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
. 2013 Mar 1;46(3):692-702.
doi: 10.1016/j.patcog.2012.10.005.

Automated Delineation of Lung Tumors from CT Images Using a Single Click Ensemble Segmentation Approach

Yuhua Gu  1 , Virendra Kumar, Lawrence O Hall, Dmitry B Goldgof, Ching-Yen Li, René Korn, Claus Bendtsen, Emmanuel Rios Velazquez, Andre Dekker, Hugo Aerts, Philippe Lambin, Xiuli Li, Jie Tian, Robert A Gatenby, Robert J Gillies
Affiliations

Automated Delineation of Lung Tumors from CT Images Using a Single Click Ensemble Segmentation Approach

Yuhua Gu et al. Pattern Recognit. .

Abstract

A single click ensemble segmentation (SCES) approach based on an existing "Click&Grow" algorithm is presented. The SCES approach requires only one operator selected seed point as compared with multiple operator inputs, which are typically needed. This facilitates processing large numbers of cases. Evaluation on a set of 129 CT lung tumor images using a similarity index (SI) was done. The average SI is above 93% using 20 different start seeds, showing stability. The average SI for 2 different readers was 79.53%. We then compared the SCES algorithm with the two readers, the level set algorithm and the skeleton graph cut algorithm obtaining an average SI of 78.29%, 77.72%, 63.77% and 63.76% respectively. We can conclude that the newly developed automatic lung lesion segmentation algorithm is stable, accurate and automated.

Keywords: CT; Delineation; Ensemble Segmentation; Image Features; Lesion; Lung Tumor; Region growing.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Lung fields (left and right) were segmented after preprocessing.
Figure 2
Figure 2
Schematic illustration of the flow of the single click ensemble segmentation method.
Figure 3
Figure 3
Illustration of the workflow to find the tumor core process.
Figure 4
Figure 4
Expand tumor region: locate 24 secondary seed points: child Seed point selection from the existing tumor region.
Figure 5
Figure 5
Number of interactions required for each method (R1=reader1, R2=reader2, SCES=single click ensemble segmentation, LS=level set algorithm, SGC=skeleton graph cut algorithm).
Figure 6
Figure 6
Similarity Index of SCES algorithm for 129 cases (20 different start seed points) from the Moffitt Cancer Center.
Figure 7
Figure 7
Representative segmentation results (P13, slices 79–85) (a) Reader 1 (b) Reader 2 (c) SCES (d) Level Set (e) Skeleton Graph Cut.
Figure 8
Figure 8
Representative segmentation results (P10, slices 46–50) (a) Reader 1 (b) Reader 2 (c) SCES (d) Level Set (e) Skeleton Graph Cut.
Figure 9
Figure 9
Representative segmentation results (P14, slices 44–54) (a) Reader 1 (b) Reader 2 (c) SCES (d) Level Set (e) Skeleton Graph Cut.
Figure 10
Figure 10
Single click ensemble segmentation result with a different start seed point (a and b) on part-solid tumors.
See this image and copyright information in PMC

References

    1. Johnson DH, Blot WJ, Carbone DP. Cancer of the lung: Non-small cell lung cancer and small cell lung cancer. In: Abeloff MD, Armitage JO, Niederbuber JE, Kastan MB, McKenna WG, editors. Abeloff’s clinical oncology. Churchill Livingstone/Elsevier; Philadelphia: 2008.
    1. Gillies RJ, Anderson AR, Gatenby RA, Morse DL. The biology underlying molecular imaging in oncology: from genome to anatome and back again. Clin Radiol. 2010;65:517–521. - PMC - PubMed
    1. Rexilius J, Hahn HK, Schluter M, Bourquain H, Peitgen HO. Evaluation of accuracy in MS lesion volumetry using realistic lesion phantoms. Acad Radiol. 2005;12:17–24. - PubMed
    1. Tai P, Van Dyk J, Yu E, Battista J, Stitt L, Coad T. Variability of target volume delineation in cervical esophageal cancer. Int J Radiat Oncol Biol Phys. 1998;42:277–288. - PubMed
    1. Cooper JS, Mukherji SK, Toledano AY, Beldon C, Schmalfuss IM, Amdur R, Sailer S, Loevner LA, Kousouboris P, Ang KK, Cormack J, Sicks J. An evaluation of the variability of tumor-shape definition derived by experienced observers from CT images of supraglottic carcinomas (ACRIN protocol 6658) Int J Radiat Oncol Biol Phys. 2007;67:972–975. - PMC - PubMed