Learning non-linear patch embeddings with neural networks for label fusion

for the Alzheimer's Disease Neuroimaging Initiative

Research output: Contribution to journalArticlepeer-review

20 Citations (Scopus)


In brain structural segmentation, multi-atlas strategies are increasingly being used over single-atlas strategies because of their ability to fit a wider anatomical variability. Patch-based label fusion (PBLF) is a type of such multi-atlas approaches that labels each target point as a weighted combination of neighboring atlas labels, where atlas points with higher local similarity to the target contribute more strongly to label fusion. PBLF can be potentially improved by increasing the discriminative capabilities of the local image similarity measurements. We propose a framework to compute patch embeddings using neural networks so as to increase discriminative abilities of similarity-based weighted voting in PBLF. As particular cases, our framework includes embeddings with different complexities, namely, a simple scaling, an affine transformation, and non-linear transformations. We compare our method with state-of-the-art alternatives in whole hippocampus and hippocampal subfields segmentation experiments using publicly available datasets. Results show that even the simplest versions of our method outperform standard PBLF, thus evidencing the benefits of discriminative learning. More complex transformation models tended to achieve better results than simpler ones, obtaining a considerable increase in average Dice score compared to standard PBLF.

Original languageEnglish
Pages (from-to)143-155
Number of pages13
JournalMedical Image Analysis
Publication statusPublished - 2018 Feb

Bibliographical note

Publisher Copyright:
© 2017 Elsevier B.V.


  • Brain MRI
  • Embedding
  • Hippocampus
  • Multi-atlas segmentation
  • Neural networks
  • Patch-based label fusion

ASJC Scopus subject areas

  • Radiological and Ultrasound Technology
  • Radiology Nuclear Medicine and imaging
  • Computer Vision and Pattern Recognition
  • Health Informatics
  • Computer Graphics and Computer-Aided Design


Dive into the research topics of 'Learning non-linear patch embeddings with neural networks for label fusion'. Together they form a unique fingerprint.

Cite this