This material is presented to ensure timely dissemination of scholarly and technical work. Copyright and all rights therein are retained by authors or by other copyright holders. All persons copying this information are expected to adhere to the terms and constraints invoked by each author's copyright. In most cases, these works may not be reposted without the explicit permission of the copyright holder.

Search for Publication

Year(s) from:  to 
Keywords (separated by spaces):

Deformation Models for Registering MR and 3D Ultrasound Breast Images

C. Tanner, N. Karssemeijer, G. Székely
IEEE International Symposium on Biomedical Imaging


This paper investigates the effectiveness of compact, task-specific transformations for aligning the breast in the prone position to the compressed breast in the supine position. It was employed for registering 3DMRto 3D ultrasound images of the breast. This task has previously not been attempted and is very difficult due to the huge differences in image appearance and the very large breast deformation. The transformation consists of the composition of a cylindrical shear and an analytic ellipsoid compression (AEC). It requires a minimum number of features to be identified. These are the location of the nipple and the breast thickness posterior of the nipple in both modality, the medial-lateral distance of the nipple to the breast edge on ultrasound and an approximation of the ribcage by a cylinder on the MRI. The performance was assessed by the mean distance between corresponding lesion locations for four cases. A mean accuracy of 15.9 mm was achieved with AEC. Replacing this by a volume-preserving scaling or an analytical sphere compression transformation provided on average better results (14.4 mm, 15.4 mm). Rotation of the ultrasound images, such that the central rib aligned horizontal, was on average not beneficial (18.7-21.4 mm).

Link to publisher's page
  author = {C. Tanner and N. Karssemeijer and G. Székely},
  title = {Deformation Models for Registering MR and 3D Ultrasound Breast Images},
  booktitle = {IEEE International Symposium on Biomedical Imaging},
  year = {2011},
  pages = {582-585},
  keywords = {}