Deformable Registration through Learning of Context-Specific Metric Aggregation

Enzo Ferrante 1, 2, 3 Puneet K Dokania 4, 2 Rafael Marini 1, 2 Nikos Paragios 1, 2
1 GALEN - Organ Modeling through Extraction, Representation and Understanding of Medical Image Content
Inria Saclay - Ile de France, Ecole Centrale Paris
2 CVN - Centre de vision numérique
3 BioMedIA - Biomedical Image Analysis Group [London]
4 University of Oxford [Oxford]
Abstract : We propose a novel weakly supervised discriminative algorithm for learning context specific registration metrics as a linear combination of conventional similarity measures. Conventional metrics have been extensively used over the past two decades and therefore both their strengths and limitations are known. The challenge is to find the optimal relative weighting (or parameters) of different metrics forming the similarity measure of the registration algorithm. Hand-tuning these parameters would result in sub optimal solutions and quickly become infeasible as the number of metrics increases. Furthermore, such hand-crafted combination can only happen at global scale (entire volume) and therefore will not be able to account for the different tissue properties. We propose a learning algorithm for estimating these parameters locally, conditioned to the data semantic classes. The objective function of our formulation is a special case of non-convex function, difference of convex function, which we optimize using the concave convex procedure. As a proof of concept, we show the impact of our approach on three challenging datasets for different anatomical structures and modalities.
Document type :
Conference papers
Liste complète des métadonnées
https://hal.inria.fr/hal-01650956
Contributor : Enzo Ferrante <>
Submitted on : Tuesday, November 28, 2017 - 3:12:53 PM
Last modification on : Tuesday, February 5, 2019 - 1:52:14 PM

Links full text

arxiv

Identifiers

  • HAL Id : hal-01650956, version 1
  • ARXIV : 1707.06263

Collections

INRIA | CVN | CENTRALESUPELEC | INRIA2017 | UNIV-PARIS-SACLAY

Citation

Enzo Ferrante, Puneet K Dokania, Rafael Marini, Nikos Paragios. Deformable Registration through Learning of Context-Specific Metric Aggregation. Machine Learning in Medical Imaging Worlshop. MLMI (MICCAI 2017), Sep 2017, Quebec City, Canada. ⟨hal-01650956⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

124

Contact


archive-ouverte@inria.fr