Peripheral bronchial identification on chest CT using unsupervised machine learning
To automatically identify small- to medium-diameter bronchial segments distributed throughout the lungs.
We segment the peripheral pulmonary vascular tree and construct cross-sectional images perpendicular to the lung vasculature. The bronchi running with pulmonary arteries appear as concentric rings, and potential center points that lie within the bronchi are identified by looking for circles (using the circular Hough transform) and rings (using a novel variable ring filter). The number of candidate bronchial center points are further reduced by using agglomerative hierarchical clustering applied to the points represented with 18 features pertaining to their 3D position, orientation and appearance of the surrounding cross-sectional image. Resulting clusters corresponded to bronchial segments. Parameters of the algorithm are varied and applied to two experimental data sets to find the best values for bronchial identification. The optimized algorithm was then applied to a further 21 CT studies obtained using two different CT vendors.
The parameters that result in the most number of true positive bronchial center points with > 95% precision are a tolerance of 0.15 for the hierarchical clustering algorithm and a threshold of 75 HU with 10 spokes for the ring filter. Overall, the performance on all 21 test data sets from CT scans from both vendors demonstrates a mean number of 563 bronchial points detected per CT study, with a mean precision of 96%. The detected points across this group of test data sets are relatively uniformly distributed spatially with respect to spherical coordinates with the origin at the center of the test imaging data sets.
We have constructed a robust algorithm for automatic detection of small- to medium-diameter bronchial segments throughout the lungs using a combination of knowledge-based approaches and unsupervised machine learning. It appears robust over two different CT vendors with similar acquisition parameters.
KeywordsLung Machine learning CAD Computed tomography
We would like to acknowledge and thank the Commonwealth Government of Australia for the support of Daniel Moses during his Ph.D. through an Australian Government Research Training Program Scholarship.
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. For this type of study, formal consent is not required. This article does not contain identified patient data.
- 5.Webb NLMu WR, Naidich DP (2001) High-resolution CT of the lung, 3rd edn. Lippincott Williams & Wilkins, PhiladelphiaGoogle Scholar
- 6.Hartman TE, Primack SL, Lee KS, Swensen SJ, Muller NL (1994) CT of bronchial and bronchiolar diseases. Radiographics 14(5):991–1003. https://doi.org/10.1148/radiographics.14.5.7991828 CrossRefPubMedGoogle Scholar
- 8.Feuerstein M, Kitasaka T, Mori K (2009) Adaptive branch tracing and image sharpening for airway tree extraction in 3-D chest CT. In: Second international workshop of pulmonary imaging analysis EXACT09Google Scholar
- 9.Lo P, Ginneken Bv, Reinhardt JM, Bruijne Md (2009) Extraction of airways from CT. In: Second international workshop of pulmonary imaging analysis EXACT 09Google Scholar
- 11.Kitasaka T, Yano H, Feuerstein M, Mori K (2010) Bronchial region extraction from 3D chest CT image by voxel classification based on local intensity structure. In: Third international workshop on pulmonary image analysis, p 21Google Scholar
- 12.Xu Z, Bagci U, Foster B, Mollura DJ (2013) A hybrid multi-scale approach to automatic airway tree segmentation from CT scans. In: 10th international symposium on biomedical imaging: from nano to macro, pp 1308–1311Google Scholar
- 14.Estepar RS, Ross JC, Kindlmann GL, Diaz A, Okajima Y, Kikinis R, Westin CF, Silverman EK, Washko GG (2012) Automatic airway analysis for genome-wide association studies in COPD. Proc IEEE Int Symp Biomed Imaging. https://doi.org/10.1109/ISBI.2012.6235848
- 17.Frangi AF, Niessen WJ, Vincken KL, Viergever MA (1998) Multiscale vessel enhancement filtering. In: Medical image computing and computer-assisted intervention—MICCAI’98. In: First international conference. Proceedings, 11–13 Oct. 1998, Berlin, Germany. Springer, pp 130-137Google Scholar
- 18.Manniesing R, Niessen W (2005) Multiscale vessel enhancing diffusion in CT angiography noise filtering. In: Information processing in medical imaging. 19th International conference, IPMI 2005. Proceedings, 10–15 July 2005, Berlin, Germany, 2005. Information processing in medical imaging. 19th International conference, IPMI 2005. Proceedings (Lecture Notes in Computer Science vol 3565). Springer, pp 138–149Google Scholar
- 22.Hastie T, Tibshirani R, Friedman J (2003) The elements of statistical learning: data mining, inference, and prediction. The elements of statistical learning. Springer, BerlinGoogle Scholar
- 26.Levitzky MG (2013) Pulmonary physiology, 8th edn. McGraw-Hill Education, New YorkGoogle Scholar