Abstract
Due to the low contrast and the partial volume effects, providing an accurate and in vivo analysis for pulmonary vascular trees from low dose CT scans is a challenging task. This paper proposes an automatic integration segmentation approach for the vascular trees in low dose CT scans. It consists of the following steps: firstly, lung volumes are acquired by the knowledge based method from the CT scans, and then the data are smoothed by the 3D Gaussian filter; secondly, two or three seeds are gotten by the adaptive 2D segmentation and the maximum area selecting from different position scans; thirdly, each seed as the start voxel is inputted for a quick multi-seeds 3D region growing to get vascular trees; finally, the trees are refined by the smooth filter. Through skeleton analyzing for the vascular trees, the results show that the proposed method can provide much better and lower level vascular branches.
Similar content being viewed by others
References
Graham, M. W., Gibbs, J. D., Cornish, D. C., et al. (2010). Robust 3-D vascular tree segmentation for image-guided peripheral bronchoscopy. IEEE Transactions on Medical Imaging, 29(4), 982–998.
Aykac, D., Hoffman, E. A., McLennan, G., et al. (2003). Segmentation and analysis of the human vascular tree from three-dimensional X-ray CT images. IEEE Transactions on Medical Imaging, 22(84), 940–950.
Tschirren, J., Hoffman, E. A., McLennan, G., et al. (2005). Intrathoracic vascular trees: Segmentation and vascular morphology analysis from low-dose CT scans. IEEE Transactions on Medical Imaging, 24(12), 1529–1539.
Liu, X., Chen, D. Z., & Tawhai, M. H. (2013). Optimal graph search based segmentation of vascular tree double surfaces across bifurcations. IEEE Transactions on Medical Imaging, 32(3), 493–510.
Sluimer, I., Schilham, A., & Prokop, M. (2006). Computer analysis of computed tomography scans of the lung: A survey. IEEE Transactions on Medical Imaging, 25(4), 385–405.
Zhu, Y., Tan, Y., & Hua, Y. (2012). Automatic segmentation of ground-glass opacities in lung CT images by using Markov random field-based algorithms. Journal of Digital Imaging, 25(3), 409–422.
Ye, X., Lin, X., & Dehmeshki, J. (2009). Shape-based computer-aided detection of lung nodules in thoracic CT images. IEEE Transactions on Bio-Medical Engineering, 56(7), 1810–1820.
Fetita, C., Brillet, P., & Preteux, F. (2009). Morpho-geometrical approach for 3D segmentation of pulmonary vascular tree in multislice CT. Proceedings SPIE Medical Imaging, 7259, 1–12.
Korfiatis, P. D., Karahaliou, A. N., & Kazantzi, A. D. (2010). Texture-based identification and characterization of interstitial pneumonia patterns. IEEE Transactions on Information Technology B, 14(3), 675–680.
Paulinas, M., Miniotas, D., Meilūnas, M., et al. (2008). An algorithm for segmentation of blood vessels in images. Electronics and Electrical Engineering, 3(83), 25–28.
Nomura, Y., Nemoto, M., Masutani, Y., et al. (2014). Reduction of false positives at vessel bifurcations in computerized detection of lung nodules. Journal of Biomedical Graphics and Computing, 4(3), 36–46.
Fabijańska, A. (2015). Segmentation of pulmonary vascular tree from 3D CT thorax scans. Biocybernetics and Biomedical Engineering, 35(2), 106–119.
Orkisz, M., Hernández Hoyos, M., et al. (2014). Segmentation of the pulmonary vascular trees in 3D CT images using variational region-growing. IRBM, 35(1), 11–19.
Kaftan, J., & Aach, T. (2011). Pulmonary vessel segmentation for multislice CT data: Methods and applications. In J. Suri (Ed.), Lung imaging and computer aided diagnosis (pp. 189–219). Boca Raton: CRC.
Shikata, H., McLennan, G., Hoffman, E., et al. (2009). Segmentation of pulmonary vascular trees from thoracic 3D CT images. International Journal of Biomedical Imaging, 2009, 107. doi:10.1155/2009/636240.
van Dongen, E., & van Ginneken, B. (2010). Automatic segmentation of pulmonary vasculature in thoracic CT scans with local thresholding and airway wall removal. In 2010 IEEE international symposium on biomedical imaging: From nano to macro (pp. 668–671).
Xiao, C., Staring, M., Shamonin, D., et al. (2011). A strain energy filter for 3D vessel enhancement with application to pulmonary CT images. Medical Image Analysis, 15(1), 112–124.
Zhou, C., Chan, H. P., Kuriakose, J. W., et al. (2011). Computerized detection of pulmonary embolism in computed tomographic pulmonary angiography (CTPA): Improvement of vessel segmentation. In Proceedings of SPIE, medical imaging: Computer-aided diagnosis, Lake Buena Vista, FL, USA (pp. 79630L-1–79630L-9).
Lo, P. V., Ginneken, B. D., & Bruijne, M. (2010). Vessel tree extraction using locally optimal paths. In: IEEE ISBI (pp. 680–683).
You, S., Bas, E., & Erdogmus, D. (2011). Extraction of samples from airway and vessel trees. In 33rd Annual international conference of the IEEE EMBS(2011), Boston, Massachusetts, USA (pp. 5157–5160).
Saha, P. K., Gao, Z., & Alford, S. K. (2010). Topomorphologic separation of fused isointensity objects via multiscale opening: Separating arteries and veins in 3-D pulmonary CT. IEEE Transactions on Medical Imaging, 29(3), 840–851.
Korfiatis, P., Karahaliou, A., & Costaridou, L. (2009). Automated vessel tree segmentation: Challenges in computer aided quantification of diffuse parenchyma lung Diseases. In: IEEE ITAB, Larnaca, Cyprus.
Lai, J., & Wei, Q. (2014). Automatic lung fields segmentation in low dose CT scans using morphological operation and anatomical information. Bio-Medical Materials and Engineering, 24(1), 335–340.
Desbrun, M., et al. (1999). Implicit faring of irregular meshes using diffusion and curvature flow. In Computer graphics proceedings, annual conference series. ACM SIGGRAPH, Los Angeles, (pp. 317–324).
Acknowledgments
This research about the lung problems is supported by the Research Projects of ChongQing under Grant Nos. cstc2014jcyjA10051, cstc2014jcyjA40043 and KJ1400407, Foundation of CQUPT (No. A2013-21) in China. This work is supported by the Program for National Natural Science Foundation of China (Nos. 61272195, 61472055 and U1401252), Chongqing Frontier and Applied Basic Research Program of Outstanding Youth Fund (cstc2014jcyjjq40001) and Project of China Scholarship Council (CSC NO. 201607845006) also. Authors thank the university of Cornell for the provided chest CT dataset and the Student Research Training Program of CQUPT(A2013-52).
Author information
Authors and Affiliations
Corresponding author
Additional information
This article is part of the Topical Collection on 4D Medical Image Segmentation.
Rights and permissions
About this article
Cite this article
Lai, J., Huang, Y., Wang, Y. et al. Three-Dimensions Segmentation of Pulmonary Vascular Trees for Low Dose CT Scans. Sens Imaging 17, 13 (2016). https://doi.org/10.1007/s11220-016-0138-3
Received:
Revised:
Published:
DOI: https://doi.org/10.1007/s11220-016-0138-3