Abstract
Objective
Recent studies have shown that three-dimensional (3D) visualization of lung cavities has distinct advantages over multiplanar computed tomographic (CT) images for surgical planning. A crucial step for achieving this 3D visualization is the automatic segmentation of lung lobes. This paper presents a watershed algorithm for segmenting lung lobes in clinical CT images so that the 3D visualization of lung lobes would be practical in clinical settings.
Materials and methods
The watershed algorithm uses a two-stage approach to automatically identify the lobar fissures (boundaries of the lung lobes): (a) adaptive fissure sweep to coarsely define fissure regions of the lobar fissures; and (b) watershed transform to refine the location and curvature of the fissures within the fissure regions.
Results
The algorithm’s feasibility was tested using six CT datasets. Compared to visual inspection, the watershed algorithm achieved an accuracy of 85.5–95.0, 88.2–92.3 and 100% for segmenting the left oblique, the right oblique, and the right horizontal fissures, respectively. The total computational time for both lungs was under 3 min.
Conclusion
We developed an autonomous algorithm for segmenting lung lobes. This algorithm provided promising potential for developing an automatic algorithm for segmenting lung lobes in clinical settings.
Similar content being viewed by others
References
Parkin DM, Bray F, Ferlay J, Pisani P (2005) Global cancer statistics, 2002. CA Cancer J Clin 55: 74–108
Wigmore SJ, Redhead DN et al (2001) Virtual hepatic resection using three-dimensional reconstruction of helical computed tomography angioportograms. Ann Surg 233: 221–226
Lee SW, Shinohara H et al (2003) Preoperative simulation of vascular anatomy by three-dimensional computed tomography imaging in laparoscopic gastric cancer surgery. J Am Coll Surg 197: 927–936
Hu Y, Malthaner RA (2007) The feasibility of three-dimensional displays of the thorax for preoperative planning in the surgical treatment of lung cancer. Eur Cardio Thorac Surg 31: 506–511
Kuhnigk J-M, Hahn HK et al (2003) Lung lobe segmentation by anatomy-guided 3-D watershed transform. Proc SPIE Med Imag 5032: 1482–1490
Zhang L, Hoffman EA, Reinhardt JM (2006) Atlas-driven lung lobe segmentation in volumetric X-ray CT images. IEEE Trans Med Imag 25: 1–16
Sluimer I, Prokop M, Ginneken B (2005) Toward automated segmentation of the pathological lung in CT. IEEE Trans Med Imag 24: 1025–1038
Zhou X, Kobayashi S, Hayashi T et al (2003) Lung structure recognition: a further study of thoracic organ recognitions based on CT images. Int Congr Series 1256: 1025–1030
Shojaii R, Alirezaie J, Babyn P (2005) Automatic lung segmentation in CT images using watershed transform. Intl Conf IEEE ICIP 2: 1270–1273
McAndrew A (2004) Introduction to Digital Image Processing with Matlab. Thomson Course Technology, Chicago
Vincent L, Soille P (1991) Watersheds in digital spaces: an efficient algorithm based on immersion simulations. IEEE Trans Pattern Anal Mach Intell 13: 583–598
Rangayyan RM (2005) Biomedical image analysis. CRC Press, Boca Raton
Bezier PE (1972) Employ des machines a commande numerique. Mason et Cie, Paris, 1970 (translated by Forrest AR, Pankhurst AF as Bezier PE. Numerical control—Mathematics and applications. Wiley, London)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Wei, Q., Hu, Y., MacGregor, J.H. et al. Segmentation of lung lobes in clinical CT images. Int J CARS 3, 151–163 (2008). https://doi.org/10.1007/s11548-008-0153-5
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11548-008-0153-5