SASHIMI 2016 is a half-day workshop that is part of the International Conference on Medical Image Computing & Computer Assisted Intervention (MICCAI). The paper ‘Registration of Pathological Images‘ has been accepted to the workshop. Its authors include Xiao Yang (University of North Carolina at Chapel Hill), Xu Han, Eunbyung Park (UNC Chapel Hill), Stephen Aylward (Kitware), Roland Kwitt (University of Salzburg), and Marc Niethammer (UNC Chapel Hill/Biomedical Research Imaging Center).

Abstract from ‘Proceedings of the International Workshop on Simulation and Synthesis in Medical Imaging (SASHIMI) 2016’
Volume Editors: Sotirios A Tsaftaris, Ali Gooya, Alejandro F Frangi, and Jerry L Prince

This paper proposes an approach to improve atlas-to-image registration accuracy with large pathologies. Instead of directly registering an atlas to a pathological image, the method learns a mapping from the pathological image to a quasi-normal image, for which more accurate
registration is possible. Speci fically, the method uses a deep variational convolutional encoder-decoder network to learn the mapping. Furthermore, the method estimates local mapping uncertainty through network inference statistics and uses those estimates to down-weight the image
registration similarity measure in areas of high uncertainty. The performance of the method is quantified using synthetic brain tumor images and images from the brain tumor segmentation challenge (BRATS 2015).

Menze, B.H., Reyes, M., Leemput, K.V.: The multimodal brain tumor image segmentation benchmark (BRATS). TMI 34(10), 1993{2024 (2015)

Physical Event