12 March 2010 A groupwise mutual information metric for cost efficient selection of a suitable reference in cardiac computational atlas construction
Author Affiliations +
Abstract
Computational atlases based on nonrigid registration have found much use in the medical imaging community. To avoid bias to any single element of the training set, there are two main approaches: using a (random) subject to serve as an initial reference and posteriorly removing bias, and a true groupwise registration with a constraint of zero average transformation for direct computation of the atlas. Major drawbacks are the possible selection of an outlier on one side, and an initialization with an invalid instance on the other. In both cases there is great potential for affecting registration performance, and producing a final average image in which the structure of interest deviates from the central anatomy of the population under study. We propose an inexpensive means of reference selection based on a groupwise correspondence measure, which avoids the selection of an outlier and is independent from the atlas construction approach that follows. Thus, it improves tractability of reference selection and robustness of automated atlas construction. We illustrate the method using a set of 20 cardiac multislice computed tomography volumes.
© (2010) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Corné Hoogendoorn, Corné Hoogendoorn, Tristan Whitmarsh, Tristan Whitmarsh, Nicolas Duchateau, Nicolas Duchateau, Federico M. Sukno, Federico M. Sukno, Mathieu De Craene, Mathieu De Craene, Alejandro F. Frangi, Alejandro F. Frangi, } "A groupwise mutual information metric for cost efficient selection of a suitable reference in cardiac computational atlas construction", Proc. SPIE 7623, Medical Imaging 2010: Image Processing, 76231R (12 March 2010); doi: 10.1117/12.844428; https://doi.org/10.1117/12.844428
PROCEEDINGS
9 PAGES


SHARE
Back to Top