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
. 2003 Dec;10(12):1341-8.
doi: 10.1016/s1076-6332(03)00506-3.

Automatic brain tumor segmentation by subject specific modification of atlas priors

Marcel Prastawa  1 , Elizabeth Bullitt, Nathan Moon, Koen Van Leemput, Guido Gerig
Affiliations

Automatic brain tumor segmentation by subject specific modification of atlas priors

Marcel Prastawa et al. Acad Radiol. 2003 Dec.

Abstract

Rationale and objectives: Manual segmentation of brain tumors from magnetic resonance images is a challenging and time-consuming task. An automated system has been developed for brain tumor segmentation that will provide objective, reproducible segmentations that are close to the manual results. Additionally, the method segments white matter, grey matter, cerebrospinal fluid, and edema. The segmentation of pathology and healthy structures is crucial for surgical planning and intervention.

Materials and methods: The method performs the segmentation of a registered set of magnetic resonance images using an expectation-maximization scheme. The segmentation is guided by a spatial probabilistic atlas that contains expert prior knowledge about brain structures. This atlas is modified with the subject-specific brain tumor prior that is computed based on contrast enhancement.

Results: Five cases with different types of tumors are selected for evaluation. The results obtained from the automatic segmentation program are compared with results from manual and semi-automated methods. The automated method yields results that have surface distances at roughly 1-4 mm compared with the manual results.

Conclusion: The automated method can be applied to different types of tumors. Although its performance is below that of the semi-automated method, it has the advantage of requiring no user supervision.

PubMed Disclaimer

Figures

Figure 1
Figure 1
Gadolinium contrast enhanced T1-weighted MR image (sagittal view) and the manual tumor segmentation result. Please note the “striping” effect due to segmenting the tumor slice-by-slice in axial direction (Tumor031 data).
Figure 2
Figure 2
The ICBM digital brain atlas. From left to right: white matter probabilities, grey matter probabilities, csf probabilities, and the T1 template.
Figure 3
Figure 3
Computation of the difference image from registered T1 post-contrast and pre-contrast images. From left to right: T1 post-contrast, T1 pre-contrast, and the difference image with tumor that appears bright (Tumor020 data).
Figure 4
Figure 4
Left: The T1 post-contrast and pre-contrast difference image histogram and the fitted model. Right: The three distributions that compose the histogram model.
Figure 5
Figure 5
The gamma posterior probability function computed from the T1 post-contrast and pre-contrast difference image histogram.
Figure 6
Figure 6
Left: The tumor spatial prior probabilities generated from the difference image. Right: The tumor prior after enforcing the smoothness constraint.
Figure 7
Figure 7
The spatial prior probability maps generated for Tumor020. From left to right: white matter, grey matter, csf, tumor, and edema.
Figure 8
Figure 8
Top left: T1-weighted image. Top middle: T2-weighted image. Top right: labels from manual segmentation. Bottom: scatterplot of the T1 and T2 intensity features for Tumor020 based on the manual segmentation labels. The horizontal axis represents T2 intensities and the vertical axis represents T1 intensities.
Figure 9
Figure 9
Automatic segmentation result for the Tumor020 data. Left: T1 post-contrast image (for reference). Middle: Labels generated by the automatic method. Right: 3D view of the segmented tumor structure and cortical surface.
See this image and copyright information in PMC

References

    1. Just M, Thelen M. Tissue characterization with T1, T2, and proton density values: Results in 160 patients with brain tumors. Radiology. 1988;2:779–785. - PubMed
    1. Gerig G, Martin J, Kikinis R, Kubler O, Shenton M, Jolesz F. Automating segmentation of dual-echo MR head data. In: Colchester A, Hawkes D, editors. Proc IPMI 1991 LNCS 511. 1991. pp. 175–185.
    1. Velthuizen R, Clarke L, Phuphianich S, Hall L, Bensaid A, Arrington J, Greenberg H, Siblinger M. Unsupervised measurement of brain tumor volume on MR images. JMRI. 1995;4:594–605. - PubMed
    1. Vinitski S, Gonzales C, Mohamed F, Iwanaga T, Knobler R, Khalili K, Mack J. Improved intracranial lesion characterization by tissue segmentation based on a 3D feature map. Mag Re Med. 1997;5:457–469. - PubMed
    1. Kamber M, Shingal R, Collins D, Francis D, Evans A. Model-based, 3-D segmentation of multiple sclerosis lesions in magnetic resonance brain images. IEEE-TMI. 1995;6:442–453. - PubMed

Publication types

LinkOut - more resources