Jennifer L. Boes [1]
Charles R. Meyer [1]
Terry E. Weymouth [2]
[1] The University of Michigan Medical Center, Department of Radiology
[2] Department of Electrical Engineering and Computer Science,
The University of Michigan, Ann Arbor, MI 48104
Abstract
Organ definition in computed tomography (CT) is of interest for treatment planning and response monitoring. We present a method for organ definition using a priori information about shape encoded in a biometric organ model--specifically a liver model--that accurately represents patient population shape information. This model is generated by averaging surfaces from a learning set of liver shapes previously registered into a standard space defined by a small set of landmarks. The model is placed in a specific patient's data set by identifying these landmarks and using them as the basis for model deformation; this preliminary representation is then iteratively fit to the patient's data based on a Bayesian combination of the model's priors and CT edge information, yielding a complete organ surface. We demonstrate this technique on a set of ten abdominal CT data sets and show its effectiveness as a tool for organ surface definition in this low-contrast domain.
Figures are available on-line.
Boes, J.L., C.R. Meyer, and T.E. Weymouth: Liver definition in CT using a population-based shape model. Proceedings of CVRMed'95, Nice, FR, in Lecture Notes in Computer Science (1995: Springer-Verlag, Berlin) 905:506-512.
This work supported in part by DHHS PHS grant NIH 1R01CA52709.
Other links: