A skull segmentation method for brain MR images based on multiscale bilateral filtering scheme

Xiaofeng Yang, Baowei Fei

Research output: Chapter in Book/Report/Conference proceedingConference contribution

9 Scopus citations


We present a novel automatic segmentation method for the skull on brain MR images for attenuation correction in combined PET/MRI applications. Our method transforms T1-weighted MR images to the Radon domain and then detects the feature of the skull. In the Radon domain we use a bilateral filter to construct a multiscale images series. For the repeated convolution we increase the spatial smoothing at each scale and make the cumulative width of the spatial and range Gaussian doubled at 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 method is robust for noise MR images because of its multiscale bilateral filtering scheme. After combining the two filtered sinogram, the reciprocal binary sinogram of the skull is obtained for the reconstruction of the skull image. We use the filtered back projection method to reconstruct the segmented skull image. We define six metrics to evaluate our segmentation method. The method has been tested with brain phantom data, simulated brain data, and real MRI data. Evaluation results showed that our method is robust and accurate, which is useful for skull segmentation and subsequently for attenuation correction in combined PET/MRI applications.

Original languageEnglish (US)
Title of host publicationMedical Imaging 2010
Subtitle of host publicationImage Processing
EditionPART 1
StatePublished - 2010
Externally publishedYes
EventMedical Imaging 2010: Image Processing - San Diego, CA, United States
Duration: Feb 14 2010Feb 16 2010

Publication series

NameProgress in Biomedical Optics and Imaging - Proceedings of SPIE
NumberPART 1
ISSN (Print)1605-7422


OtherMedical Imaging 2010: Image Processing
Country/TerritoryUnited States
CitySan Diego, CA


  • Radon transform
  • bilateral filter
  • multiscale scheme
  • skull segmentation

ASJC Scopus subject areas

  • Electronic, Optical and Magnetic Materials
  • Biomaterials
  • Atomic and Molecular Physics, and Optics
  • Radiology Nuclear Medicine and imaging


Dive into the research topics of 'A skull segmentation method for brain MR images based on multiscale bilateral filtering scheme'. Together they form a unique fingerprint.

Cite this