Multi-modal Multi-Atlas Segmentation using Discrete Optimisation and Self-Similarities


This work presents the application of a discrete medical image registration framework to multi-organ segmentation in different modalities. The algorithm works completely automatically and does not have to be tuned specifically for different datasets. A robust similarity measure, using the local self-similarity context (SSC), is employed and shown to outperform other commonly used metrics. Both affine and deformable registration are driven by a dense displacement sampling (deeds) strategy. The smoothness of displacements is enforced by inference on a Markov random field (MRF), using a tree approximation for computational efficiency. Consensus segmentations for unseen test images of the VISCERAL Anatomy 3 data are found by majority voting.

Original languageEnglish
Title of host publicationCEUR Workshop Proceedings
Publication date01.01.2015
Publication statusPublished - 01.01.2015
EventVISCERAL Anatomy3 Organ Segmentation Challenge, VISCERAL 2015 - co-located with IEEE International Symposium on Biomedical Imaging 2015 - New York, United States
Duration: 16.04.201516.04.2015


Dive into the research topics of 'Multi-modal Multi-Atlas Segmentation using Discrete Optimisation and Self-Similarities'. Together they form a unique fingerprint.

Cite this