Skip to main page content
U.S. flag

An official website of the United States government

Dot gov

The .gov means it’s official.
Federal government websites often end in .gov or .mil. Before sharing sensitive information, make sure you’re on a federal government site.

Https

The site is secure.
The https:// ensures that you are connecting to the official website and that any information you provide is encrypted and transmitted securely.

Access keys NCBI Homepage MyNCBI Homepage Main Content Main Navigation
. 2010 Dec;37(12):6338-46.
doi: 10.1118/1.3515459.

Combining registration and active shape models for the automatic segmentation of the lymph node regions in head and neck CT images

Antong Chen  1 , Matthew A Deeley, Kenneth J Niermann, Luigi Moretti, Benoit M Dawant
Affiliations

Combining registration and active shape models for the automatic segmentation of the lymph node regions in head and neck CT images

Antong Chen et al. Med Phys. 2010 Dec.

Abstract

Purpose: Intensity-modulated radiation therapy (IMRT) is the state of the art technique for head and neck cancer treatment. It requires precise delineation of the target to be treated and structures to be spared, which is currently done manually. The process is a time-consuming task of which the delineation of lymph node regions is often the longest step. Atlas-based delineation has been proposed as an alternative, but, in the authors' experience, this approach is not accurate enough for routine clinical use. Here, the authors improve atlas-based segmentation results obtained for level II-IV lymph node regions using an active shape model (ASM) approach.

Methods: An average image volume was first created from a set of head and neck patient images with minimally enlarged nodes. The average image volume was then registered using affine, global, and local nonrigid transformations to the other volumes to establish a correspondence between surface points in the atlas and surface points in each of the other volumes. Once the correspondence was established, the ASMs were created for each node level. The models were then used to first constrain the results obtained with an atlas-based approach and then to iteratively refine the solution.

Results: The method was evaluated through a leave-one-out experiment. The ASM- and atlas-based segmentations were compared to manual delineations via the Dice similarity coefficient (DSC) for volume overlap and the Euclidean distance between manual and automatic 3D surfaces. The mean DSC value obtained with the ASM-based approach is 10.7% higher than with the atlas-based approach; the mean and median surface errors were decreased by 13.6% and 12.0%, respectively.

Conclusions: The ASM approach is effective in reducing segmentation errors in areas of low CT contrast where purely atlas-based methods are challenged. Statistical analysis shows that the improvements brought by this approach are significant.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Flow charts illustrating the process used to register the training images and the average image volume. Panel (a): Full scale image. Panel (b): Registration in the bounding box containing the nodes.
Figure 2
Figure 2
Flow charts illustrating the process used for the construction of the ASM using transformations obtained from registrations. Panel (a): Creation of the mask in the average volume. Panel (b): Establishing point correspondence to create the ASM.
Figure 3
Figure 3
Search for the point on the search vector with the best fit to the gray-level model. The entire search vector consists of M candidates points. At each candidate point on the search vector, a profile of length N is calculated. These profiles are compared to analogous profiles in the training images.
Figure 4
Figure 4
Cumulative distributions for the surface errors for each volume, with the x axis showing a distance error and the y axis showing the percentage of points for which the error is smaller than this distance.
Figure 5
Figure 5
2D contours for the manual, atlas-based, and ASM-based segmentations for patients 2, 5, 8, 10, and 15. Shown from the left to the right are contours in level II–IV regions; the manual contour is in green, the atlas-based in yellow, and the ASM-based in red.
See this image and copyright information in PMC

References

    1. Chao K. S. et al., “Reduce in variation and improve efficiency of target volume delineation by a computer-assisted system using a deformable image registration approach,” Int. J. Radiat. Oncol., Biol., Phys. IOBPD3 68, 1512–1521 (2007).10.1016/j.ijrobp.2007.04.037 - DOI - PubMed
    1. Commowick O., Grégoire V., and Malandain G., “Atlas-based delineation of lymph node levels in head and neck computed tomography images,” Radiother. Oncol. RAONDT 87, 281–289 (2008).10.1016/j.radonc.2008.01.018 - DOI - PubMed
    1. Commowick O., Warfield S. K., and Malandain G., “Using Frankenstein’s creature paradigm to build a patient specific atlas,” Proceedings of the 12th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI ‘09), Vol. 5762, Pt. II, pp. 993–1000, September 2009. (unpublished). - PMC - PubMed
    1. Gorthi S., Duay V., Houhou N., Cuadra M. B., Schick U., Becker M., Allal A. S., and Thiran J. P., “Segmentation of head and neck lymph node regions for radiotherapy planning using active contour-based atlas registration,” IEEE J. Sel. Top. Signal Process. IJSTGY 3, 135–147 (2009).10.1109/JSTSP.2008.2011104 - DOI
    1. Cootes T. F., Taylor C. J., Cooper C. H., and Graham J., “Active shape models-their training and application,” Comput. Vis. Image Underst. CVIUF4 61, 38–59 (1995).10.1006/cviu.1995.1004 - DOI

Publication types

MeSH terms