Multiscale Segmentation of the Skull in MR Images for MRI-based Attenuation Correction of Combined MR/PET

Overview

Journal J Am Med Inform Assoc

Publisher Oxford University Press

Specialty Medical Informatics

Date 2013 Jun 14

PMID 23761683

Citations 18

Authors

Xiaofeng Yang

Baowei Fei

Affiliations

Soon will be listed here.

Abstract

Background And Objective: Combined magnetic resonance/positron emission tomography (MR/PET) is a relatively new, hybrid imaging modality. MR-based attenuation correction often requires segmentation of the bone on MR images. In this study, we present an automatic segmentation method for the skull on MR images for attenuation correction in brain MR/PET applications.

Materials And Methods: Our method transforms T1-weighted MR images to the Radon domain and then detects the features of the skull image. In the Radon domain we use a bilateral filter to construct a multiscale image series. For the repeated convolution we increase the spatial smoothing in each scale and make the width of the spatial and range Gaussian function doubled in each scale. Two filters with different kernels along the vertical direction are applied along the scales from the coarse to fine levels. The results from a coarse scale give a mask for the next fine scale and supervise the segmentation in the next fine scale. The use of the multiscale bilateral filtering scheme is to improve the robustness of the method for noise MR images. After combining the two filtered sinograms, the reciprocal binary sinogram of the skull is obtained for the reconstruction of the skull image.

Results: This method has been tested with brain phantom data, simulated brain data, and real MRI data. For real MRI data the Dice overlap ratios are 92.2%±1.9% between our segmentation and manual segmentation.

Conclusions: The multiscale segmentation method is robust and accurate and can be used for MRI-based attenuation correction in combined MR/PET.

Citing Articles

A systematic literature review: deep learning techniques for synthetic medical image generation and their applications in radiotherapy.

Sherwani M, Gopalakrishnan S Front Radiol. 2024; 4:1385742.

PMID: 38601888 PMC: 11004271. DOI: 10.3389/fradi.2024.1385742.

A review of PET attenuation correction methods for PET-MR.

Krokos G, MacKewn J, Dunn J, Marsden P EJNMMI Phys. 2023; 10(1):52.

PMID: 37695384 PMC: 10495310. DOI: 10.1186/s40658-023-00569-0.

MRI classification using semantic random forest with auto-context model.

Lei Y, Wang T, Dong X, Tian S, Liu Y, Mao H Quant Imaging Med Surg. 2021; 11(12):4753-4766.

PMID: 34888187 PMC: 8611460. DOI: 10.21037/qims-20-1114.

A review on medical imaging synthesis using deep learning and its clinical applications.

Wang T, Lei Y, Fu Y, Wynne J, Curran W, Liu T J Appl Clin Med Phys. 2020; 22(1):11-36.

PMID: 33305538 PMC: 7856512. DOI: 10.1002/acm2.13121.

Machine learning in quantitative PET: A review of attenuation correction and low-count image reconstruction methods.

Wang T, Lei Y, Fu Y, Curran W, Liu T, Nye J Phys Med. 2020; 76:294-306.

PMID: 32738777 PMC: 7484241. DOI: 10.1016/j.ejmp.2020.07.028.

References

Wang H, Fei B . A modified fuzzy C-means classification method using a multiscale diffusion filtering scheme. Med Image Anal. 2008; 13(2):193-202. PMC: 2817958. DOI: 10.1016/j.media.2008.06.014. View

Berker Y, Franke J, Salomon A, Palmowski M, Donker H, Temur Y . MRI-based attenuation correction for hybrid PET/MRI systems: a 4-class tissue segmentation technique using a combined ultrashort-echo-time/Dixon MRI sequence. J Nucl Med. 2012; 53(5):796-804. DOI: 10.2967/jnumed.111.092577. View

Lemieux L, Hagemann G, Krakow K, Woermann F . Fast, accurate, and reproducible automatic segmentation of the brain in T1-weighted volume MRI data. Magn Reson Med. 1999; 42(1):127-35. DOI: 10.1002/(sici)1522-2594(199907)42:1<127::aid-mrm17>3.0.co;2-o. View

Baillard C, Hellier P, Barillot C . Segmentation of brain 3D MR images using level sets and dense registration. Med Image Anal. 2001; 5(3):185-94. DOI: 10.1016/s1361-8415(01)00039-1. View

Boesen K, Rehm K, Schaper K, Stoltzner S, Woods R, Luders E . Quantitative comparison of four brain extraction algorithms. Neuroimage. 2004; 22(3):1255-61. DOI: 10.1016/j.neuroimage.2004.03.010. View

Soltanian-Zadeh H, Windham J . A multiresolution approach for contour extraction from brain images. Med Phys. 1998; 24(12):1844-53. DOI: 10.1118/1.598099. View

Grau V, Mewes A, Alcaniz M, Kikinis R, Warfield S . Improved watershed transform for medical image segmentation using prior information. IEEE Trans Med Imaging. 2004; 23(4):447-58. DOI: 10.1109/TMI.2004.824224. View

Wang H, Feyes D, Mulvihill J, Oleinick N, MacLennan G, Fei B . Multiscale Fuzzy C-Means Image Classification for Multiple Weighted MR Images for the Assessment of Photodynamic Therapy in Mice. Proc SPIE Int Soc Opt Eng. 2014; 6512. PMC: 3877232. DOI: 10.1117/12.710188. View

Keereman V, Fierens Y, Broux T, De Deene Y, Lonneux M, Vandenberghe S . MRI-based attenuation correction for PET/MRI using ultrashort echo time sequences. J Nucl Med. 2010; 51(5):812-8. DOI: 10.2967/jnumed.109.065425. View

10.

Horbelt S, Liebling M, Unser M . Discretization of the radon transform and of its inverse by spline convolutions. IEEE Trans Med Imaging. 2002; 21(4):363-76. DOI: 10.1109/TMI.2002.1000260. View

11.

Beyer T, Weigert M, Quick H, Pietrzyk U, Vogt F, Palm C . MR-based attenuation correction for torso-PET/MR imaging: pitfalls in mapping MR to CT data. Eur J Nucl Med Mol Imaging. 2008; 35(6):1142-6. DOI: 10.1007/s00259-008-0734-0. View

12.

van Ginneken B, Frangi A, Staal J, Romeny B, Viergever M . Active shape model segmentation with optimal features. IEEE Trans Med Imaging. 2002; 21(8):924-33. DOI: 10.1109/TMI.2002.803121. View

13.

Fei B, Wang H, Muzic Jr R, Flask C, Wilson D, Duerk J . Deformable and rigid registration of MRI and microPET images for photodynamic therapy of cancer in mice. Med Phys. 2006; 33(3):753-60. DOI: 10.1118/1.2163831. View

14.

Pohl K, Fisher J, Kikinis R, Grimson W, Wells W . Shape Based Segmentation of Anatomical Structures in Magnetic Resonance Images. Comput Vis Biomed Image Appl (2005). 2017; 3765:489-498. PMC: 5486153. DOI: 10.1007/11569541_49. View

15.

Yang X, Fei B . A multiscale and multiblock fuzzy C-means classification method for brain MR images. Med Phys. 2011; 38(6):2879-91. PMC: 3117893. DOI: 10.1118/1.3584199. View

16.

Yang X, Fei B . A wavelet multiscale denoising algorithm for magnetic resonance (MR) images. Meas Sci Technol. 2013; 22(2):25803. PMC: 3707516. DOI: 10.1088/0957-0233/22/2/025803. View

17.

Rex D, Shattuck D, Woods R, Narr K, Luders E, Rehm K . A meta-algorithm for brain extraction in MRI. Neuroimage. 2004; 23(2):625-37. DOI: 10.1016/j.neuroimage.2004.06.019. View

18.

Kapur T, Grimson W, Wells 3rd W, Kikinis R . Segmentation of brain tissue from magnetic resonance images. Med Image Anal. 1996; 1(2):109-27. DOI: 10.1016/S1361-8415(96)80008-9. View

19.

West J, Fitzpatrick J, Wang M, Dawant B, Maurer Jr C, Kessler R . Comparison and evaluation of retrospective intermodality brain image registration techniques. J Comput Assist Tomogr. 1997; 21(4):554-66. DOI: 10.1097/00004728-199707000-00007. View

20.

Fei B, Duerk J, Sodee D, Wilson D . Semiautomatic nonrigid registration for the prostate and pelvic MR volumes. Acad Radiol. 2005; 12(7):815-24. DOI: 10.1016/j.acra.2005.03.063. View