Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
184 tokens/sec
GPT-4o
7 tokens/sec
Gemini 2.5 Pro Pro
45 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
38 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

NaviAirway: a Bronchiole-sensitive Deep Learning-based Airway Segmentation Pipeline (2203.04294v3)

Published 8 Mar 2022 in eess.IV, cs.AI, and cs.CV

Abstract: Airway segmentation is essential for chest CT image analysis. Different from natural image segmentation, which pursues high pixel-wise accuracy, airway segmentation focuses on topology. The task is challenging not only because of its complex tree-like structure but also the severe pixel imbalance among airway branches of different generations. To tackle the problems, we present a NaviAirway method which consists of a bronchiole-sensitive loss function for airway topology preservation and an iterative training strategy for accurate model learning across different airway generations. To supplement the features of airway branches learned by the model, we distill the knowledge from numerous unlabeled chest CT images in a teacher-student manner. Experimental results show that NaviAirway outperforms existing methods, particularly in the identification of higher-generation bronchioles and robustness to new CT scans. Moreover, NaviAirway is general enough to be combined with different backbone models to significantly improve their performance. NaviAirway can generate an airway roadmap for Navigation Bronchoscopy and can also be applied to other scenarios when segmenting fine and long tubular structures in biomedical images. The code is publicly available on https://github.com/AntonotnaWang/NaviAirway.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (60)
  1. T. Ishiwata, A. Gregor, T. Inage, and K. Yasufuku, “Bronchoscopic navigation and tissue diagnosis,” General thoracic and cardiovascular surgery, vol. 68, no. 7, pp. 672–678, 2020.
  2. E. Edell and D. Krier-Morrow, “Navigational bronchoscopy: Overview of technology and practical considerations—new current procedural terminology codes effective 2010,” Chest, vol. 137, no. 2, pp. 450–454, 2010.
  3. F. Asano, R. Eberhardt, and F. J. Herth, “Virtual bronchoscopic navigation for peripheral pulmonary lesions,” Respiration, vol. 88, no. 5, pp. 430–440, 2014.
  4. S. V. Kemp, “Navigation bronchoscopy,” Respiration, vol. 99, no. 4, pp. 277–286, 2020.
  5. P. Berger, V. Perot, P. Desbarats, J. M. Tunon-de Lara, R. Marthan, and F. Laurent, “Airway wall thickness in cigarette smokers: quantitative thin-section ct assessment,” Radiology, vol. 235, no. 3, pp. 1055–1064, 2005.
  6. A. Agustí and J. C. Hogg, “Update on the pathogenesis of chronic obstructive pulmonary disease,” New England Journal of Medicine, vol. 381, no. 13, pp. 1248–1256, 2019.
  7. Y. Qin, H. Zheng, Y. Gu, X. Huang, J. Yang, L. Wang, and Y.-M. Zhu, “Learning bronchiole-sensitive airway segmentation cnns by feature recalibration and attention distillation,” in International Conference on Medical Image Computing and Computer-Assisted Intervention.   Springer, 2020, pp. 221–231.
  8. W. O. Reece, “Overview of the respiratory system,” Dukes’ physiology of domestic animals, vol. 203, 2015.
  9. H. Zhang, M. Shen, P. L. Shah, and G.-Z. Yang, “Pathological airway segmentation with cascaded neural networks for bronchoscopic navigation,” in 2020 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2020, pp. 9974–9980.
  10. E. M. Van Rikxoort and B. Van Ginneken, “Automated segmentation of pulmonary structures in thoracic computed tomography scans: a review,” Physics in Medicine & Biology, vol. 58, no. 17, p. R187, 2013.
  11. J. Pu, S. Gu, S. Liu, S. Zhu, D. Wilson, J. M. Siegfried, and D. Gur, “Ct based computerized identification and analysis of human airways: a review,” Medical physics, vol. 39, no. 5, pp. 2603–2616, 2012.
  12. P. Lo, B. Van Ginneken, J. M. Reinhardt, T. Yavarna, P. A. De Jong, B. Irving, C. Fetita, M. Ortner, R. Pinho, J. Sijbers et al., “Extraction of airways from ct (exact’09),” IEEE Transactions on Medical Imaging, vol. 31, no. 11, pp. 2093–2107, 2012.
  13. D. Aykac, E. A. Hoffman, G. McLennan, and J. M. Reinhardt, “Segmentation and analysis of the human airway tree from three-dimensional x-ray ct images,” IEEE transactions on medical imaging, vol. 22, no. 8, pp. 940–950, 2003.
  14. H. Shi, W. C. Scarfe, and A. G. Farman, “Upper airway segmentation and dimensions estimation from cone-beam ct image datasets,” International Journal of Computer Assisted Radiology and Surgery, vol. 1, no. 3, pp. 177–186, 2006.
  15. I. Cheng, S. Nilufar, C. Flores-Mir, and A. Basu, “Airway segmentation and measurement in ct images,” in 2007 29th Annual International Conference of the IEEE Engineering in Medicine and Biology Society.   IEEE, 2007, pp. 795–799.
  16. J. Tschirren, E. A. Hoffman, G. McLennan, and M. Sonka, “Intrathoracic airway trees: segmentation and airway morphology analysis from low-dose ct scans,” IEEE transactions on medical imaging, vol. 24, no. 12, pp. 1529–1539, 2005.
  17. ——, “Segmentation and quantitative analysis of intrathoracic airway trees from computed tomography images,” Proceedings of the American Thoracic Society, vol. 2, no. 6, pp. 484–487, 2005.
  18. A. Fabijańska, “Two-pass region growing algorithm for segmenting airway tree from mdct chest scans,” Computerized Medical Imaging and Graphics, vol. 33, no. 7, pp. 537–546, 2009.
  19. M. W. Graham, J. D. Gibbs, D. C. Cornish, and W. E. Higgins, “Robust 3-d airway tree segmentation for image-guided peripheral bronchoscopy,” IEEE transactions on medical imaging, vol. 29, no. 4, pp. 982–997, 2010.
  20. C. Fetita, M. Ortner, P.-Y. Brillet, F. Prêteux, P. Grenier et al., “A morphological-aggregative approach for 3d segmentation of pulmonary airways from generic msct acquisitions,” in Proc. of Second International Workshop on Pulmonary Image Analysis, 2009, pp. 215–226.
  21. A. P. Kiraly, W. E. Higgins, G. McLennan, E. A. Hoffman, and J. M. Reinhardt, “Three-dimensional human airway segmentation methods for clinical virtual bronchoscopy,” Academic radiology, vol. 9, no. 10, pp. 1153–1168, 2002.
  22. Q. Meng, T. Kitasaka, Y. Nimura, M. Oda, J. Ueno, and K. Mori, “Automatic segmentation of airway tree based on local intensity filter and machine learning technique in 3d chest ct volume,” International journal of computer assisted radiology and surgery, vol. 12, no. 2, pp. 245–261, 2017.
  23. B. van Ginneken, W. Baggerman, and E. M. van Rikxoort, “Robust segmentation and anatomical labeling of the airway tree from thoracic ct scans,” in International Conference on Medical Image Computing and Computer-Assisted Intervention.   Springer, 2008, pp. 219–226.
  24. Ö. Çiçek, A. Abdulkadir, S. S. Lienkamp, T. Brox, and O. Ronneberger, “3d u-net: learning dense volumetric segmentation from sparse annotation,” in International conference on medical image computing and computer-assisted intervention.   Springer, 2016, pp. 424–432.
  25. D. Jin, Z. Xu, A. P. Harrison, K. George, and D. J. Mollura, “3d convolutional neural networks with graph refinement for airway segmentation using incomplete data labels,” in International workshop on machine learning in medical imaging.   Springer, 2017, pp. 141–149.
  26. A. G.-U. Juarez, H. A. Tiddens, and M. de Bruijne, “Automatic airway segmentation in chest ct using convolutional neural networks,” in Image analysis for moving organ, breast, and thoracic images.   Springer, 2018, pp. 238–250.
  27. S. A. Nadeem, E. A. Hoffman, J. C. Sieren, A. P. Comellas, S. P. Bhatt, I. Z. Barjaktarevic, F. Abtin, and P. K. Saha, “A ct-based automated algorithm for airway segmentation using freeze-and-grow propagation and deep learning,” IEEE Transactions on Medical Imaging, vol. 40, no. 1, pp. 405–418, 2020.
  28. A. Garcia-Uceda, R. Selvan, Z. Saghir, H. Tiddens, and M. de Bruijne, “Automatic airway segmentation from computed tomography using robust and efficient 3-d convolutional neural networks,” arXiv preprint arXiv:2103.16328, 2021.
  29. J. Schlemper, O. Oktay, M. Schaap, M. Heinrich, B. Kainz, B. Glocker, and D. Rueckert, “Attention gated networks: Learning to leverage salient regions in medical images,” Medical image analysis, vol. 53, pp. 197–207, 2019.
  30. C. Wang, Y. Hayashi, M. Oda, H. Itoh, T. Kitasaka, A. F. Frangi, and K. Mori, “Tubular structure segmentation using spatial fully connected network with radial distance loss for 3d medical images,” in International Conference on Medical Image Computing and Computer-Assisted Intervention.   Springer, 2019, pp. 348–356.
  31. A. G.-U. Juarez, R. Selvan, Z. Saghir, and M. de Bruijne, “A joint 3d unet-graph neural network-based method for airway segmentation from chest cts,” in International workshop on machine learning in medical imaging.   Springer, 2019, pp. 583–591.
  32. R. Selvan, T. Kipf, M. Welling, A. G.-U. Juarez, J. H. Pedersen, J. Petersen, and M. de Bruijne, “Graph refinement based airway extraction using mean-field networks and graph neural networks,” Medical Image Analysis, vol. 64, p. 101751, 2020.
  33. J. Yun, J. Park, D. Yu, J. Yi, M. Lee, H. J. Park, J.-G. Lee, J. B. Seo, and N. Kim, “Improvement of fully automated airway segmentation on volumetric computed tomographic images using a 2.5 dimensional convolutional neural net,” Medical image analysis, vol. 51, pp. 13–20, 2019.
  34. Y. Qin, M. Chen, H. Zheng, Y. Gu, M. Shen, J. Yang, X. Huang, Y.-M. Zhu, and G.-Z. Yang, “Airwaynet: a voxel-connectivity aware approach for accurate airway segmentation using convolutional neural networks,” in International Conference on Medical Image Computing and Computer-Assisted Intervention.   Springer, 2019, pp. 212–220.
  35. Y. Qin, Y. Gu, H. Zheng, M. Chen, J. Yang, and Y.-M. Zhu, “Airwaynet-se: A simple-yet-effective approach to improve airway segmentation using context scale fusion,” in 2020 IEEE 17th International Symposium on Biomedical Imaging (ISBI).   IEEE, 2020, pp. 809–813.
  36. Y. Qin, H. Zheng, Y. Gu, X. Huang, J. Yang, L. Wang, F. Yao, Y.-M. Zhu, and G.-Z. Yang, “Learning tubule-sensitive cnns for pulmonary airway and artery-vein segmentation in ct,” IEEE Transactions on Medical Imaging, vol. 40, no. 6, pp. 1603–1617, 2021.
  37. H. Zheng, Y. Qin, Y. Gu, F. Xie, J. Yang, J. Sun, and G.-Z. Yanga, “Alleviating class-wise gradient imbalance for pulmonary airway segmentation,” IEEE Transactions on Medical Imaging, 2021.
  38. W. Wu, Y. Yu, Q. Wang, D. Liu, and X. Yuan, “Upper airway segmentation based on the attention mechanism of weak feature regions,” IEEE Access, vol. 9, pp. 95 372–95 381, 2021.
  39. W. Yu, H. Zheng, M. Zhang, H. Zhang, J. Sun, and J. Yang, “Break: Bronchi reconstruction by geodesic transformation and skeleton embedding,” in 2022 IEEE 19th International Symposium on Biomedical Imaging (ISBI).   IEEE, 2022, pp. 1–5.
  40. M. Zhang, X. Yu, H. Zhang, H. Zheng, W. Yu, H. Pan, X. Cai, and Y. Gu, “Fda: Feature decomposition and aggregation for robust airway segmentation,” in Domain Adaptation and Representation Transfer, and Affordable Healthcare and AI for Resource Diverse Global Health: Third MICCAI Workshop, DART 2021, and First MICCAI Workshop, FAIR 2021, Held in Conjunction with MICCAI 2021, Strasbourg, France, September 27 and October 1, 2021, Proceedings 3.   Springer, 2021, pp. 25–34.
  41. Y. Gu, C. Gu, J. Yang, J. Sun, and G.-Z. Yang, “Vision–kinematics interaction for robotic-assisted bronchoscopy navigation,” IEEE Transactions on Medical Imaging, vol. 41, no. 12, pp. 3600–3610, 2022.
  42. H. Zheng, Y. Qin, Y. Gu, F. Xie, J. Sun, J. Yang, and G.-Z. Yang, “Refined local-imbalance-based weight for airway segmentation in ct,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2021: 24th International Conference, Strasbourg, France, September 27–October 1, 2021, Proceedings, Part I.   Springer, 2021, pp. 410–419.
  43. M. Zhang, H. Zhang, G.-Z. Yang, and Y. Gu, “Cfda: Collaborative feature disentanglement and augmentation for pulmonary airway tree modeling of covid-19 cts,” in Medical Image Computing and Computer Assisted Intervention–MICCAI 2022: 25th International Conference, Singapore, September 18–22, 2022, Proceedings, Part I.   Springer, 2022, pp. 506–516.
  44. Y. Wu, M. Zhang, W. Yu, H. Zheng, J. Xu, and Y. Gu, “Ltsp: long-term slice propagation for accurate airway segmentation,” International Journal of Computer Assisted Radiology and Surgery, vol. 17, no. 5, pp. 857–865, 2022.
  45. Q. Xie, M.-T. Luong, E. Hovy, and Q. V. Le, “Self-training with noisy student improves imagenet classification,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2020, pp. 10 687–10 698.
  46. H. Balacey, “Mise en place d’une chaîne complète d’analyse de l’arbre trachéo-bronchique à partir d’examen (s) issus d’un scanner-ct: de la 3d vers la 4d,” Ph.D. dissertation, Bordeaux 1, 2013.
  47. P. Nardelli, K. A. Khan, A. Corvò, N. Moore, M. J. Murphy, M. Twomey, O. J. O’Connor, M. P. Kennedy, R. S. J. Estépar, M. M. Maher et al., “Optimizing parameters of an open-source airway segmentation algorithm using different ct images,” Biomedical engineering online, vol. 14, no. 1, pp. 1–24, 2015.
  48. T. Inoue, Y. Kitamura, Y. Li, and W. Ito, “Robust airway extraction based on machine learning and minimum spanning tree,” in Medical Imaging 2013: Computer-Aided Diagnosis, vol. 8670.   International Society for Optics and Photonics, 2013, p. 86700L.
  49. F. Milletari, N. Navab, and S.-A. Ahmadi, “V-net: Fully convolutional neural networks for volumetric medical image segmentation,” in 2016 fourth international conference on 3D vision (3DV).   IEEE, 2016, pp. 565–571.
  50. T.-C. Lee, R. L. Kashyap, and C.-N. Chu, “Building skeleton models via 3-d medial surface axis thinning algorithms,” CVGIP: graphical models and image processing, vol. 56, no. 6, pp. 462–478, 1994.
  51. H. He and E. A. Garcia, “Learning from imbalanced data,” IEEE Transactions on knowledge and data engineering, vol. 21, no. 9, pp. 1263–1284, 2009.
  52. C. Wei, K. Shen, Y. Chen, and T. Ma, “Theoretical analysis of self-training with deep networks on unlabeled data,” arXiv preprint arXiv:2010.03622, 2020.
  53. S. G. Armato III, G. McLennan, L. Bidaut, M. F. McNitt-Gray, C. R. Meyer, A. P. Reeves, B. Zhao, D. R. Aberle, C. I. Henschke, E. A. Hoffman et al., “The lung image database consortium (lidc) and image database resource initiative (idri): a completed reference database of lung nodules on ct scans,” Medical physics, vol. 38, no. 2, pp. 915–931, 2011.
  54. Y. Xue, H. Tang, Z. Qiao, G. Gong, Y. Yin, Z. Qian, C. Huang, W. Fan, and X. Huang, “Shape-aware organ segmentation by predicting signed distance maps,” in Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, no. 07, 2020, pp. 12 565–12 572.
  55. Z. Xu, U. Bagci, B. Foster, A. Mansoor, J. K. Udupa, and D. J. Mollura, “A hybrid method for airway segmentation and automated measurement of bronchial wall thickness on ct,” Medical image analysis, vol. 24, no. 1, pp. 1–17, 2015.
  56. M. Zhang, G.-Z. Yang, and Y. Gu, “Differentiable topology-preserved distance transform for pulmonary airway segmentation,” arXiv preprint arXiv:2209.08355, 2022.
  57. E. Smistad, A. C. Elster, and F. Lindseth, “Gpu accelerated segmentation and centerline extraction of tubular structures from medical images,” International journal of computer assisted radiology and surgery, vol. 9, no. 4, pp. 561–575, 2014.
  58. A. Paszke, S. Gross, F. Massa, A. Lerer, J. Bradbury, G. Chanan, T. Killeen, Z. Lin, N. Gimelshein, L. Antiga et al., “Pytorch: An imperative style, high-performance deep learning library,” Advances in neural information processing systems, vol. 32, 2019.
  59. F. Pérez-García, R. Sparks, and S. Ourselin, “Torchio: a python library for efficient loading, preprocessing, augmentation and patch-based sampling of medical images in deep learning,” Computer Methods and Programs in Biomedicine, p. 106236, 2021.
  60. H. Chen, Q. Dou, L. Yu, J. Qin, and P.-A. Heng, “Voxresnet: Deep voxelwise residual networks for brain segmentation from 3d mr images,” NeuroImage, vol. 170, pp. 446–455, 2018.
Citations (22)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now