Abstract
The newborn’s cranium is composed of flat cranial bone and fontanels forming together the envelope of the cerebral cavity. The fontanels are relatively flexible since they consist of fibrous membrane that ossifies during maturation becoming flat cranial bone as well. Fontanels give less contrast in computerized tomography (CT) images; they can be identified as gaps between the cranial bones. In this paper, we propose an automatic model-based method using variational level set to segment the skull and fontanels from CT images. In this approach, firstly a skull model consisting of cranial bones and fontanels is created and then used as constraint for level set evolution. Then, by removing the cranial bones from the segmented skulls, the fontanels are obtained. To verify the validity of the achieved results, automatically segmented skull and fontanels have been compared with the ones manually segmented by an expert using Dice similarity and Hausdorff dissimilarity measures, which show the good agreement between them. Furthermore, the surface areas of cranium and fontanel have been determined for these segmentations. The results for both, manual and automatic segmentation, are in good agreement.
Similar content being viewed by others
Abbreviations
- A i (·):
-
The 12-parameter affine transformation
- C :
-
Evolving contour
- c 1 :
-
Approximation of the mean value of image intensity inside C
- c 2 :
-
Approximation of the mean value of image intensity outside C
- D(·):
-
The Euclidean distance
- \({D_{H_K} (\cdot)}\) :
-
The Hausdorff distance
- D i (·):
-
Nonlinear deformation
- h(·):
-
Direct Hausdorff distance
- H(·):
-
Heaviside function
- I :
-
Input image
- I R :
-
Reference image
- I′:
-
The affine-normalized image
- I′′:
-
The affine- and nonlinear normalized image
- Ĩ:
-
Transformed image by applying computed \({\bar{T}}\) to \({I_i^{{\prime}{\prime}}}\) for each subject
- S′:
-
The affine-normalized extracted skull
- S′′:
-
The affine and nonlinear normalized skull
- S͂:
-
Transformed skull by applying computed \({\bar{T}}\) to \({S_i^{{\prime}{\prime}}}\) for each subject
- T :
-
The inverse nonlinear transformation
- \({\bar{T}}\) :
-
The mean of T i transformations
- W:
-
Registration parameters
- α :
-
Non-negative constant
- δ(.):
-
Delta function
- ε :
-
Constant for Heaviside function approximation
- λ 1 :
-
Positive weighting constants
- λ 2 :
-
Positive weighting constants
- μ :
-
Positive weighting constant
- ν :
-
Positive weighting constant
- φ :
-
Level set function
- φ m :
-
Level set function of the shape prior
- Ω:
-
Image space
- \({\mathfrak{R}^{n}}\) :
-
n-Dimensional space
References
Shi, L., Heng, P.A., Wong, T.T., Chu, W.C.W., Yeung, B.H.Y., Cheng, J.C.Y.: Morphometric analysis for pathological abnormality detection in the skull vaults of adolescent idiopathic scoliosis girls. In: Proceedings of 9th International Conference on Medical Image Computing and Computer Assisted Intervention (MICCAI), vol. 9, no Pt 1, pp. 175–182 (2006)
Burguet, J., Gadi, N., Bloch, I.: Realistic models of children heads from 3D MRI segmentation and tetrahedral mesh construction. In: Proceedings of IEEE, 2nd International Symposium on 3D Data Processing, Visualization and Transmission, pp. 631–639 (2004)
Dannhauer M., Lanfer B., Wolters C.H., Knösche T.R.: Modeling of the human skull in EEG source analysis. Hum. Brain Mapp. 32(9), 1383–1399 (2011)
Kiesler J., Richer R.: The abnormal fontanel. Am. Family Physician 67(12), 2547–2552 (2003)
Baillet S., Riere J.J., Marin G., Mangin J.F., Aubert J., Garnero L.: Evaluation of inverse methods and head models for EEG source localization using a human skull phantom. Phys. Med. Biol. 46(1), 77–96 (2001)
Liu H., Gao X., Schimpf P.H., Yang F., Gao S.: A recursive algorithm for the three-dimensional imaging of brain electric activity: shrinking LORETA-FOCUSS. Trans. IEEE. Biomed. Eng. 51(10), 1794–1802 (2004)
Roche-Labarbe N., Aarabi A., Kongolo G., Gondry-Jouet C., Dümpelmann M., Grebe R., Wallois F.: High-resolution EEG and source localization in neonates. Hum. Brain Mapp. 29(2), 167–176 (2008)
Cuffin B.N.: EEG localization accuracy improvements using realistically shaped head models. Trans. IEEE. Biomed. Eng. 43(3), 299–303 (1996)
De Munck J.C., Peters M.J.: A fast method to compute the potential in the multisphere model. Trans. IEEE. Biomed. Eng. 40(2), 1166–1174 (1993)
Ermer J.J., Mosher J.C., Baillet S., Leahy R.M.: Rapidly recomputable EEG forward models for realistic head shapes. Phys. Med. Biol. 46(4), 1265–1281 (2001)
Fuchs M., Kastner J., Wagner M., Hawes S., Ebersole J.: A standardized boundary element method volume conductor model. Clin. Neurophysiol. 113(5), 702–712 (2002)
Valdés-Hernández P.A., von Ellenrieder N., Ojeda-Gonzalez A., Kochen S., Alemán-Gómez Y., Muravchik C., Valdés-Sosa P.A.: Approximate average head models for EEG source imaging. J. Neurosci Methods 185(1), 125–132 (2009)
Flemming L., Wanga Y., Caprihanc A., Eiseltd M., Haueisenb J., Okada Y.: Evaluation of the distortion of EEG signals caused by a hole in the skull mimicking the fontanel in the skull of human neonates. Clin. Neurophysiol. 116(5), 1141–1152 (2005)
Dehaes, M., Kazemi, K., Pélégrini-Issac, M., Grebe1, R., Benali, H., Wallois, F.: Quantitative effect of the neonatal fontanel on synthetic near infrared spectroscopy measurements. Hum. Brain Map. (to appear)
Rifai H., Bloch I., Hutchinson S., Wiart J., Garnero L.: Segmentation of the skull in MRI volumes using deformable model and taking the partial volume effect into account. Med. Image Anal. 4(3), 219–233 (2000)
Dogdas B., Shattuck D.W., Leahy R.M.: Segmentation of skull and scalp in 3D human MRI using mathematical morphology. Hum. Brain Mapp. 26(4), 273–285 (2005)
Wang D., Shi L., Chu C.W., Cheng J.C., Heng P.A.: Segmentation of human skull in MRI using statistical shape information from CT data. J. Magn. Reson. Imaging 30(3), 490–498 (2009)
Ghadimi, S., Abrishami Moghaddam, H., Kazemi, K., Grebe, R., Goundry-Jouet, C., Wallois, F.: Segmentation of scalp and skull in neonatal MR images using probabilistic atlas and level set method. In: Conference on Proceedings of IEEE Engineering in Medicine and Biology Society, pp. 3060–3063 (2008)
Mumford D., Shah J.: Optimal approximation by piecewise smooth functions and associated variational problems. Commun. Pure Appl. Math. 42(5), 577–685 (1989)
Chan T., Vese L.: Active contours without edges. Trans. IEEE. Image Process 10(2), 266–277 (2001)
Osher S., Sethian J.: Fronts propagation with curvature-dependent speed: algorithms based on the Hamilton-Jacobi formulation. J. Comput. Phys. 79(1), 12–149 (1988)
Cremers D., Sochen N., Schnorr C. (2003) Towards recognition-based variational segmentation using shape priors and dynamic labeling. Isle of Skye. Springer, Berlin, pp. 388–400
Otsu N.: A threshold selection method from gray-level histograms. Trans. IEEE. Syst. Man. Cybern. 9(1), 62–66 (1979)
Kazemi K., Abrishami Moghaddam H., Grebe R., Gondry-Jouet C., Wallois F.: A neonatal atlas template for spatial normalization of whole-brain magnetic resonance images of newborns: preliminary results. Neuroimage 37(2), 463–473 (2007)
Ashburner J., Friston K.J.: Nonlinear spatial normalization using basis functions. Hum. Brain Mapp. 7(4), 254–266 (1999)
Kazemi, K., Ghadimi, S., Abrishami-Moghaddam, H., Grebe, R., Gondry-Jouet, C., Wallois, F.: Neonatal probabilistic models for brain, CSF and skull using T1-MRI data: preliminary results. In: Conference on Proceedings of IEEE Engineering in Medicine and Biology Society, pp. 3892–3895 (2008)
Calder, J., Tahmasebi, A., Mansouri, A. A variational approach to bone segmentation in CT images. In: Proceedings of SPIE, vol. 7962, pp. 79620B–79620B-15 (2011)
Dice L.R.: Measures of the amount of ecologic association between species. Ecology 26(3), 297–302 (1945)
Huttenlocher D.P., Klanderman G.A., Rucklidge W.J.: Comparing images using the Hausdorff distance. Trans, IEEE. Pattern. Anal. Mach. Intell. 15, 850–863 (1993)
Paumard J.: Robust comparison of binary images. Pattern Recogn. Lett. 18(10), 1057–1063 (1997)
Dubuisson, M.P., Jain, A.K.: A modified Hausdorff distance for object matching. In: Proceedings of 12th IAPR International Pattern Recognition, pp. 566–568 (1994)
Mathur S., Kumar R., Mathur G.P., Singh V.K., Gupta V., Tripathi V.N.: Anterior fontanel size. Indian Pediatr 31(2), 161–164 (1994)
Kiesler J., Ricer R.: The abnormal fontanel. Am. Family Physician 67(12), 2547–2552 (2003)
Tsai A., Yezzi A. Jr., Wells W., Tempany C., Tucker D., Fan A., Grimson W.E., Willsky A.: A shape-based approach to the segmentation of medical imagery using level sets. Trans. IEEE. Med. Imaging 22(2), 137–154 (2003)
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
Jafarian, N., Kazemi, K., Abrishami Moghaddam, H. et al. Automatic segmentation of newborns’ skull and fontanel from CT data using model-based variational level set. SIViP 8, 377–387 (2014). https://doi.org/10.1007/s11760-012-0300-x
Received:
Revised:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11760-012-0300-x