Building an ensemble of complementary segmentation methods by exploiting probabilistic estimates

  • Authors
  • Sanroma G, Benkarim OM, Piella G, Gonzalez Ballester M
  • UPF authors
  • PIELLA FENOY, GEMA; BENKARIM ., MOHAMED OUALID; SANROMA GÜELL, GERARD; GONZALEZ BALLESTER, MIGUEL ANGEL;
  • Type
  • Scholarly articles
  • Journal títle
  • Lecture Notes in Computer Science / Artificial Intelligence
  • Publication year
  • 2016
  • Volume
  • 10019
  • Pages
  • 27-35
  • ISSN
  • 0302-9743
  • Publication State
  • Published
  • Abstract
  • Two common ways of approaching atlas-based segmentation of brain MRI are (1) intensity-based modelling and (2) multi-atlas label fusion. Intensity-based methods are robust to registration errors but need distinctive image appearances. Multi-atlas label fusion can identify anatomical correspondences with faint appearance cues, but needs a reasonable registration. We propose an ensemble segmentation method that combines the complementary features of both types of approaches. Our method uses the probabilistic estimates of the base methods to compute their optimal combination weights in a spatially varying way. We also propose an intensity-based method (to be used as base method) that offers a trade-off between invariance to registration errors and dependence on distinct appearances. Results show that sacrificing invariance to registration errors (up to a certain degree) improves the performance of our intensity-based method. Our proposed ensemble method outperforms the rest of participating methods in most of the structures of the NeoBrainS12 Challenge on neonatal brain segmentation. We achieve up to ~10% of improvement in some structures
  • Complete citation
  • Sanroma G, Benkarim OM, Piella G, Gonzalez Ballester M. Building an ensemble of complementary segmentation methods by exploiting probabilistic estimates Lecture Notes in Computer Science / Artificial Intelligence 2016; 10019( ): 27-35.
Bibliometric indicators
  • 17 times cited Scopus
  • 15 times cited WOS
  • Índex Scimago de 0.339(2016)