Advertisement

Artificial neural network based classification of lung nodules in CT images using intensity, shape and texture features

  • Furqan Shaukat
  • Gulistan Raja
  • Rehan Ashraf
  • Shehzad Khalid
  • Mudassar AhmadEmail author
  • Amjad Ali
Original Research
  • 26 Downloads

Abstract

The cancer of lung has been one of the major threats to human life for decades in developed and developing countries. The Computer Aided Detection CAD could be a powerful tool for initial lung nodule detection and preventing the deaths caused by the lung tumor. In this paper, an advanced technique for lung-nodule detection by using a hybrid feature set and artificial neural network is proposed. Initially, the lung volume is segmented from the input Computed Tomography image using optimal thresholding which is followed by image enhancement using with multi scale dot augmentation filtering. Next, lung nodule candidates have been detected from enhanced image and certain features are extracted. The set feature consists of the texture features, shape 2D and 3D and intensity. Finally, lung nodule’s classification is attained using two-layer feed forward neural network. The Lung Image Database Consortium dataset has been used to evaluate the novel system which achieved a sensitivity of 95.5% with only 5.72 FP per scan.

Keywords

Lung nodule detection Feature extraction ANN CAD 

Notes

References

  1. Akram S, Javed MY, Akram MU, Qamar U, Hassan A (2016) Pulmonary nodules detection and classification using hybrid features from computerized tomographic images. J Med Imaging Health Inform 6(1):252–259.  https://doi.org/10.1166/jmihi.2016.1600 CrossRefGoogle Scholar
  2. Ali AM, Farag AA (2008) Automatic lung segmentation of volumetric low-dose CT scans using graph cuts. Adv Vis Comput.  https://doi.org/10.1007/978-3-540-89639-5_25 Google Scholar
  3. Armato SG, Giger ML, Moran CJ, Blackburn JT, Doi K, MacMahon H (1999) Computerized detection of pulmonary nodules on CT scans. RadioGraphics 19(5):1303–1311.  https://doi.org/10.1148/radiographics.19.5.g99se181303 CrossRefGoogle Scholar
  4. Assefa M, Faye I, Malik AS, Shoaib M (2013) Lung nodule detection using multi-resolution analysis. 2013 ICME International Conference on Complex Medical Engineering.  https://doi.org/10.1109/iccme.2013.6548290
  5. Bergtholdt M, Wiemker R, Klinder T (2016) Pulmonary nodule detection using a cascaded SVM classifier. Med Imaging 2016 Comput Aided Diagn.  https://doi.org/10.1117/12.2216747 Google Scholar
  6. Choi W, Choi T (2012) Genetic programming-based feature transform and classification for the automatic detection of pulmonary nodules on computed tomography images. Inf Sci 212:57–78.  https://doi.org/10.1016/j.ins.2012.05.008 CrossRefGoogle Scholar
  7. Choi W, Choi T (2013) Automated pulmonary nodule detection system in computed tomography images: a hierarchical block classification approach. Entropy 15(2):507–523.  https://doi.org/10.3390/e15020507 MathSciNetCrossRefGoogle Scholar
  8. Choi W, Choi T (2014) Automated pulmonary nodule detection based on three-dimensional shape-based feature descriptor. Comput Methods Programs Biomed 113(1):37–54.  https://doi.org/10.1016/j.cmpb.2013.08.015 CrossRefGoogle Scholar
  9. Da Silva Sousa JR, Silva AC, De Paiva AC, Nunes RA (2010) Methodology for automatic detection of lung nodules in computerized tomography images. Comput Methods Programs Biomed 98(1):1–14.  https://doi.org/10.1016/j.cmpb.2009.07.006 CrossRefGoogle Scholar
  10. De Nunzio G, Tommasi E, Agrusti A, Cataldo R, De Mitri I, Favetta M, Oliva P (2009) Automatic lung segmentation in CT images with accurate handling of the Hilar Region. J Digit Imaging 24(1):11–27.  https://doi.org/10.1007/s10278-009-9229-1 CrossRefGoogle Scholar
  11. Dehmeshki J, Ye X, Lin X, Valdivieso M, Amin H (2007) Automated detection of lung nodules in CT images using shape-based genetic algorithm. Comput Med Imaging Graph 31(6):408–417.  https://doi.org/10.1016/j.compmedimag.2007.03.002 CrossRefGoogle Scholar
  12. Diaz JM, Pinon RC, Solano G (2014) Lung cancer classification using genetic algorithm to optimize prediction models. IISA 2014, The 5th International Conference on Information, Intelligence, Systems and Applications.  https://doi.org/10.1109/iisa.2014.6878770
  13. Ding J, Li A, Hu Z, Wang L (2017) Accurate pulmonary nodule detection in computed tomography images using deep convolutional neural networks. Lect Notes Comput Sci.  https://doi.org/10.1007/978-3-319-66179-7_64 CrossRefGoogle Scholar
  14. Dou Q, Chen H, Yu L, Qin J, Heng P (2017) Multilevel contextual 3-D CNNs for false positive reduction in pulmonary nodule detection. IEEE Trans Biomed Eng 64(7):1558–1567.  https://doi.org/10.1109/tbme.2016.2613502 CrossRefGoogle Scholar
  15. Espejo P, Ventura S, Herrera F (2010) A Survey on the application of genetic programming to classification. IEEE Trans Syst Man Cybern Part C (Appl Rev) 40(2):121–144.  https://doi.org/10.1109/tsmcc.2009.2033566 CrossRefGoogle Scholar
  16. Guo W, Wei Y, Hanxun Z, DingYe X (2009). An adaptive lung nodule detection algorithm. 2009 Chinese Control and Decision Conference.  https://doi.org/10.1109/ccdc.2009.5192686
  17. Haralick RM, Shanmugam K, Dinstein I (1973) Textural features for image classification. IEEE Trans Syst Man Cybern 3(6):610–621.  https://doi.org/10.1109/tsmc.1973.4309314 CrossRefGoogle Scholar
  18. He X, Yu S, Xu P, Wang J, Zhan M (2012) Combining red and blue-detuned optical potentials to form a Lamb-Dicke trap for a single neutral atom. Opt Express 20(4):3711.  https://doi.org/10.1364/oe.20.003711 CrossRefGoogle Scholar
  19. Henschke CI (2001) Early lung cancer action project: a summary of the findings on baseline screening. Oncologist 6(2):147–152.  https://doi.org/10.1634/theoncologist.6-2-147 CrossRefGoogle Scholar
  20. Hu S, Hoffman E, Reinhardt J (2001) Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images. IEEE Trans Med Imaging 20(6):490–498.  https://doi.org/10.1109/42.929615 CrossRefGoogle Scholar
  21. Jiantao P, Paik DS, Xin M, Roos J, Rubin GD (2011) Shape “break-and-repair” strategy and its application to automated medical image segmentation. IEEE Trans Visual Comput Graphics 17(1):115–124.  https://doi.org/10.1109/tvcg.2010.56 CrossRefGoogle Scholar
  22. Kostis W, Reeves A, Yankelevitz D, Henschke C (2003) Three-dimensional segmentation and growth-rate estimation of small pulmonary nodules in helical ct images. IEEE Trans Med Imaging 22(10):1259–1274.  https://doi.org/10.1109/tmi.2003.817785 CrossRefGoogle Scholar
  23. Kubota T, Jerebko AK, Dewan M, Salganicoff M, Krishnan A (2011) Segmentation of pulmonary nodules of various densities with morphological approaches and convexity models. Med Image Anal 15(1):133–154.  https://doi.org/10.1016/j.media.2010.08.005 CrossRefGoogle Scholar
  24. Lee S, Kouzani A, Hu E (2010) Random forest based lung nodule classification aided by clustering. Comput Med Imaging Graph 34(7):535–542.  https://doi.org/10.1016/j.compmedimag.2010.03.006 CrossRefGoogle Scholar
  25. Li Q, Sone S, Doi K (2003) Selective enhancement filters for nodules, vessels, and airway walls in two- and three-dimensional CT scans. Med Phys 30(8):2040–2051.  https://doi.org/10.1118/1.1581411 CrossRefGoogle Scholar
  26. Liu Y, Yang J, Zhao D, Liu J (2009) Computer aided detection of lung nodules based on voxel analysis utilizing support vector machines. 2009 International Conference on Future BioMedical Information Engineering (FBIE).  https://doi.org/10.1109/fbie.2009.5405784
  27. Mahesh S, Rakesh S, Patil VC (2018) Computer aided detection system for lung cancer using computer tomography scans. AIP Conf Proc.  https://doi.org/10.1063/1.5032063 Google Scholar
  28. McNitt-Gray MF, Armato SG, Meyer CR, Reeves AP, McLennan G, Pais RC, Clarke LP (2007) The lung image database consortium (LIDC) data collection process for nodule detection and annotation. Acad Radiol 14(12):1464–1474.  https://doi.org/10.1016/j.acra.2007.07.021 CrossRefGoogle Scholar
  29. Messay T, Hardie RC, Rogers SK (2010) A new computationally efficient CAD system for pulmonary nodule detection in CT imagery. Med Image Anal 14(3):390–406.  https://doi.org/10.1016/j.media.2010.02.004 CrossRefGoogle Scholar
  30. Murphy K, Van Ginneken B, Schilham A, De Hoop B, Gietema H, Prokop M (2009) A large-scale evaluation of automatic pulmonary nodule detection in chest CT using local image features and k-nearest-neighbour classification. Med Image Anal 13(5):757–770.  https://doi.org/10.1016/j.media.2009.07.001 CrossRefGoogle Scholar
  31. Niemeijer M, Loog M, Abràmoff MD, Viergever MA, Prokop M, Van Ginneken B (2011) On combining computer-aided detection systems. IEEE Trans Med Imaging 30(2):215–223.  https://doi.org/10.1109/tmi.2010.2072789 CrossRefGoogle Scholar
  32. Orozco HM, Villegas OO, Dominguez HD, Sanchez VG (2013) Lung nodule classification in ct thorax images using support vector machines. 2013 12th Mexican International Conference on Artificial Intelligence.  https://doi.org/10.1109/micai.2013.38
  33. Ozekes S, Osman O (2008) Computerized lung nodule detection using 3D feature extraction and learning based algorithms. J Med Syst 34(2):185–194.  https://doi.org/10.1007/s10916-008-9230-0 CrossRefGoogle Scholar
  34. Retico A, Fantacci M, Gori I, Kasae P, Golosio B, Piccioli A, Tangaro S (2009) Pleural nodule identification in low-dose and thin-slice lung computed tomography. Comput Biol Med 39(12):1137–1144.  https://doi.org/10.1016/j.compbiomed.2009.10.005 CrossRefGoogle Scholar
  35. Sahiner B, Chan H, Hadjiiski LM, Cascade PN, Kazerooni EA, Chughtai AR, Attili A (2009) Effect of CAD on radiologists’ detection of lung nodules on thoracic CT scans: analysis of an observer performance study by nodule size. Acad Radiol 16(12):1518–1530.  https://doi.org/10.1016/j.acra.2009.08.006 CrossRefGoogle Scholar
  36. Setio AA, Ciompi F, Litjens G, Gerke P, Jacobs C, Van Riel SJ, Van Ginneken B (2016) Pulmonary nodule detection in CT images: false positive reduction using multi-view convolutional networks. IEEE Trans Med Imaging 35(5):1160–1169.  https://doi.org/10.1109/tmi.2016.2536809 CrossRefGoogle Scholar
  37. Setio AA, Traverso A, De Bel T, Berens MS, Bogaard CV, Cerello P, Jacobs C (2017) Validation, comparison, and combination of algorithms for automatic detection of pulmonary nodules in computed tomography images: the LUNA16 challenge. Med Image Anal 42:1–13.  https://doi.org/10.1016/j.media.2017.06.015 CrossRefGoogle Scholar
  38. Shapiro L, Kak A (1986) Special issue on current issues and trends in computer vision. Comput Vis Graphics Image Process 36(2–3):137.  https://doi.org/10.1016/0734-189x(86)90072-1 CrossRefGoogle Scholar
  39. Shaukat F, Raja G, Gooya A, Frangi AF (2017) Fully automatic detection of lung nodules in CT images using a hybrid feature set. Med Phys 44(7):3615–3629.  https://doi.org/10.1002/mp.12273 CrossRefGoogle Scholar
  40. Siegel RL, Miller KD, Jemal A (2016) Cancer statistics, 2016. CA: a cancer. J Clin 66(1):7–30.  https://doi.org/10.3322/caac.21332 Google Scholar
  41. Suárez-Cuenca JJ, Tahoces PG, Souto M, Lado MJ, Remy-Jardin M, Remy J, José Vidal J (2009) Application of the iris filter for automatic detection of pulmonary nodules on computed tomography images. Comput Biol Med 39(10):921–933.  https://doi.org/10.1016/j.compbiomed.2009.07.005 CrossRefGoogle Scholar
  42. Suzuki K, Armato SG, Li F, Sone S, Doi K (2003) Massive training artificial neural network (MTANN) for reduction of false positives in computerized detection of lung nodules in low-dose computed tomography. Med Phys 30(7):1602–1617.  https://doi.org/10.1118/1.1580485 CrossRefGoogle Scholar
  43. Tartar A, Kilic N, Akan A (2013) Classification of pulmonary nodules by using hybrid features. Comput Math Methods Med 2013:1–11.  https://doi.org/10.1155/2013/148363 MathSciNetCrossRefzbMATHGoogle Scholar
  44. Teramoto A, Fujita H, Takahashi K, Yamamuro O, Tamaki T, Nishio M, Kobayashi T (2013) Hybrid method for the detection of pulmonary nodules using positron emission tomography/computed tomography: a preliminary study. Int J Comput Assist Radiol Surg 9(1):59–69.  https://doi.org/10.1007/s11548-013-0910-y CrossRefGoogle Scholar
  45. Valente IR, Cortez PC, Neto EC, Soares JM, De Albuquerque VH, Tavares JM (2016) Automatic 3D pulmonary nodule detection in CT images: a survey. Comput Methods Progr Biomed 124:91–107.  https://doi.org/10.1016/j.cmpb.2015.10.006 CrossRefGoogle Scholar
  46. Xian G (2010) An identification method of malignant and benign liver tumors from ultrasonography based on GLCM texture features and fuzzy SVM. Expert Syst Appl 37(10):6737–6741.  https://doi.org/10.1016/j.eswa.2010.02.067 CrossRefGoogle Scholar
  47. Yu Y, Zhao H (2006) Enhancement filter for computer-aided detection of pulmonary nodules on thoracic CT images. Sixth International Conference on Intelligent Systems Design and Applications.  https://doi.org/10.1109/isda.2006.253783

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Faculty of Electronics and Electrical EngineeringUniversity of Engineering and TechnologyTaxilaPakistan
  2. 2.Department of Computer ScienceNational Textile University FaisalabadFaisalabadPakistan
  3. 3.Department of Computer EngineeringBahria UniversityIslamabadPakistan
  4. 4.Department of Computer and Software TechnologyUniversity of SwatSwatPakistan

Personalised recommendations