Korean Journal of Radiology

  • 제22권3호
  • /
  • Pages.476-488
  • /
  • 2021
  • /
  • 1229-6929(pISSN)
  • /
  • 2005-8330(eISSN)
대한영상의학회 (The Korean Society of Radiology)
권호 표지
DOI QR코드

DOI QR Code

Automated Lung Segmentation on Chest Computed Tomography Images with Extensive Lung Parenchymal Abnormalities Using a Deep Neural Network

  • Seung-Jin Yoo (Department of Radiology, Hanyang University Medical Center, Hanyang University College of Medicine) ;
  • Soon Ho Yoon (Department of Radiology, Seoul National University Hospital, Seoul National College of Medicine) ;
  • Jong Hyuk Lee (Department of Radiology, Seoul National University Hospital, Seoul National College of Medicine) ;
  • Ki Hwan Kim (Department of Radiology, Myongji Hospital) ;
  • Hyoung In Choi (Korean Armed Forces Capital Hospital) ;
  • Sang Joon Park (Department of Radiology, Seoul National University Hospital, Seoul National College of Medicine) ;
  • Jin Mo Goo (Department of Radiology, Seoul National University Hospital, Seoul National College of Medicine)
  • 투고 : 2020.03.20
  • 심사 : 2020.06.28
  • 발행 : 2021.03.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

Objective: We aimed to develop a deep neural network for segmenting lung parenchyma with extensive pathological conditions on non-contrast chest computed tomography (CT) images. Materials and Methods: Thin-section non-contrast chest CT images from 203 patients (115 males, 88 females; age range, 31-89 years) between January 2017 and May 2017 were included in the study, of which 150 cases had extensive lung parenchymal disease involving more than 40% of the parenchymal area. Parenchymal diseases included interstitial lung disease (ILD), emphysema, nontuberculous mycobacterial lung disease, tuberculous destroyed lung, pneumonia, lung cancer, and other diseases. Five experienced radiologists manually drew the margin of the lungs, slice by slice, on CT images. The dataset used to develop the network consisted of 157 cases for training, 20 cases for development, and 26 cases for internal validation. Two-dimensional (2D) U-Net and three-dimensional (3D) U-Net models were used for the task. The network was trained to segment the lung parenchyma as a whole and segment the right and left lung separately. The University Hospitals of Geneva ILD dataset, which contained high-resolution CT images of ILD, was used for external validation. Results: The Dice similarity coefficients for internal validation were 99.6 ± 0.3% (2D U-Net whole lung model), 99.5 ± 0.3% (2D U-Net separate lung model), 99.4 ± 0.5% (3D U-Net whole lung model), and 99.4 ± 0.5% (3D U-Net separate lung model). The Dice similarity coefficients for the external validation dataset were 98.4 ± 1.0% (2D U-Net whole lung model) and 98.4 ± 1.0% (2D U-Net separate lung model). In 31 cases, where the extent of ILD was larger than 75% of the lung parenchymal area, the Dice similarity coefficients were 97.9 ± 1.3% (2D U-Net whole lung model) and 98.0 ± 1.2% (2D U-Net separate lung model). Conclusion: The deep neural network achieved excellent performance in automatically delineating the boundaries of lung parenchyma with extensive pathological conditions on non-contrast chest CT images.

키워드

과제정보

The authors would like to acknowledge Andrew Dombrowski, PhD (Compecs, Inc.) for his assistance in improving the use of English in this manuscript.

참고문헌

  1. De Nunzio G, Tommasi E, Agrusti A, Cataldo R, De Mitri I, Favetta M, et al. Automatic lung segmentation in CT images with accurate handling of the hilar region. J Digit Imaging 2011;24:11-27 
  2. Scholten ET, Jacobs C, van Ginneken B, Willemink MJ, Kuhnigk JM, van Ooijen PM, et al. Computer-aided segmentation and volumetry of artificial ground-glass nodules at chest CT. AJR Am J Roentgenol 2013;201:295-300 
  3. Wang J, Li F, Li Q. Automated segmentation of lungs with severe interstitial lung disease in CT. Med Phys 2009;36:4592-4599 
  4. Tan KL, Toshiyuki T, Hidetoshi N, Akitoshi I. A neural network based computer-aided diagnosis of emphysema using CT lung images. Proceedings of the SICE Annual Conference; 2007 Sep 17-20; Takamatsu, Japan: IEEE; p. 703-709 
  5. Brown MS, Kim HJ, Abtin FG, Strange C, Galperin-Aizenberg M, Pais R, et al. Emphysema lung lobe volume reduction: effects on the ipsilateral and contralateral lobes. Eur Radiol 2012;22:1547-1555 
  6. Agnes SA, Anitha J, Peter JD. Automatic lung segmentation in low-dose chest CT scans using convolutional deep and wide network (CDWN). Neural Comput & Applic 2020;32:15845-15855 
  7. Mansoor A, Bagci U, Foster B, Xu Z, Papadakis GZ, Folio LR, et al. Segmentation and image analysis of abnormal lungs at CT: current approaches, challenges, and future trends. Radiographics 2015;35:1056-1076 
  8. Lee JW, Kim HY, Goo JM, Kim EY, Lee SJ, Kim TJ, et al. Radiological report of pilot study for the Korean lung cancer screening (K-LUCAS) project: feasibility of implementing lung imaging reporting and data system. Korean J Radiol 2018;19:803-808 
  9. Romei C, Tavanti L, Sbragia P, De Liperi A, Carrozzi L, Aquilini F, et al. Idiopathic interstitial pneumonias: do HRCT criteria established by ATS/ERS/JRS/ALAT in 2011 predict disease progression and prognosis? Radiol Med 2015;120:930-940 
  10. Han MK, Kazerooni EA, Lynch DA, Liu LX, Murray S, Curtis JL, et al. Chronic obstructive pulmonary disease exacerbations in the COPDGene study: associated radiologic phenotypes. Radiology 2011;261:274-282 
  11. Ioffe S, Szegedy C. Batch normalization: accelerating deep network training by reducing internal covariate shift. arXiv preprint 2015;arXiv:1502.03167 
  12. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Proceedings neural information processing systems conrerence (NIPS) 2012; 2012 Dec 3-6; Nevada, USA: NIPS; p. 1097-1105 
  13. Wu Y, He K. Group normalization. Proceedings of the European Conference on Computer Vision (ECCV); 2018 Sep 8-14; Munich, Germany: ECCV; p. 3-19 
  14. He K, Zhang X, Ren S, Sun J. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. Proceedings of the IEEE international conference on computer vision (ICCV); 2015 DEC 7-13; Santiago, Chile: IEEE; p. 1026-1034 
  15. Depeursinge A, Vargas A, Platon A, Geissbuhler A, Poletti PA, Muller H. Building a reference multimedia database for interstitial lung diseases. Comput Med Imaging Graph 2012;36:227-238 
  16. Taha AA, Hanbury A. An efficient algorithm for calculating the exact Hausdorff distance. IEEE Trans Pattern Anal Mach Intell 2015;37:2153-2163 
  17. Choi H, Qi X, Yoon SH, Park SJ, Lee KH, Kim JY, et al. Extension of coronavirus disease 2019 (COVID-19) on chest CT and implications for chest radiograph interpretation. Radiology: Cardiothoracic Imaging 2020;2:e200107 
  18. Colombi D, Bodini FC, Petrini M, Maffi G, Morelli N, Milanese G, et al. Well-aerated lung on admitting chest CT to predict adverse outcome in COVID-19 pneumonia. Radiology 2020;296:E86-E96 
  19. Pulagam AR, Kande GB, Ede VK, Inampudi RB. Automated lung segmentation from HRCT scans with diffuse parenchymal lung diseases. J Digit Imaging 2016;29:507-519 
  20. Harrison AP, Xu Z, George K, Lu L, Summers RM, Mollura DJ. Progressive and multi-path holistically nested neural networks for pathological lung segmentation from CT images. In: DescoteauxLena M, Maier-Hein L, Franz A, Jannin P, Collins DL, Duchesne S. eds. International Conference on Medical Image Computing and Computer-Assisted Intervention (MICCAI) 2017; 2017 Sep 11-13; Quebec City, Canada: Springer; p. 621-629 
  21. Alves JH, Neto PMM, Oliveira LF. Extracting lungs from CT images using fully convolutional networks. Proceedings 2018 International Joint Conference on Neural Networks (IJCNN); 2018 Jul 8-13; Rio de Janeiro, Brazil: IEEE; p. 1-8 
  22. Gibbs JM, Chandrasekhar CA, Ferguson EC, Oldham SA. Lines and stripes: where did they go?--From conventional radiography to CT. Radiographics 2007;27:33-48