 1–4.
[14] Z. Majd, A. Pim and D. Bob, Automatic calcium scoring in low-dose chest CT using deep neural networks with dilated convolutions Nikolas Lessmann, Bram van Ginneken, Member IEEE Trans. Med. Imag. 37 (2018), no. 2, 615–625.
[15] R. Prajwal, A. Nishal and S. Raghuram, Convolutional neural networks for lung cancer screening in computed tomography (CT) scans, 2nd Int. Conf. Contemp. Comput. Inf., IEEE, 2016, pp. 489–493.
[16] A. Rasha and K. Muntadher, A real-time American sign language recognition system using convolutional neural network for real datasets, TEM J. 9 (2020), no. 3.
[17] S. Sasikala, M. Bharathi and B.R. Sowmiya, Lung cancer detection and classification using deep CNN, Int. J. Innov. Tech. Explor. Eng. 8 (2018), no. 25, 259–262.
[18] H. Shin, H.R. Roth, M. Gao, L. Lu, Z. Xu, I. Nogues, J. Yao, D. Mollura and R. M. Summers Deep convolutional neural networks for computer-aided detection: CNN architectures, dataset characteristics and transfer learning, IEEE Trans. Med. Imag.35 (2016), no. 5, 1285–1298.
[19] R. Tekade and K. Rajeswari, Lung cancer detection and classification using deep learning, Int. Conf. Comput. Commun. Control Autom., 2019, pp. 1–5.
[20] A. Teramoto, T. Tsukamoto, Y. Kiriyama and H. Fujita, Automated classification of lung cancer types from cytological images using deep convolutional neural networks, BioMed Res. Int. 2017 (2017).
[21] J. Xu, X. Luo, G. Wang, H. Gilmore and A. Madabhu, A deep convolutional neural network for segmenting and classifying epithelial and stromal regions in histopathological images, Neurocomput. 191 (2016), 214–223.
[22] R. Yamashita, M. Nishio, R.K.G. Do and K. Togashi, Convolutional neural network: An overview and application in radiology, Insights Imag. 9 (2018), no. 4, 611–629.
Volume 13, Issue 2
July 2022
Pages 3281-3289
  • Receive Date: 15 June 2022
  • Revise Date: 13 July 2022
  • Accept Date: 12 August 2022