Skip to main content
placeholder image

Segmentation of cone-beam CT using a hidden Markov random field with informative priors

Journal Article


Download full-text (Open Access)

Abstract


  • Cone-beam computed tomography (CBCT) has enormous potential to improve the accuracy of treatment delivery in image-guided radiotherapy (IGRT). To assist radiotherapists in interpreting these images, we use a Bayesian statistical model to label each voxel according to its tissue type. The rich sources of prior information in IGRT are incorporated into a hidden Markov random field model of the 3D image lattice. Tissue densities in the reference CT scan are estimated using inverse regression and then rescaled to approximate the corresponding CBCT intensity values. The treatment planning contours are combined with published studies of physiological variability to produce a spatial prior distribution for changes in the size, shape and position of the tumour volume and organs at risk. The voxel labels are estimated using iterated conditional modes. The accuracy of the method has been evaluated using 27 CBCT scans of an electron density phantom. The mean voxel-wise misclassification rate was 6.2%, with Dice similarity coefficient of 0.73 for liver, muscle, breast and adipose tissue. By incorporating prior information, we are able to successfully segment CBCT images. This could be a viable approach for automated, online image analysis in radiotherapy.

Authors


  •   Moores, Matt T.
  •   Hargrave, Catriona (external author)
  •   Harden, Fiona (external author)
  •   Mengersen, Kerrie (external author)

Publication Date


  • 2014

Citation


  • Moores, M., Hargrave, C., Harden, F. & Mengersen, K. (2014). Segmentation of cone-beam CT using a hidden Markov random field with informative priors. Journal of Physics: Conference Series, 489 (1), 012076-1-012076-4.

Scopus Eid


  • 2-s2.0-84899542990

Ro Full-text Url


  • https://ro.uow.edu.au/cgi/viewcontent.cgi?article=2680&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/1678

Start Page


  • 012076-1

End Page


  • 012076-4

Volume


  • 489

Issue


  • 1

Place Of Publication


  • United Kingdom

Abstract


  • Cone-beam computed tomography (CBCT) has enormous potential to improve the accuracy of treatment delivery in image-guided radiotherapy (IGRT). To assist radiotherapists in interpreting these images, we use a Bayesian statistical model to label each voxel according to its tissue type. The rich sources of prior information in IGRT are incorporated into a hidden Markov random field model of the 3D image lattice. Tissue densities in the reference CT scan are estimated using inverse regression and then rescaled to approximate the corresponding CBCT intensity values. The treatment planning contours are combined with published studies of physiological variability to produce a spatial prior distribution for changes in the size, shape and position of the tumour volume and organs at risk. The voxel labels are estimated using iterated conditional modes. The accuracy of the method has been evaluated using 27 CBCT scans of an electron density phantom. The mean voxel-wise misclassification rate was 6.2%, with Dice similarity coefficient of 0.73 for liver, muscle, breast and adipose tissue. By incorporating prior information, we are able to successfully segment CBCT images. This could be a viable approach for automated, online image analysis in radiotherapy.

Authors


  •   Moores, Matt T.
  •   Hargrave, Catriona (external author)
  •   Harden, Fiona (external author)
  •   Mengersen, Kerrie (external author)

Publication Date


  • 2014

Citation


  • Moores, M., Hargrave, C., Harden, F. & Mengersen, K. (2014). Segmentation of cone-beam CT using a hidden Markov random field with informative priors. Journal of Physics: Conference Series, 489 (1), 012076-1-012076-4.

Scopus Eid


  • 2-s2.0-84899542990

Ro Full-text Url


  • https://ro.uow.edu.au/cgi/viewcontent.cgi?article=2680&context=eispapers1

Ro Metadata Url


  • http://ro.uow.edu.au/eispapers1/1678

Start Page


  • 012076-1

End Page


  • 012076-4

Volume


  • 489

Issue


  • 1

Place Of Publication


  • United Kingdom