Enhanced probabilistic label fusion by estimating label confidences through discriminative learning

  • Authors
  • Benkarim OM, Piella G, Gonzalez Ballester MA, Sanroma G
  • UPF authors
  • SANROMA GÜELL, GERARD; BENKARIM ., MOHAMED OUALID; GONZALEZ BALLESTER, MIGUEL ANGEL; PIELLA FENOY, GEMA;
  • Type
  • Scholarly articles
  • Journal títle
  • Lecture Notes in Computer Science / Artificial Intelligence
  • Publication year
  • 2016
  • Volume
  • 9901
  • Pages
  • 505-512
  • ISSN
  • 0302-9743
  • Publication State
  • Published
  • Abstract
  • Multiple-atlas segmentation has recently shown success in automatic segmentation of brain images. It consists in registering the labelmaps from a set of atlases to the anatomy of a target image,and then fusing the multiple labelmaps into a consensus segmentation on the target image. Accurately estimating the confidence of each atlas decision is key for the success of label fusion. Common approaches either rely on local patch similarity,probabilistic statistical frameworks or a combination of both. We present a probabilistic label fusion framework that takes into account label confidence at each point. Maximum likelihood atlas confidences are estimated by explicitly modelling the relationship between image appearance and segmentation errors. We also propose a novel type of label-dependent appearance features based on atlas labelmaps. Our results indicate that the proposed label fusion framework achieves state-of-the-art performance in the segmentation of subcortical structures.
  • Complete citation
  • Benkarim OM, Piella G, Gonzalez Ballester MA, Sanroma G. Enhanced probabilistic label fusion by estimating label confidences through discriminative learning Lecture Notes in Computer Science / Artificial Intelligence 2016; 9901( ): 505-512.
Bibliometric indicators
  • 3 times cited Scopus
  • Índex Scimago de 0.339(2016)