A groupwise mutual information metric for cost efficient selection of a suitable reference in cardiac computational atlas construction

Corné Hoogendoorn (1) , Tristan Whitmarsh (1) , Nicolas Duchateau (1) , Federico M Sukno (1) , Mathieu de Craene (1) , Alejandro Frangi (1, 2)

1 CISTIB - Center for Computational Imaging and Simulation Technologies in Biomedicine
2 ICREA - Institució Catalana de Recerca i Estudis Avançats = Catalan Institution for Research and Advanced Studies

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.

Mots clés: Cardiac atlas construction; bias reduction; reference selection; groupwise mutual information

Domaines: Imagerie médicale

Corné Hoogendoorn, Tristan Whitmarsh, Nicolas Duchateau, Federico M Sukno, Mathieu de Craene, et al.. A groupwise mutual information metric for cost efficient selection of a suitable reference in cardiac computational atlas construction. SPIE Conference on Medical Imaging, 2010, San Diego, United States. pp.76231R, ⟨10.1117/12.844428⟩. ⟨hal-02320752⟩