A Deep Attention-based U-Net for Airways Segmentation in Computed
Tomography Images

Anita      Khanna; Narendra   Digambar   Londhe; Shubhrata      Gupta

doi:10.2174/1573405618666220630151409

Abstract

Background: Airway segmentation is a way to quantify the diagnosis of pulmonary diseases, including chronic obstructive problems and bronchiectasis. Manual analysis by radiologists is a challenging task due to the complex airway structure. Additionally, tree-like patterns, varied shapes, sizes, and intensity make the manual airway segmentation task more complex. Deeper airways are even more difficult to segment as their intensity starts matching the lung parenchyma as the diameter of the airway cross-section gets reduced.

Objective: Many earlier works have proposed different deep learning networks for airway segmentation but were unable to achieve the desired performance; hence the task of airway segmentation still possesses challenges in this field.

Methods: This work proposes a convolutional neural network based on deep U-Net architecture and employs an attention block technique for airway segmentation. The attention mechanism aids in the extraction of the complicated and multi-sized airways found in the lung region, hence increasing the efficiency of the U-Net architecture.

Results: The model has been validated using VESSEL12 and EXACT09 datasets, individually and combined, with and without trachea images. The best DSC scores on EXACT09 and VESSEL12 datasets are 95.21% and 95.80%, respectively. The performance on both datasets combined gave a DSC score of 94.1%, showing that the overall performance of the proposed methodology is quite satisfactory. The generalizability of the model is also confirmed using k-fold cross-validation. The comparison of the proposed model to existing research on airway segmentation found competitive results.

Conclusion: The use of an attention unit in the proposed model highlights the relevant information and reduces the irrelevant features, which helps to improve the performance and saves time.

Keywords: Airway segmentation, deep learning, convolutional neural network, U-Net, attention mechanism, medical image processing.

Graphical Abstract

[1]
Mori K, Hasegawa JI, Toriwaki JI, Anno H, Katada K. Automated extraction and visualization of bronchus from 3D CT images of lung. International Conference on Computer Vision, Virtual Reality, and Robotics in Medicine.  542-8.

[2]
Kiraly AP, Higgins WE, Hoffman EA, McLennan G, Reinhardt JM. 3D human airway segmentation for virtual bronchoscopy. In: Medical Imaging.   2002; 4638: pp. 16-29.

[3]
Fabijanska A. Results of applying two-pass region growing algorithm for airway tree segmentation to MDCT chest scans from EXACT database. The Second International Workshop on Pulmonary Image Analysis,. CreateSpace, USA. 

[4]
Aykac D, Hoffman EA, McLennan G, Reinhardt JM. Segmentation and analysis of the human airway tree from three-dimensional X-ray CT images. IEEE Trans Med Imaging  2003; 22(8): 940-50.
 [http://dx.doi.org/10.1109/TMI.2003.815905] [PMID:  12906248]

[5]
Fetita CI, Prêteux F, Beigelman-Aubry C, Grenier P. Pulmonary airways: 3-D reconstruction from multislice CT and clinical investigation. IEEE Trans Med Imaging  2004; 23(11): 1353-64.
 [http://dx.doi.org/10.1109/TMI.2004.826945] [PMID:  15554124]

[6]
Frangi AF, Niessen WJ, Vincken KL, Viergever MA. Multiscale vessel enhancement filtering, medical image computing and computer-assisted intervention. 1496.

[7]
Mori K, Hasegawa JI, Toriwaki JI, Anno H, Katada K. Recognition of bronchus in three-dimensional X-ray CT images with applications to virtualized bronchoscopy system. Proceedings of 13th International Conference on Pattern Recognition. 

[8]
Schlathoelter T, Lorenz C, Carlsen IC, Renisch S, Deschamps T. Simultaneous segmentation and tree reconstruction of the airways for virtual bronchoscopy. Medical imaging 2002: image processing.   2002; 4684: pp. 103-13.
 [http://dx.doi.org/10.1117/12.467061]

[9]
Mayer D, Bartz D, Fischer J, et al. Hybrid segmentation and virtual bronchoscopy based on CT images. Acad Radiol  2004; 11(5): 551-65.
 [http://dx.doi.org/10.1016/j.acra.2004.01.012] [PMID:  15147620]

[10]
Palágyi K, Balogh E, Kuba A, et al. A sequential 3D thinning algorithm and its medical applications. Biennial International Conference on Information Processing in Medical Imaging.  409-15.

[11]
Gagvani N, Silver D. Parameter-controlled volume thinning. Graph Models Image Proc  1999; 61(3): 149-64.
 [http://dx.doi.org/10.1006/gmip.1999.0495]

[12]
Liu B, Telea AC, Roerdink JB, et al. Parallel centerline extraction on the GPU. Comput Graph  2014; 41: 72-83.
 [http://dx.doi.org/10.1016/j.cag.2014.02.003]

[13]
Pulagam AR, Ede VK, Inampudi RB. Segmentation of airways in lung region using novel statistical thresholding and morphology methods. Biomed Pharmacol J  2017; 10(4): 2035-43.
 [http://dx.doi.org/10.13005/bpj/1325]

[14]
Lo P, van Ginneken B, Reinhardt JM, et al. Extraction of airways from CT (EXACT’09). IEEE Trans Med Imaging  2012; 31(11): 2093-107.
 [http://dx.doi.org/10.1109/TMI.2012.2209674] [PMID:  22855226]

[15]
Bian Z, Tan W, Yang J, Liu J, Zhao D. Accurate airway centerline extraction based on topological thinning using graph-theoretic analysis. Biomed Mater Eng  2014; 24(6): 3239-49.
 [http://dx.doi.org/10.3233/BME-141146] [PMID:  25227033]

[16]
Xu Z, Bagci U, Foster B, Mansoor A, Udupa JK, Mollura DJ. A hybrid method for airway segmentation and automated measurement of bronchial wall thickness on CT. Med Image Anal  2015; 24(1): 1-17.
 [http://dx.doi.org/10.1016/j.media.2015.05.003] [PMID:  26026778]

[17]
LeCun Y, Bengio Y, Hinton G. Deep learning. Nature  2015; 521(7553): 436-4.

[18]
Schmidhuber J. Deep learning in neural networks: an overview. Neural Netw  2015; 61: 85-117.
 [http://dx.doi.org/10.1016/j.neunet.2014.09.003] [PMID:  25462637]

[19]
Sermanet P, Eigen D, Zhang X, Mathieu M, Fergus R, LeCun Y. Overfeat: Integrated recognition, localization and detection using convolutional networks. 2013.

[20]
Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. 2014.

[21]
Jin D, Xu Z, Harrison AP, George K, Mollura DJ. 3D convolutional neural networks with graph refinement for airway segmentation using incomplete data labels. International workshop on machine learning in medical imaging  141-9.

[22]
Juarez AG, Tiddens HA, de Bruijne M. Automatic airway segmentation in chest CT using convolutional neural networks. In: Image analysis for moving organ, breast, and thoracic images.  Springer, Cham 2018; pp. 238-50.

[23]
Charbonnier JP, Rikxoort EMV, Setio AAA, Schaefer-Prokop CM, Ginneken BV, Ciompi F. Improving airway segmentation in computed tomography using leak detection with convolutional networks. Med Image Anal  2017; 36: 52-60.
 [http://dx.doi.org/10.1016/j.media.2016.11.001] [PMID:  27842236]

[24]
Yun J, Park J, Yu D, et al. Improvement of fully automated airway segmentation on volumetric computed tomographic images using a 2.5 dimensional convolutional neural net. Med Image Anal  2019; 51: 13-20.
 [http://dx.doi.org/10.1016/j.media.2018.10.006] [PMID:  30388500]

[25]
Juarez AG, Selvan R, Saghir Z, de Bruijne M. A joint 3D UNet-graph neural network-based method for airway segmentation from chest CTs. International workshop on machine learning in medical imaging  583-91.

[26]
Qin Y, Chen M, Zheng H, et al. Airwaynet: A voxel-connectivity aware approach for accurate airway segmentation using convolutional neural networks. International Conference on Medical Image Computing and Computer-Assisted Intervention  212-20.
 [http://dx.doi.org/10.1007/978-3-030-32226-7_24]

[27]
Park J, Hwang J, Ryu J, et al. Deep learning based airway segmentation using key point prediction. Appl Sci (Basel)  2021; 11(8): 3501.
 [http://dx.doi.org/10.3390/app11083501]

[28]
Guo J, Fu R, Pan L, et al. Coarse-to-fine airway segmentation using multi information fusion network and CNN-based region growing. Comput Methods Programs Biomed  2022; 215: 106610.
 [http://dx.doi.org/10.1016/j.cmpb.2021.106610] [PMID:  35077902]

[29]
Oktay O, Schlemper J, Folgoc LL, et al. Attention u-net: Learning where to look for the pancreas. 2018.

[30]
Hernández A, Amigó JM. Attention mechanisms and their applications to complex systems. Entropy (Basel)  2021; 23(3): 283.
 [http://dx.doi.org/10.3390/e23030283] [PMID:  33652728]

[31]
Rudyanto RD, Kerkstra S, van Rikxoort EM, et al. Comparing algorithms for automated vessel segmentation in computed tomography scans of the lung: The VESSEL12 study. Med Image Anal  2014; 18(7): 1217-32.
 [http://dx.doi.org/10.1016/j.media.2014.07.003] [PMID:  25113321]

[32]
Ronneberger O, Fischer P, Brox T. U-net: Convolutional networks for biomedical image segmentation. In: International Conference on Medical image computing and computer-assisted intervention.  Springer, Cham 2015; pp. 234-41.

[33]
Zeng X, Zhang Z, Wang D. AdaMax online training for speech recognition. 2016.

[34]
Datta L. A survey on activation functions and their relation with xavier and he normal initialization. 2020.

Rights & Permissions Print Cite

Article Metrics

3

Journal Information

For Authors

For Editors

For Reviewers

Explore Articles

For Visitors

DOI https://dx.doi.org/10.2174/1573405618666220630151409	Print ISSN 1573-4056
Publisher Name Bentham Science Publisher	Online ISSN 1875-6603

Current Medical Imaging

A Deep Attention-based U-Net for Airways Segmentation in Computed Tomography Images

Abstract Play Pause

Graphical Abstract

Related Books

Abstract