PET image segmentation using a Gaussian mixture model and Markov random fields

被引：23

作者：

Layer T. ^{[1
,2
]}

Blaickner M. ^{[2
]}

Knäusl B. ^{[3
]}

Georg D. ^{[3
]}

Neuwirth J. ^{[4
]}

Baum R.P. ^{[5
]}

Schuchardt C. ^{[5
]}

Wiessalla S. ^{[5
]}

Matz G. ^{[1
]}

机构：

[1] Institute of Telecommunications, Vienna University of Technology, Karlsplatz 13, Vienna

[2] Health & Environment Department, Austrian Institute of Technology, Donau-City-Strasse 1/2, Vienna

[3] Department of Radiation Oncology, Division of Medical Radiation Physics, Christian Doppler Laboratory for Medical Radiation Research for Radiation Oncology, Medical University of Vienna/AKH Vienna, Währinger Gürtel 18-20, Vienna

[4] Radiation Safety and Applications, Seibersdorf Labor GmbH, 2444 Seibersdorf, Seibersdorf

[5] THERANOSTICS Center for Molecular Radiotherapy and Molecular Imaging (PET/CT) ENETS Center of Excellence, Zentralklinik Bad Berka, Robert-Koch-Allee 9, 99437 Bad Berka, Bad Berka

来源：

EJNMMI Physics | / 2卷 / 1期

关键词：

Expectation maximization; Markov random field; Positron emission tomography; Radiotherapy; Tumor segmentation;

D O I：

10.1186/s40658-015-0110-7

中图分类号：

学科分类号：

摘要：

Background: Classification algorithms for positron emission tomography (PET) images support computational treatment planning in radiotherapy. Common clinical practice is based on manual delineation and fixed or iterative threshold methods, the latter of which requires regression curves dependent on many parameters. Methods: An improved statistical approach using a Gaussian mixture model (GMM) is proposed to obtain initial estimates of a target volume, followed by a correction step based on a Markov random field (MRF) and a Gibbs distribution to account for dependencies among neighboring voxels. In order to evaluate the proposed algorithm, phantom measurements of spherical and non-spherical objects with the smallest diameter being 8 mm were performed at signal-to-background ratios (SBRs) between 2.06 and 9.39. Additionally 68Ga-PET data from patients with lesions in the liver and lymph nodes were evaluated. Results: The proposed algorithm produces stable results for different reconstruction algorithms and different lesion shapes. Furthermore, it outperforms all threshold methods regarding detection rate, determines the spheres’ volumes more accurately than fixed threshold methods, and produces similar values as iterative thresholding. In a comparison with other statistical approaches, the algorithm performs equally well for larger volumes and even shows improvements for small volumes and SBRs. The comparison with experts’ manual delineations on the clinical data shows the same qualitative behavior as for the phantom measurements. Conclusions: In conclusion, a generic probabilistic approach that does not require data measured beforehand is presented whose performance, robustness, and swiftness make it a feasible choice for PET segmentation. © 2015, Layer et al.; licensee Springer.

引用

页码：1 / 15

页数：14

共 43 条

[31]

Pokric M., Thacker N.A., Scott M.L.J., Jackson A., Multidimensional medical image segmentation with partial voluming, Medical image computing and computer-assisted intervention, vol. 2208, (2001)

[32]

Moon T.K., The expectation-maximization algorithm, IEEE Signal Processing Mag., 13, pp. 47-60, (1996)

[33]

Fessler J.A., Hero A.O., Space-alternating generalized expectation-maximization algorithm, IEEE Trans Signal Process., 42, pp. 2664-2677, (1994)

[34]

Fessler J.A., Hero A.O., Penalized maximum-likelihood image reconstruction using space-alternating generalized EM algorithms, IEEE Trans Image Process., 4, pp. 1417-1429, (1995)

[35]

Dempster A.P., Laird N.M., Rubin D.B., Maximum likelihood from incomplete data via the EM algorithm, J Roy Stat Soc., 39, 1, pp. 1-38, (1977)

[36]

Kay S.M., Maximum likelihood estimation, Fundamentals of statistical signal processing, volume I: estimation theory, (1993)

[37]

Su K.H., Chen J.S., Lee J.S., Hu C.M., Chang C.W., Chou Y.H., Et al., Image segmentation and activity estimation for microPET 11C-raclopride images using an expectation-maximum algorithm with a mixture of Poisson distributions, Comput Med Imaging Graph., 35, pp. 417-426, (2011)

[38]

Hatt M., Cheze le Rest C., Turzo A., Roux C., Visvikis D., A fuzzy locally adaptive Bayesian segmentation approach for volume determination in PET, IEEE Trans Med Imag., 28, pp. 881-893, (2009)

[39]

Gribben H., Miller P., Wang H., Carson K., Hounsell A., Zatari A., Automated MAP-MRF EM labelling for volume determination in PET, 5th IEEE int symp biomedical imaging: from nano macro, (2008)

[40]

Dewalle-Vignion A.S., Betrouni N., Lopes R., Huglo D., Stute S., Vermandel M., A new method for volume segmentation of PET images, based on possibility theory, IEEE Trans Med Imag., 30, pp. 409-423, (2011)

← 1 2 3 4 5 →