Advertisement

High Throughput Lung and Lobar Segmentation by 2D and 3D CNN on Chest CT with Diffuse Lung Disease

  • Xiaoyong Wang
  • Pangyu Teng
  • Pechin Lo
  • Ashley Banola
  • Grace Kim
  • Fereidoun Abtin
  • Jonathan Goldin
  • Matthew BrownEmail author
Conference paper
Part of the Lecture Notes in Computer Science book series (LNCS, volume 11040)

Abstract

Deep learning methods have been widely and successfully applied to the medical imaging field. Specifically, fully convolutional neural networks have become the state-of-the-art supervised segmentation method in a variety of biomedical segmentation problems. Two fully convolutional networks were proposed to sequentially achieve accurate lobar segmentation. Firstly, a 2D ResNet-101 based network is proposed for lung segmentation and 575 chest CT scans from multicenter clinical trials were used with radiologist approved lung segmentation. Secondly, a 3D DenseNet based network is applied to segment the 5 lobes and a total of 1280 different CT scans were used with radiologist approved lobar segmentation as ground truth. The dataset includes various pathological lung diseases and stratified sampling was used to form training and test sets following a ratio of 4:1 to ensure a balanced number and type of abnormality present. A 3D CNN segmentation model was also built for lung segmentation to investigate the feasibility using current hardware. Using 5-fold cross validation a mean Dice coefficient of 0.988 ± 0.012 and Average Surface Distance of 0.562 ± 0.49 mm was achieved by the proposed 2D CNN on lung segmentation. 3D DenseNet on lobar segmentation achieved Dice score of 0.959 ± 0.087 and Average surface distance of 0.873 ± 0.61 mm.

Keywords

CT Lung segmentation Lobar segmentation CNN 

References

  1. 1.
    Mansoor, A., et al.: A generic approach to pathological lung segmentation. IEEE Trans. Med. Imaging 33(12), 2293–2310 (2014)CrossRefGoogle Scholar
  2. 2.
    Birkbeck, N., et al.: Lung Segmentation from CT with Severe Pathologies Using Anatomical Constraints. In: Golland, P., Hata, N., Barillot, C., Hornegger, J., Howe, R. (eds.) MICCAI 2014. LNCS, vol. 8673, pp. 804–811. Springer, Cham (2014).  https://doi.org/10.1007/978-3-319-10404-1_100CrossRefGoogle Scholar
  3. 3.
    Prasad, M.N., et al.: Automatic segmentation of lung parenchyma in the presence of diseases based on curvature of ribs. Acad. Radiol. 15(9), 1173–1180 (2008)CrossRefGoogle Scholar
  4. 4.
    Pulagam, A.R., Kande, G.B., Ede, V.K.R., Inampudi, R.B.: Automated lung segmentation from HRCT scans with diffuse parenchymal lung diseases. J. Digit. Imaging 29(4), 507–519 (2016)CrossRefGoogle Scholar
  5. 5.
    Antony, J., McGuinness, K., Connor, N.E.O., Moran, K.: Quantifying radiographic knee osteoarthritis severity using deep convolutional neural networks, arXiv cs.CV, vol. 9, p. 02469 (2016)Google Scholar
  6. 6.
    Kim, E., Corte-Real, M., Baloch, Z.: A deep semantic mobile application for thyroid cytopathology. In: Proceedings of SPIE, vol. 9789, pp. 97890A–97890A-9 (2016)Google Scholar
  7. 7.
    Suk, H.-I., Shen, D.: Deep learning-based feature representation for AD/MCI classification. In: Mori, K., Sakuma, I., Sato, Y., Barillot, C., Navab, N. (eds.) MICCAI 2013. LNCS, vol. 8150, pp. 583–590. Springer, Heidelberg (2013).  https://doi.org/10.1007/978-3-642-40763-5_72CrossRefGoogle Scholar
  8. 8.
    Long, J., Shelhamer, E., Darrell, T.: Fully convolutional networks for semantic segmentation. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 12 June 2015, vol. 07, pp. 3431–3440 (2015)Google Scholar
  9. 9.
    Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234–241. Springer, Cham (2015).  https://doi.org/10.1007/978-3-319-24574-4_28CrossRefGoogle Scholar
  10. 10.
    Kalinovsky, A., Kalinovsky, A., Kovalev, V.: Lung image segmentation using deep learning methods and convolutional neural networks lung image segmentation using deep learning methods and convolutional neural networks, October 2016Google Scholar
  11. 11.
    Çiçek, Ö., Abdulkadir, A., Lienkamp, S.S., Ronneberger, O.: 3D U-Net: learning dense volumetric segmentation from sparse annotation, arXiv Prepr. arXiv:1606.06650 (2016)
  12. 12.
    Milletari, F., Navab, N., Ahmadi, S.-A.: V-Net: fully convolutional neural networks for volumetric medical image segmentation, arXiv Prepr. arXiv:1606.04797, pp. 1–11 (2016)
  13. 13.
    Harrison, A.P., Xu, Z., George, K., Lu, L., Summers, R.M., Mollura, D.J.: Progressive and multi-path holistically nested neural networks for pathological lung segmentation from CT images, CoRR, vol. abs/1706.0 (2017)Google Scholar
  14. 14.
    Negahdar, M., Beymer, D.: Automated volumetric lung segmentation of thoracic CT images using fully convolutional neural network, February 2018Google Scholar
  15. 15.
    George, K., Harrison, A.P., Jin, D., Xu, Z., Mollura, D.J.: Pathological pulmonary lobe segmentation from CT images using progressive holistically nested neural networks and random walker, ArXiv e-prints, August 2017Google Scholar
  16. 16.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition, CoRR, vol. abs/1512.0 (2015)Google Scholar
  17. 17.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: ImageNet Challenge, pp. 1–10 (2014)Google Scholar
  18. 18.
    Szegedy, C., Vanhoucke, V., Ioffe, S., Shlens, J., Wojna, Z.: Rethinking the Inception Architecture for Computer Vision (2015)Google Scholar
  19. 19.
    Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings - 30th IEEE Conference Computer Vision Pattern Recognition, CVPR 2017, January, vol. 2017, pp. 2261–2269 (2017)Google Scholar
  20. 20.
    Brown, M.S., et al.: Method for segmenting chest CT image data using an anatomical model: preliminary results. IEEE Trans. Med. Imaging 16(6), 828–839 (1997)CrossRefGoogle Scholar
  21. 21.
    Brown, M.S., et al.: Reproducibility of lung and lobar volume measurements using computed tomography. Acad. Radiol. 17(3), 316–322 (2010)CrossRefGoogle Scholar
  22. 22.
    Kohavi, R.: A study of cross-validation and bootstrap for accuracy estimation and model selection, pp. 1137–1143 (1995)Google Scholar
  23. 23.
    Szegedy, C., et al.: Going deeper with convolutions. In: Computer Vision and Pattern Recognition (CVPR) (2015)Google Scholar
  24. 24.
    Chollet, F.: “Keras.” GitHub (2015)Google Scholar

Copyright information

© Springer Nature Switzerland AG 2018

Authors and Affiliations

  • Xiaoyong Wang
    • 1
    • 2
  • Pangyu Teng
    • 1
    • 2
  • Pechin Lo
    • 1
    • 2
  • Ashley Banola
    • 1
    • 2
  • Grace Kim
    • 1
    • 2
  • Fereidoun Abtin
    • 1
    • 2
  • Jonathan Goldin
    • 1
    • 2
  • Matthew Brown
    • 1
    • 2
    Email author
  1. 1.Center for Computer Vision and Imaging BiomarkersUniversity of California, Los AngelesLos AngelesUSA
  2. 2.Department of Radiological SciencesUniversity of California, Los AngelesLos AngelesUSA

Personalised recommendations