@Article{freedman:tmi05,
  author =	 {D.\ Freedman and R.\ J.\ Radke and Tao Zhang and
                  Yongwon Jeong and D.\ M.\ Lovelock and G.\ T.\ Y.\
                  Chen},
  title =	 {Model-based segmentation of medical imagery by
                  matching distributions},
  journal =	 {Medical Imaging, IEEE Transactions on},
  year =	 2005,
  volume =	 24,
  number =	 3,
  pages =	 {281--292},
  keywords =	 {computerised tomography, image segmentation, medical
                  image processing, radiation therapy, 3-D computed
                  tomography images, deformable objects, fast
                  principled algorithm, image-guided radiotherapy,
                  male pelvis, matching probability distributions,
                  medical imagery, model-based segmentation,
                  photometric variables, prostate, Deformable
                  segmentation, image-guided therapy, medical image
                  segmentation, prostate cancer, prostate
                  segmentation, shape and appearance model},
  abstract =	 {The segmentation of deformable objects from
                  three-dimensional (3-D) images is an important and
                  challenging problem, especially in the context of
                  medical imagery. We present a new segmentation
                  algorithm based on matching probability
                  distributions of photometric variables that
                  incorporates learned shape and appearance models for
                  the objects of interest. The main innovation over
                  similar approaches is that there is no need to
                  compute a pixelwise correspondence between the model
                  and the image. This allows for a fast, principled
                  algorithm. We present promising results on difficult
                  imagery for 3-D computed tomography images of the
                  male pelvis for the purpose of image-guided
                  radiotherapy of the prostate.},
  issn =	 {0278-0062},
  annote =	 {}
}