Publication Detail Page

S. Ukil. Anatomy-guided lung lobe segmentation and fissure analysis in X-ray CT images. PhD thesis, The University of Iowa, Iowa City, IA, 2006.

Abstract: The human lungs are divided into five distinct anatomic compartments called the lobes, which are separated by the pulmonary fissures. Accurate identication of the fissures is of increasing importance in the early detection of pathologies, and in the regional functional analysis of the lungs. The large volume of thoracic CT data make it necessary to have reliable computer-based methods for the identication of the fissures. We have a developed an automatic method for the segmentation and analysis of the fissures, based on the anatomical information provided by the airway and vascular trees. This information is used to provide an initial approximation to the fissures, using a watershed transform on a distance map of the vasculature. In a further refnement step, this estimate is used to construct a region of interest (ROI) encompassing the fissures. The ROI is enhanced using a ridgeness measure, which is followed by a 3-D graph search to find the optimal surface within the ROI. The method has been tested on 12 normal subjects, using 4 different sets of scans. The first pair consisted of TLC scans reconstructed using the B/B30 and D/B50 kernels. The second pair consisted of FRC scans for the same pair of kernels. The results for all 4 sets were compared with manual tracings. The mean RMS error for all images, over all fissures, was less than 2.70 mm. The method was also validated for 17 subjects with varying degrees of emphysema, and the mean RMS error over all fissures was less than 2.04 mm. For low-dose scans, we compared the results with corresponding results at normal dose, and a mean RMS error of 1.29 mm was observed. We have also developed an automatic method to detect and analyze incomplete fissures, using a segmentation of a projection of the optimal surface computed by the graph search. The detected incomplete fissure is used to extrapolate and complete the fissure, from which an index of incompleteness of the fissure is computed. A test for repeatability of the incompleteness measure over repeat scans from the same subject showed a high level of agreement between the repeated values.

Citation: BibTeX format Endnote format

Keywords: lobes segmentation

Other publications by: S. Ukil

Related journal papers:

L. Zhang, E. A. Hoffman, and J. M. Reinhardt. Lung lobe segmentation in volumetric X-ray CT images. IEEE Trans. Medical Imaging, vol. 25, no. 1, pp. 1-16, 2006. (details)
S. Ukil and J. M. Reinhardt. Anatomy-guided lung lobar surface detection in X-ray CT images. IEEE Trans. Medical Imaging, vol. 28, no. 2, pp. 202-214, 2009. (details)
J. M. Reinhardt and W. E. Higgins. Paradigm for Shape-Based Image Analysis. Optical Engineering, vol. 37, no. 2, pp. 570-581, 1998. (details)
J. M. Reinhardt, A. J. Wang, T. P. Weldon, and W. E. Higgins. Cue-Based Segmentation of 4D Cardiac Image Sequences. Comp. Vision and Image Understanding, vol. 77, no. 2, pp. 251-262, 2000. (details)
S. Hu, E. A. Hoffman, and J. M. Reinhardt. Automatic lung segmentation for accurate quantitation of volumetric X-ray CT images. IEEE Trans. Medical Imaging, vol. 20, no. 6, pp. 490-498, 2001. (details)

Related conference papers:

L. Zhang and J. M. Reinhardt. Detection of Lung Lobar Fissures using Fuzzy Logic. In Proc. SPIE Conf. Medical Imaging, vol. 3660, pp. 188-199, 1999. (details)
L. Zhang, E. A. Hoffman, and J. M. Reinhardt. Lung lobar segmentation by graph search with 3D shape constraints. In C.-T. Chen and A. V. Clough, eds., Proc. SPIE Conf. Medical Imaging, vol. 4321, pp. 204-215, San Diego, CA, 2001. (details)
L. Zhang, E. A. Hoffman, and J. M. Reinhardt. Atlas-Driven Lung Lobe Segmentation in Volumetric X-ray CT Images. In M. Sonka and J. M. Fitzpatrick, eds., Proc. SPIE Conf. Medical Imaging, vol. 5032, pp. 309-319, San Diego, CA, 2003. (details)
S. Ukil, E. A. Hoffman, and J. M. Reinhardt. Automatic lung lobe segmentation in X-ray CT images by 3D watershed transform using anatomic information from the segmented airway tree. In J. M. Fitzpatrick and J. M. Reinhardt, eds., Proc. SPIE Conf. Medical Imaging, vol. 5747, pp. 556-567, San Diego, CA, 2005. (details)
S. Ukil, M. Sonka, and J. M. Reinhardt. Automatic segmentation of pulmonary fissures in X-ray CT images using anatomic guidance. In J. M. Reinhardt and J. P. Pluim, eds., Proc. SPIE Conf. Medical Imaging, vol. 6144, pp. 213-223, San Diego, CA, 2006. (details)

Related theses:

L. Zhang. Atlas-driven lung lobe segmentation in volumetric X-ray CT images. PhD thesis, The University of Iowa, Iowa City, IA, 2002. (details)
D. Aykac. Segmentation and analysis of the human airway tree from 3D X-ray CT images. MS thesis, The University of Iowa, Iowa City, IA, 2000. (details)