MR-less surface-based amyloid estimation by subject-specific atlas selection and Bayesian fusion

Authors

Luping Zhou, University of WollongongFollow
Oliver Salvado, Australian E-Health Research Centre, Csiro
Vincent Dore, Australian E-Health Research Centre, Csiro
Pierrick Bourgeat, University of Wollongong
Parnesh Raniga, Australian E-Health Research Centre, Csiro
Victor L. Villemagne, Department Of Nuclear Medicine And Centre For Pet, Austin Hospital
Christopher C. Rowe, Department Of Nuclear Medicine And Centre For Pet, Austin Hospital
Jurgen Fripp, University of Wollongong

RIS ID

119687

Publication Details

Zhou, L., Salvado, O., Dore, V., Bourgeat, P., Raniga, P., Villemagne, V. L., Rowe, C. C. & Fripp, J. (2012). MR-less surface-based amyloid estimation by subject-specific atlas selection and Bayesian fusion. In N. Ayache, H. Delingette, P. Golland & K. Mori (Eds.), International Conference on Medical Image Computing and Computer-Assisted Intervention (pp. 220-227). Berlin, Germany: Springer-Verlag.

Abstract

For clinical evaluation, assessing amyloid deposition with PiB-PET is desirable without requiring MR acquisition and associated fusion/segmentation techniques. A useful clinical tool is to estimate PiB-PET against the brain surface, which is however challenging using PET alone because of the lack of structural information. We propose a method to generate such estimate, where multiple atlases are selected and combined with local weights in a Bayesian framework. Qualitative and quantitative comparison with and without MRI are presented. Using PET only, the average error on the brain surface was around 13% compared to MRI-dependant method.