Lungs Cancer Nodules Detection from CT Scan Images with Convolutional Neural Networks

  • Muhammad Zubair Rehman
  • Nazri Mohd NawiEmail author
  • Aisha Tanveer
  • Hassan Zafar
  • Hamza Munir
  • Sher Hassan
Conference paper
Part of the Advances in Intelligent Systems and Computing book series (AISC, volume 978)


Lungs cancer is a life-taking disease and is causing a problem around the world for a long time. The only plausible solution for this type of disease is the early detection of the disease because at preliminary stages it can be treated or cured. With the recent medical advancements, Computerized Tomography (CT) scan is the best technique out there to get the images of internal body organs. Sometimes, even experienced doctors are not able to identify cancer just by looking at the CT scan. During the past few years, a lot of research work is devoted to achieve the task for lung cancer detection but they failed to achieve accuracy. The main objective of this piece of this research was to find an appropriate method for classification of nodules and non-nodules. For classification, the dataset was taken from Japanese Society of Radiological Technology (JSRT) with 247 three-dimensional images. The images were preprocessed into gray-scale images. The lung cancer detection model was built using Convolutional Neural Networks (CNN). The model was able to achieve an accuracy of 88% with lowest loss rate of 0.21% and was found better than other highly complex methods for classification.


Lungs cancer Convolutional neural networks Features extraction Computed tomography Preprocessing Deep learning Computer vision 



The authors would like to thank Universiti Tun Hussein Onn Malaysia (UTHM) and Ministry of Higher Education (MOHE) Malaysia for financially supporting this Research under IGSP grants note U420 and under Trans-displinary Research Grant Scheme (TRGS) vote no. T003.


  1. 1.
    Gindi A, Attiatalla TA, Sami MM (2014) A comparative study for comparing two feature extraction methods and two classifiers in classification of earlystage lung cancer diagnosis of chest x-ray images. J Am Sci 10(6):13–22Google Scholar
  2. 2.
    Choi Wook-Jin, Choi Tae-Sun (2013) Automated pulmonary nodule detection system in computed tomography images: a hierarchical block classification approach. Entropy 15(2):507–523MathSciNetCrossRefGoogle Scholar
  3. 3.
    Chon A, Balachandar N, Lu P (2017) Deep convolutional neural networks for lung cancer detection, Standford UniversityGoogle Scholar
  4. 4.
    Suzuki K et al (2006) Radiologic classification of small adenocarcinoma of the lung: radiologic-pathologic correlation and its prognostic impact. Ann Thorac Surg 81(2):413–419CrossRefGoogle Scholar
  5. 5.
    Kanarek NF et al (2014) Survival after community diagnosis of early-stage non-small cell lung cancer. Am J Med 127(5):443–449CrossRefGoogle Scholar
  6. 6.
    Dieguez C (2016) Passive smoking: the importance of 100% smoke-free environments. Accessed 09 Feb 2016
  7. 7.
    Hua KL et al (2015) Computer-aided classification of lung nodules on computed tomography images via deep learning technique. OncoTargets Ther 8Google Scholar
  8. 8.
    Kumar D, Wong A, Clausi DA (2015) Lung nodule classification using deep features in CT images. In: 2015 12th conference on computer and robot vision. IEEEGoogle Scholar
  9. 9.
    Kuruvilla J, Gunavathi K ((2014)) Lung cancer classification using neural networks for CT images. Comput Methods Program Biomed 113(1): 202–209CrossRefGoogle Scholar
  10. 10.
    Gupta B, Tiwari S (2014) Lung cancer detection using curvelet transform and neural network. Int J Comput Appl 86(1)CrossRefGoogle Scholar
  11. 11.
    Dandıl E et al (2014) Artificial neural network-based classification system for lung nodules on computed tomography scans. In: 2014 6th International conference of soft computing and pattern recognition (SoCPaR). IEEEGoogle Scholar
  12. 12.
    Parveen SS, Kavitha C (2014) Classification of lung cancer nodules using SVM Kernels. Int J Comput Appl 95(25)Google Scholar
  13. 13.
    Nascimento LB, de Paiva AC, Silva AC (2012) Lung nodules classification in CT images using Shannon and Simpson diversity indices and SVM. In: International workshop on machine learning and data mining in pattern recognition. Springer, BerlinCrossRefGoogle Scholar
  14. 14.
    Orozco HM et al (2015) Automated system for lung nodules classification based on wavelet feature descriptor and support vector machine. Biomed Eng Online 14(1): 9Google Scholar
  15. 15.
    Krewer H et al (2013) Effect of texture features in computer aided diagnosis of pulmonary nodules in low-dose computed tomography. In: 2013 IEEE International conference on systems, man, and cybernetics. IEEEGoogle Scholar
  16. 16.
    Aggarwal T, Furqan A, Kalra K (2015) Feature extraction and LDA based classification of lung nodules in chest CT scan images. In: 2015 International conference on advances in computing, communications and informatics (ICACCI). IEEEGoogle Scholar
  17. 17.
    Jin XY, Zhang YC, Jin QL (2016) Pulmonary nodule detection based on CT images using convolution neural network. In: 2016 9th International symposium on computational intelligence and design (ISCID), vol 1. IEEEGoogle Scholar
  18. 18.
    Golan R, Jacob C, Denzinger J (2016) Lung nodule detection in CT images using deep convolutional neural networks. In: 2016 International joint conference on neural networks (IJCNN). IEEEGoogle Scholar
  19. 19.
    Milletari F, Navab N, Ahmadi SA (2016) V-net: Fully convolutional neural networks for volumetric medical image segmentation. In: 2016 Fourth international conference on 3D vision (3DV). IEEEGoogle Scholar
  20. 20.
    Rendon-Gonzalez, E, Ponomaryov V (2016) Automatic lung nodule segmentation and classification in CT images based on SVM. In: 2016 9th International Kharkiv symposium on physics and engineering of microwaves, millimeter and submillimeter waves (MSMW). IEEEGoogle Scholar
  21. 21.
    Andrej C (2018) Convolutional neural networks for visual recognition. Accessed 09 July 2018
  22. 22.
    Shiraishi J et al (2000) Development of a digital image database for chest radiographs with and without a lung nodule: receiver operating characteristic analysis of radiologists’ detection of pulmonary nodules. Am J Roentgenol 174(1):71–74CrossRefGoogle Scholar
  23. 23.
    Srivastava N et al (2014) Dropout: a simple way to prevent neural networks from overfitting. J Mach Learn Res 15(1):1929–1958Google Scholar

Copyright information

© Springer Nature Switzerland AG 2020

Authors and Affiliations

  • Muhammad Zubair Rehman
    • 1
  • Nazri Mohd Nawi
    • 2
    Email author
  • Aisha Tanveer
    • 1
  • Hassan Zafar
    • 3
  • Hamza Munir
    • 3
  • Sher Hassan
    • 3
  1. 1.Faculty of ComputingUniversiti Malaysia PahangPekanMalaysia
  2. 2.Soft Computing and Data Mining Center (SMC), Faculty of Computer Science and Information TechnologyUniversiti Tun Hussein Onn MalaysiaBatu PahatMalaysia
  3. 3.Machine Learning Research Group (MLRG)The University of LahoreIslamabadPakistan

Personalised recommendations