[go: up one dir, main page]
More Web Proxy on the site http://driver.im/ Skip to main content

Advertisement

Springer Nature Link
Log in

Automatic lung tumor segmentation from CT images using improved 3D densely connected UNet

  • Original Article
  • Published:
Medical & Biological Engineering & Computing Aims and scope Submit manuscript

Abstract

Accurate lung tumor segmentation has great significance in the treatment planning of lung cancer. However, robust lung tumor segmentation becomes challenging due to the heterogeneity of tumors and the similar visual characteristics between tumors and surrounding tissues. Hence, we developed an improved 3D dense connected UNet (I-3D DenseUNet) to segment various lung tumors from CT images. The nested dense skip connection adopted in the I-3D DenseUNet aims to contribute similar feature maps between encoder and decoder sub-networks. The dense connection used in encoder-decoder blocks also encourages feature propagation and reuse. A robust data augmentation strategy was employed to alleviate over-fitting based on a 3D thin plate spline (TPS) algorithm. We evaluated our method on 938 lung tumors from three datasets consisting of 421 tumors from the Cancer Imaging Archive (TCIA), 450 malignant tumors from the Lung Image Database Consortium (LIDC), and 67 tumors from the private dataset. Experiment results showed an excellent Dice similarity coefficients (DSC) of 0.8316 for the TCIA and LIDC and 0.8167 for the private dataset. The proposed method presents a strong ability in lung tumor segmentation, and it has the potential to help radiologists in lung cancer treatment planning.

Graphical abstract

Framework of the proposed lung tumor segmentation method.

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
£29.99 /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 includes VAT (United Kingdom)

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

Similar content being viewed by others

References

  1. Siegel RL, Miller KD, Jemal A (2019) Cancer statistics, 2019. CA-Cancer J Clin 69(1):7–3

    Article  Google Scholar 

  2. Punithavathy K, Ramya MM, Poobal S (2015) Analysis of statistical texture features for automatic lung cancer detection in PET/CT images. In 2015 IEEE International Conference on Robotics

  3. Vas M, Dessai A (2017) Lung cancer detection system using lung CT image processing. In 2017 IEEE International Conference on Computing

  4. Zhang GB, Yang ZY, Gong L, Jiang S, Wang L (2019) Classification of benign and malignant lung nodules from CT images based on hybrid features. Phys Med Biol 64(12):125011

    Article  Google Scholar 

  5. Gibaldi A, Barone D, Gavelli G, Malavasi S, Bevilacqua A (2015) Effects of guided random sampling of TCCs on blood flow values in CT perfusion studies of lung tumors. Acad Radiol 22(1):58–69

    Article  Google Scholar 

  6. Ng QS, Goh V (2010) Angiogenesis in non-small cell lung cancer: imaging with perfusion computed tomography. J Thorac Imag 25(2):142–150

    Article  Google Scholar 

  7. Velazquez ER, Parmar C, Jermoumi M, Mak RH, van Baardwijk A, Fennessy FM, Lewis JH, De Ruysscher D, Kikinis R, Lambin P, Aerts HJWL (2013) Volumetric CT-based segmentation of NSCLC using 3D-Slicer. Sci Rep-UK 3:3529

    Article  Google Scholar 

  8. Reeves AP, Chan AB, Yankelevitz DF, Henschke CI, Kressler B, Kostis WJ (2006) On measuring the change in size of pulmonary nodules. IEEE T Med Imaging 25(4):435–450

    Article  Google Scholar 

  9. Goncalves L, Novo J, Campilho A (2016) Hessian based approaches for 3D lung nodule segmentation. Expert Syst Appl 61:1–15

    Article  Google Scholar 

  10. Hosseini-Asl E, Zurada JM, Gimel’farb G, El-Baz A (2016) 3-D lung segmentation by incremental constrained nonnegative matrix factorization. IEEE T Bio-Med Eng 63(5):952-963

  11. 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

    Article  Google Scholar 

  12. Dehmeshki J, Amin H, Valdivieso M, Ye X (2008) Segmentation of pulmonary nodules in thoracic CT scans: a region growing approach. IEEE T Med Imaging 27(4):467–480

    Article  CAS  Google Scholar 

  13. Ganem J, Thureau S, Gardin I, Modzelewski R, Hapdey S, Vera P (2018) Delineation of lung cancer with FDG PET/CT during radiation therapy. Radiat Oncol 13:219

    Article  CAS  Google Scholar 

  14. Lian C, Ruan S, Denœux T, Li H, Vera P (2019) Joint tumor segmentation in PET-CT images using co-clustering and fusion based on belief functions. IEEE T Image Process 28(2):755–766

    Article  Google Scholar 

  15. Lei YR, Zheng L, Lyu Z (2018) Lung tumor segmentation and 3D reconstruction based on region growing and correlation. In 2018 International Conference on Computer Information Science and Application Technology

  16. Kasinathan G, Jayakumar S, Gandomi AH, Ramachandran M, Fong SJ, Patan R (2019) Automated 3-D lung tumor detection and classification by an active contour model and CNN classifier. Expert Syst Appl 134:112–119

    Article  Google Scholar 

  17. Nithila EE, Kumar SS (2016) Segmentation of lung nodule in CT data using active contour model and fuzzy C-mean clustering. Alex Eng J 55(3):2583–2588

    Article  Google Scholar 

  18. Kuhnigk JM, Dicken V, Bornemann L, Bakai A, Wormanns D, Krass S, Peitgen HQ (2006) Morphological segmentation and partial volume analysis for volumetry of solid pulmonary lesions in thoracic CT scans. IEEE T Med Imaging 25(4):417–434

    Article  Google Scholar 

  19. Sargent D, Park SY (2017) Semi-automatic 3D lung nodule segmentation in CT using dynamic programming. In Medical Imaging 2017

  20. Diciotti S, Lombardo S, Falchini M, Picozzi G, Mascalchi M (2011) Automated segmentation refinement of small lung nodules in CT scans by local shape analysis. IEEE T Bio-Med Eng 58(12):3418–3428

    Article  Google Scholar 

  21. Khadidos A, Sanchez V, Li C (2017) Weighted level set evolution based on local edge features for medical image segmentation. IEEE T Image Process 26(4):1979–1991

    Article  Google Scholar 

  22. Wang J, Guo HY (2016) Automatic approach for lung segmentation with Juxta-pleural nodules from thoracic CT based on contour tracing and correction. Comput Math Method M :2962047

  23. Reboucas PP, Barros ACD, Almeida JS, Rodrigues JPC, de Albuquerque VHC (2019) A new effective and powerful medical image segmentation algorithm based on optimum path snakes. Appl Soft Comput 76:649–670

    Article  Google Scholar 

  24. Jiang J, Hu YC, Liu CJ, Halpenny D, Hellmann HM, Deasy JO, Mageras G, Veeraraghavan H (2019) Multiple resolution residually connected feature streams for automatic lung tumor segmentation from CT images. IEEE T Med Imaging 38(1):134–144

    Article  Google Scholar 

  25. Zhao XM, Li LQ, Lu W, Tan S (2019) Tumor co-segmentation in PET/CT using multimodality fully convolutional neural network. Phys Med Biol 64(1):015011

    Article  Google Scholar 

  26. Chen W, Wei H, Peng S, Sun J, Qiao X, Liu B (2019) HSN: hybrid segmentation network for small cell lung cancer segmentation. IEEE Access 7:75591–75603

    Article  Google Scholar 

  27. Cao HC, Liu H, Song EM, Hung CC, Ma GZ, Xu XY, Jin RC, Lu JG (2020) Dual-branch residual network for lung nodule segmentation. Appl Soft Comput 86:105934

    Article  Google Scholar 

  28. Wang C, Tyagi N, Rimner A, Hu YC, Veeraraghavan H, Li G, Hunt M, Mageras G, Zhang PP (2019) Segmenting lung tumors on longitudinal imaging studies via a patient-specific adaptive convolutional neural network. Radiother Oncol 131:101–107

    Article  Google Scholar 

  29. Nakano R, Arimura H, Haekal M, Ohga S (2019) Automated segmentation framework of lung gross tumor volumes on 3D planning CT images using dense V-Net deep learning. In International Forum on Medical Imaging in Asia

  30. Liu H, Cao HC, Song EM, Ma GZ, Xu XY, Jin RC, Jin Y, Hung CC (2019) A cascaded dual-pathway residual network for lung nodule segmentation in CT images. Phys Medica 63:112–121

    Article  Google Scholar 

  31. Wang S, Zhou M, Liu ZY, Gu DS, Zang YL, Dong D, Gevaert O, Tian J (2017) Central focused convolutional neural networks: developing a data-driven model for lung nodule segmentation. Med Image Anal 40:172–183

    Article  Google Scholar 

  32. Wu WH, Gao L, Duan HH, Huang G, Ye XD, Nie SD (2020) Segmentation of pulmonary nodules in CT images based on 3D-UNET combined with three-dimensional conditional random field optimization. Med Phys 47:4054–4063

    Article  Google Scholar 

  33. Pezzano G, Ripoll VR, Radeva (2021) PCoLe-CNN: context-learning convolutional neural network with adaptive loss function for lung nodule segmentation, Comput Meth Prog Bio, 198: 105792

  34. Yang JZ, Wu B, Li LT, Cao P, Zaiane O (2021) MSDS-UNet: a multi-scale deeply supervised 3D U-Net for automatic segmentation of lung tumor in CT. Comput Med Imag Grap 92:101957

    Article  Google Scholar 

  35. Xiao ZT, Liu BW, Geng L, Zhang F, Liu YB (2020) Segmentation of lung nodules using improved 3D-UNet neural network. Symmetry-Basel 12:1787

    Article  Google Scholar 

  36. Badrinarayanan V, Kendall A, Cipolla R (2017) SegNet: a deep convolutional encoder- decoder architecture for image segmentation. IEEE T Pattern Anal 39(12):2481–2495

    Article  Google Scholar 

Download references

Acknowledgements

We gratefully acknowledge the Second Hospital of Tianjin Medical University for their continuous support in collecting patient data and providing a professional diagnosis.

Funding

This study was funded by the National Natural Science Foundation of China (grant number 81871457), National Natural Science Foundation of China (grant number 51811530310), and National Natural Science Foundation of China (grant number 51775368).

Author information

Authors and Affiliations

  1. Tianjin Key Laboratory for Advanced Mechatronic System Design and Intelligent Control, School of Mechanical Engineering, Tianjin University of Technology, Tianjin, 300384, China

    Guobin Zhang

  2. National Demonstration Center for Experimental Mechanical and Electrical Engineering Education, Tianjin University of Technology, Tianjin, 300384, China

    Guobin Zhang

  3. School of Mechanical Engineering, Tianjin University, Tianjin, 300350, China

    Zhiyong Yang & Shan Jiang

  4. Centre for Advanced Mechanisms and Robotics, Tianjin University, 135 Yaguan Road, Jinnan District, Tianjin, 300350, China

    Shan Jiang

Authors
  1. Guobin Zhang
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zhiyong Yang
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Shan Jiang
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Shan Jiang.

Additional information

Publisher’s note

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

Rights and permissions

Springer Nature or its licensor holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Zhang, G., Yang, Z. & Jiang, S. Automatic lung tumor segmentation from CT images using improved 3D densely connected UNet. Med Biol Eng Comput 60, 3311–3323 (2022). https://doi.org/10.1007/s11517-022-02667-0

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s11517-022-02667-0

Keywords

Search

Navigation