|| Checking for direct PDF access through Ovid
A method to learn and combine pairwise image similarities obtained from heterogeneous sources of information for manifold learning is proposed.Image neighborhoods are learned through random forests based on multiple user-defined distances and combined optimally in a manifold learning step.The performance of the method is shown in neonatal magnetic resonance images of three different diagnostic groups (term controls, patients affected by intrauterine growth restriction and mild isolated ventriculomegaly).Results demonstrated that the combination of heterogeneous similarity definitions improves the overall characterization of clinical groups.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.