A review on segmentation of positron emission tomography images - PubMed 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
Review
. 2014 Jul:50:76-96.
doi: 10.1016/j.compbiomed.2014.04.014. Epub 2014 Apr 28.

A review on segmentation of positron emission tomography images

Brent Foster  1 , Ulas Bagci  2 , Awais Mansoor  1 , Ziyue Xu  1 , Daniel J Mollura  1
Affiliations
Review

A review on segmentation of positron emission tomography images

Brent Foster et al. Comput Biol Med. 2014 Jul.

Abstract

Positron Emission Tomography (PET), a non-invasive functional imaging method at the molecular level, images the distribution of biologically targeted radiotracers with high sensitivity. PET imaging provides detailed quantitative information about many diseases and is often used to evaluate inflammation, infection, and cancer by detecting emitted photons from a radiotracer localized to abnormal cells. In order to differentiate abnormal tissue from surrounding areas in PET images, image segmentation methods play a vital role; therefore, accurate image segmentation is often necessary for proper disease detection, diagnosis, treatment planning, and follow-ups. In this review paper, we present state-of-the-art PET image segmentation methods, as well as the recent advances in image segmentation techniques. In order to make this manuscript self-contained, we also briefly explain the fundamentals of PET imaging, the challenges of diagnostic PET image analysis, and the effects of these challenges on the segmentation results.

Keywords: Image segmentation; MRI-PET; PET; PET-CT; Review; SUV; Thresholding.

PubMed Disclaimer

Figures

Figure 1
Figure 1
A summary of PET technology used in the U.S is shown in (a) [10]. (b) gives the breakdown of clinical PET and PET-CT studies in 2011 by the branch of medicine. (c) demonstrates 2010 PET technology used in the U.S. for oncology applications, in which PET has been used for mostly staging and follow-up therapy.
Figure 2
Figure 2
Analysis of publications pertaining to PET image segmentation methods and their applications is shown (from 1983-2012). Journal and conference publications are shown in (a). A comparison of modality dependent image segmentation methods published for MRI, CT, and PET are shown in (b). Further categorization on the published papers has been conducted in (c) and (d) from 1984 to 2012 and from 2007 to 2012, respectively.
Figure 3
Figure 3
An overview of the categories of PET segmentation methods: Manual segmentation, Thresholding-based, Region-based, Stochastic and Learning-based, Boundary Based, and Joint segmentation methods.
Figure 4
Figure 4
An overview of intensity-based segmentation methods for PET images.
Figure 5
Figure 5
Iterative thresholding method for finding optimal thresholding value.
Figure 6
Figure 6
The segmentation result at each iteration using the ITM is shown.
Figure 7
Figure 7
An overview of the Stochastic and learning-based segmentation methods.
Figure 8
Figure 8
Left: A representative slice (segmented to remove non-lung regions) showing focal radiotracer uptake in a small animal model while Right: demonstrates multi-focal/diffuse uptake patterns in a rabbit model infected with tuberculosis (5 weeks). Most PET segmentation techniques focus on segmenting the focal uptakes while ignoring the diffuse uptakes that occur in infectious pulmonary disease.
Figure 9
Figure 9
An overview of the region-based segmentation methods.
Figure 10
Figure 10
The homogeneity metric for (a), (b) = 0.1 and (c), (d) = 0.3. The black outline in the images is the gold standard while the blue line is found from the region grown algorithm. The blue dot represents the location of the user defined seed.
Figure 11
Figure 11
An overview of the boundary-based segmentation methods.
Figure 12
Figure 12
Here is an example of a segmentation that incorporates anatomical and functional information from multi-modalities (PET and CT). The original images are shown on the left while a zoom in view showing the segmentation (using the information only from the respective image) is provided on the right. The resulting co-segmentation is in the middle image on the right in white.
See this image and copyright information in PMC

Similar articles

See all similar articles

Cited by

See all "Cited by" articles

References

    1. Seute T, Leffers P, ten Velde G, Twijnstra A. Detection of brain metastases from small cell lung cancer. Cancer. 2008;112(8):1827–1834. - PubMed
    1. MacManus M, Nestle U, Rosenzweig K, Carrio I, Messa C, Belohlavek O, Danna M, Inoue T, Deniaud-Alexandre E, Schipani S, et al. Use of pet and pet/ct for radiation therapy planning: Iaea expert report 2006–2007. Radiotherapy and oncology. 2009;91(1):85–94. - PubMed
    1. Basu S, Kwee T, Surti S, Akin E, Yoo D, Alavi A. Fundamentals of pet and pet/ct imaging. Annals of the New York Academy of Sciences. 2011;1228(1):1–18. - PubMed
    1. Lardinois D, Weder W, Hany T, Kamel E, Korom S, Seifert B, von Schulthess G, Steinert H. Staging of non–small-cell lung cancer with integrated positron-emission tomography and computed tomography. New England Journal of Medicine. 2003;348(25):2500–2507. - PubMed
    1. Kostakoglu L, Agress H, Jr, Goldsmith S. Clinical role of fdg pet in evaluation of cancer patients. Radiographics. 2003;23(2):315–340. - PubMed

Publication types

MeSH terms

Substances

LinkOut - more resources