Learning and Combining Image Similarities for Neonatal Brain Population Studies

Zimmer, Veronika A.; Glocker, Ben; Aljabar, Paul; Counsell, Serena J.; Rutherford, Mary A.; Edwards, A. David; Hajnal, Joseph V.; Ballester, Miguel Ángel González; Rueckert, Daniel; Piella, Gemma

doi:10.1007/978-3-319-24888-2_14

Cited by 1 publication

(2 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This work extends our previous conference paper (Zimmer et al, 2015a) with a more detailed description of the method, a more sophisticated combination method for the approximated neighborhoods and a more extensive evaluation on new data.…”

mentioning

confidence: 60%

See 1 more Smart Citation

Learning and combining image neighborhoods using random forests for neonatal brain disease classification

Zimmer

Glocker

Hahner

et al. 2017

Medical Image Analysis

Self Cite

View full text Add to dashboard Cite

It is challenging to characterize and classify normal and abnormal brain development during early childhood. To reduce the complexity of heterogeneous data population, manifold learning techniques are increasingly applied, which find a low-dimensional representation of the data, while preserving all relevant information. The neighborhood definition used for constructing manifold representations of the population is crucial for preserving the similarity structure and it is highly application dependent. The recently proposed neighborhood approximation forests learn a neighborhood structure in a dataset based on a user-defined distance. We propose a framework to learn multiple pairwise distances in a population of brain images and to combine them in an unsupervised manner optimally in a manifold learning step. Unlike other methods that only use a univariate distance measure, our method allows for a natural combination of multiple distances from heterogeneous sources. As a result, it yields a representation of the population that preserves the multiple distances. Furthermore, our method also selects the most predictive features associated with the distances. We evaluate our method in neonatal magnetic resonance images of three groups (term controls, patients affected by intrauterine growth restriction and mild isolated ventriculomegaly). We show that combining multiple distances related to the condition improves the overall characterization and classification of the three clinical groups compared to the use of single distances and classical unsupervised manifold learning.

show abstract

mentioning

confidence: 60%

“…As a manifold learning method, we employed LE, but other non-linear methods are possible. In our previous work (Zimmer et al, 2015a), we applied Isomap to the approximated neighborhoods obtained from the NAFs, because it had the best performance on the given dataset. In Section 2.2, we presented two methods to optimize the weights in Eq.…”

Section: Iugrmentioning

confidence: 99%