Nothing Special   »   [go: up one dir, main page]
Skip to main content
Springer Nature Link
Log in

Extracting Lungs from CT Images via Deep Convolutional Neural Network Based Segmentation and Two-Pass Contour Refinement

  • Original Paper
  • Published:
Journal of Digital Imaging Aims and scope Submit manuscript

Abstract

Lung segmentation is a key step of thoracic computed tomography (CT) image processing, and it plays an important role in computer-aided pulmonary disease diagnostics. However, the presence of image noises, pathologies, vessels, individual anatomical varieties, and so on makes lung segmentation a complex task. In this paper, we present a fully automatic algorithm for segmenting lungs from thoracic CT images accurately. An input image is first spilt into a set of non-overlapping fixed-sized image patches, and a deep convolutional neural network model is constructed to extract initial lung regions by classifying image patches. Superpixel segmentation is then performed on the preprocessed thoracic CT image, and the lung contours are locally refined according to corresponding superpixel contours with our adjacent point statistics method. Segmented lung contours are further globally refined by an edge direction tracing technique for the inclusion of juxta-pleural lesions. Our algorithm is tested on a group of thoracic CT scans with interstitial lung diseases. Experiments show that our algorithm creates an average Dice similarity coefficient of 97.95% and Jaccard’s similarity index of 94.48%, with 2.8% average over-segmentation rate and 3.3% under-segmentation rate compared with manually segmented results. Meanwhile, it shows better performance compared with several feature-based machine learning methods and current methods on lung segmentation.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Subscribe and save

Springer+ Basic
$34.99 /Month
  • Get 10 units per month
  • Download Article/Chapter or eBook
  • 1 Unit = 1 Article or 1 Chapter
  • Cancel anytime
Subscribe now

Buy Now

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12
Fig. 13
Fig. 14
Fig. 15
Fig. 16
Fig. 17

Similar content being viewed by others

References

  1. Zhou S, Cheng Y, Tamura S: Automated lung segmentation and smoothing techniques for inclusion of juxtapleural nodules and pulmonary vessels on chest CT images. Biomed Signal Process Control 13: 62–70, 2014

    Article  Google Scholar 

  2. Armato III S, Sensakovic W: Automated lung segmentation for thoracic CT: impact on computer-aided diagnosis1. Acad Radiol 11 (9): 1011–1021, 2004

    Article  Google Scholar 

  3. Sluimer I, Prokop M, Van Ginneken B: Toward automated segmentation of the pathological lung in CT. IEEE Trans Medical Imag 24 (8): 1025–1038, 2005

    Article  Google Scholar 

  4. Hu Z, Tang J, Wang Z, et al: Deep learning for image-based cancer detection and diagnosis- a survey. Pattern Recognit 83: 134–149, 2018

    Article  Google Scholar 

  5. Litjens G, Kooi T, Bejnordi B, et al: A survey on deep learning in medical image analysis. Med Image Anal 42: 60–88, 2017

    Article  Google Scholar 

  6. Sahu S, Agrawal P, Londhe N, et al: A new hybrid approach using fuzzy clustering and morphological operations for lung segmentation in thoracic ct images. Biomed Pharmacol J 10 (4): 1949–1961, 2017

    Article  Google Scholar 

  7. Gomathi M, Thangaraj P: A new approach to lung image segmentation using fuzzy possibilistic c-means algorithm. Int J Comput Sci Inf Secur 7 (3): 14–24, 2010

    Google Scholar 

  8. Santos A, de Carvalho Filho A, Silva A, et al: Automatic detection of small lung nodules in 3D CT data using Gaussian mixture models, Tsallis entropy and SVM. Eng Appl Artif Intell 36: 27–39, 2014

    Article  Google Scholar 

  9. Arimura H, Katsuragawa S, Suzuki K, et al: Computerized scheme for automated detection of lung nodules in low-dose computed tomography images for lung cancer screening. Acad Radiol 11 (6): 617–629, 2004

    Article  Google Scholar 

  10. Mansoor A, Bagci U, Xu Z, et al: A generic approach to pathological lung segmentation. IEEE Trans Med Imaging 33 (12): 2293–2310, 2014

    Article  Google Scholar 

  11. Alin Mercybha P, Brinda T: Intelligent pathological lung segmentation using random forest machine learning. Int J Innov Res Comput Commun Eng 3 (3): 21–26, 2015

    Google Scholar 

  12. Dincer E, Duru N: Automatic lung segmentation by using histogram based k-means algorithm.. In: Proceedings of International Conference on Electric Electronics, Computer Science, Biomedical Engineerings Meeting, 2016, pp 1–4

  13. Liu C, Zhao R, Pang M: A fully automatic segmentation algorithm for CT lung images based on random forest. Med Phys 47 (2): 518–529, 2020

    Article  Google Scholar 

  14. Shen S, Bui A, Cong J, et al: An automated lung segmentation approach using bidirectional chain codes to improve nodule detection accuracy. Comput Biol Med 57: 139–149, 2015

    Article  Google Scholar 

  15. Liu C, Zhao R, Pang M: Lung segmentation based on random forest and multi-scale edge detection. IET Image Process 13 (10): 1745–1754, 2019

    Article  Google Scholar 

  16. Jalal D, Ganesan R, Merline A: Fuzzy-c-means clustering based segmentation and CNN-classification for accurate segmentation of lung nodules. Asian Pac J Cancer Prev Apjcp 18 (7): 1869–1874, 2017

    Google Scholar 

  17. Park B, Park H, Lee S, et al: Lung segmentation on HRCT and volumetric CT for diffuse interstitial lung disease using deep convolutional neural networks. J Digital Imaging 32 (6): 1019–1026, 2019

    Article  Google Scholar 

  18. Islam J, Zhang Y (2018) Towards robust lung segmentation in chest radiographs with deep learning. arXiv:1811.12638, 1–5

  19. Xu M, Qi S, Yue Y, et al: Segmentation of lung parenchyma in CT images using CNN trained with the clustering algorithm generated dataset. Biomed Eng Online 18 (1): 1–21, 2019

    Article  Google Scholar 

  20. Tajbakhsh N, Suzuki K: Comparing two classes of end-to-end machine-learning models in lung nodule detection and classification: MTANNS vs. CNNS. Pattern Recognit 63: 476–486, 2017

    Article  Google Scholar 

  21. LeCun Y, Bottou L, Bengio Y, et al: Gradient-based learning applied to document recognition. Proc IEEE 86 (11): 2278–2324, 1998

    Article  Google Scholar 

  22. Lai Z, Deng H: Medical image classification based on deep features extracted by deep model and statistic feature fusion with multilayer perceptron. Comput Intel Neurosc 28: 1–13, 2018

    Article  Google Scholar 

  23. Palm R (2014) Deeplearntoolbox, a matlab toolbox for deep learning. [Online]. Dispon⋅⋅avel em: https://github.com/rasmusbergpalm/DeepLearnToolbox

  24. Achanta R, Shaji A, Smith K, et al: SLIC superpixels compared to state-of-the-art superpixel methods. IEEE Trans Pattern Anal Mach Intell 34 (11): 2274–2282, 2012

    Article  Google Scholar 

  25. Vincent L: Morphological grayscale reconstruction in image analysis: Applications and e cient algorithms. IEEE Trans Image Process 2 (2): 176–201, 1993

    Article  CAS  Google Scholar 

  26. Bai J, Feng X: Fractional-order anisotropic diffusion for image denoising. IEEE Trans Image Process 16 (10): 2492–2502, 2007

    Article  Google Scholar 

  27. Depeursinge A, Vargas A, Platon A, et al: Building a reference multimedia database for interstitial lung diseases. Comput Med Imag Grap 36 (3): 227–238, 2012

    Article  Google Scholar 

  28. de Siqueira F, Schwartz W, Pedrini H: Multi-scale gray level co-occurrence matrices for texture description. Neurocomputing 120: 336–345, 2013

    Article  Google Scholar 

Download references

Funding

The work in this paper was supported by grants from the National Natural Science Foundation of China (Grant Nos. 41631175, 61702068), the Key Project of Ministry of Education for the 13th 5-years Plan of National Education Science of China (Grant No. DCA170302), the Social Science Foundation of Jiangsu Province of China (Grant No. 15TQB005), the Priority Academic Program Development of Jiangsu Higher Education Institutions (Grant No. 1643320H111) and the Postgraduate Research & Practice Innovation Program of Jiangsu Province (Grand No. KYCX19_0733).

Author information

Authors and Affiliations

  1. Institute of EduInfo Science and Engineering, Nanjing Normal University, No. 122, Ninghai Ave., Nanjing, 210097, People’s Republic of China

    Caixia Liu & Mingyong Pang

Authors
  1. Caixia Liu
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Mingyong Pang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Mingyong Pang.

Ethics declarations

Conflict of Interest

The authors declare that they have no conflict of interest.

Additional information

Publisher’s Note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Liu, C., Pang, M. Extracting Lungs from CT Images via Deep Convolutional Neural Network Based Segmentation and Two-Pass Contour Refinement. J Digit Imaging 33, 1465–1478 (2020). https://doi.org/10.1007/s10278-020-00388-0

Download citation

  • Received:

  • Revised:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s10278-020-00388-0

Keywords

Search

Navigation