Automatic segmentation of airway tree based on local intensity filter and machine learning technique in 3D chest CT volume
- 852 Downloads
Airway segmentation plays an important role in analyzing chest computed tomography (CT) volumes for computerized lung cancer detection, emphysema diagnosis and pre- and intra-operative bronchoscope navigation. However, obtaining a complete 3D airway tree structure from a CT volume is quite a challenging task. Several researchers have proposed automated airway segmentation algorithms basically based on region growing and machine learning techniques. However, these methods fail to detect the peripheral bronchial branches, which results in a large amount of leakage. This paper presents a novel approach for more accurate extraction of the complex airway tree.
This proposed segmentation method is composed of three steps. First, Hessian analysis is utilized to enhance the tube-like structure in CT volumes; then, an adaptive multiscale cavity enhancement filter is employed to detect the cavity-like structure with different radii. In the second step, support vector machine learning will be utilized to remove the false positive (FP) regions from the result obtained in the previous step. Finally, the graph-cut algorithm is used to refine the candidate voxels to form an integrated airway tree.
A test dataset including 50 standard-dose chest CT volumes was used for evaluating our proposed method. The average extraction rate was about 79.1 % with the significantly decreased FP rate.
A new method of airway segmentation based on local intensity structure and machine learning technique was developed. The method was shown to be feasible for airway segmentation in a computer-aided diagnosis system for a lung and bronchoscope guidance system.
KeywordsHessian matrix analysis Adaptive multiscale cavity enhancement filter Support vector machine Graph-cut
The authors thank our colleagues for suggestions and advice. Parts of this research were supported by the MEXT, the JSPS KAKENHI Grant Numbers 25242047, 26108006, 26560255, and the Kayamori Foundation of Informational Science Advancement.
Compliance with ethical standards
Conflict of interest
The authors declare that they have no conflict of interest.
All procedures performed in studies involving human participants were in accordance with the ethical standards of the institutional and/or national research committee and with the 1964 Helsinki Declaration and its later amendments or comparable ethical standards.
Informed consent was obtained from all individual participants included in the study.
- 1.World Health Organization (Feb 2015) Cancer, fact sheet N deg 297. http://www.who.int/mediacentre/factsheets/fs297/en/
- 6.Chen B, Kitasaka T, Honma H, Takabatake H, Mori M, Natori H, Mori K (2012) Automatic segmentation of pulmonary blood vessels and nodules based on local intensity structure analysis and surface propagation in 3D chest CT images. Int J Comput Assist Radiol Surg 7(3):465–482PubMedCrossRefGoogle Scholar
- 9.Lo P, Ginneken B, Reinhardt J, Yavarna T, Jong P, Irving B, Fetita C, Ortner M, Pinho R, Sijbers J, Feuerstein M, Fabijanska A, Bauer C, Beichel R, Mendoza C, Wiemker R, Lee J, Reeves A, Born R, Weinheimer O, Rikxoort E, Tschirren J, Mori K, Odry B, Naidich D, Hartmann I, Hoffman E, Prokop M, Pedersen J, Bruijne M (2012) Extraction of airways from CT (EXACT’09). IEEE Trans Med Imaging 31(11):2093–2107PubMedCrossRefGoogle Scholar
- 10.Mori K, Hasegawa J, Toriwaki J, Anno H, Kataba K (1995) Automated extraction and visualization of bronchus from 3D CT images of lung. Proc CVRMIed 95:542–548Google Scholar
- 13.Singh H, Crawford M, Curtin JP, Zwiggelaar R (2004) Automated 3D segmentation of the lung airway tree using gain-based region growing approach. In: MICCAI. Lecture notes in computer science, pp 975–982Google Scholar
- 14.Kitasaka T, Mori K, Hasegawa J, Toriwaki J (2002) A method for extraction of bronchus regions from 3D branch tracing and image sharpening for airway tree chest X-ray images by analyzing structural features of the bronchus. Forma 17:321–338Google Scholar
- 16.Feuerstein M, Kitasaka T, Mori K (2009) Adaptive branch tracing and image sharpening for airway tree extraction in 3-D chest CT. In: Proceeding of 2nd international workshop on pulmonary image analysis, pp 273–284Google Scholar
- 20.Yano H, Feuerstein M, Kitasaka T, Mori K (2009) Study on bronchus region extraction from 3D chest CT images using loca1 intensity structure analysis and CT value distribution feature. In: IEICE, MI2009-13, pp 69–74Google Scholar
- 21.Meng Q, Kitasaka T, Nimura Y, Oda M, Mori K (2015) A study on improvement of airway segmentation using hybrid method. In: The 3rd IAPR Asian conference on pattern recognition, pp 225–229Google Scholar
- 22.Meng Q, Kitsaka T, Nimura Y, Oda M, Mori K (2016) Accurate airway segmentation based on intensity structure analysis and graphcut. In: Proceedings of SPIE, 9784, SPIE medical imaging: computer-aided diagnosisGoogle Scholar
- 23.Pratt W (1991) Digital image processing, 2nd edn. Wiley, New YorkGoogle Scholar
- 26.Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering. Med Image Comput Comput Assist Interv (MICCAI) 1496:130–137Google Scholar
- 28.Li Q, Sone S, Doi K (2003) Selective enhancement filters for nodules, vessels, and airway walls in two and three-dimensional CT images. Med Phys 30:20–40Google Scholar
- 29.Hirano Y, Xu R, Tachibana R, Kido S (2011) A method for extracting airway tree by using a cavity enhancement filter. In: 4th international workshop on pulmonary image analysis, pp 91–99Google Scholar
- 31.Chang C, Lin CJ (2011) LIBSVM: a library for support vector machines. ACM Trans Intell Syst Technol (TIST) 2(3):27Google Scholar
- 33.Boykov Y, Kolmogorov V (2004) An experimental comparison of minexperimental comparison of minexperimental min-cutmax-flow algorithms for energy minimization in vision. IEEE Trans Pattern Anal Mach Intell 26(9):1124–1137Google Scholar
- 34.Ali AM, El-Baz AS, Farag AA (2007) A novel framework for accurate lung segmentation using graph cuts. In: 4th IEEE international symposium on biomedical imaging, pp 908–911Google Scholar