DeepAI AI Chat
Log In Sign Up

AutoAtlas: Neural Network for 3D Unsupervised Partitioning and Representation Learning

by   K. Aditya Mohan, et al.

We present a novel neural network architecture called AutoAtlas for fully unsupervised partitioning and representation learning of 3D brain Magnetic Resonance Imaging (MRI) volumes. AutoAtlas consists of two neural network components: one that performs multi-label partitioning based on local texture in the volume and a second that compresses the information contained within each partition. We train both of these components simultaneously by optimizing a loss function that is designed to promote accurate reconstruction of each partition, while encouraging spatially smooth and contiguous partitioning, and discouraging relatively small partitions. We show that the partitions adapt to the subject specific structural variations of brain tissue while consistently appearing at similar spatial locations across subjects. AutoAtlas also produces very low dimensional features that represent local texture of each partition. We demonstrate prediction of metadata associated with each subject using the derived feature representations and compare the results to prediction using features derived from FreeSurfer anatomical parcellation. Since our features are intrinsically linked to distinct partitions, we can then map values of interest, such as partition-specific feature importance scores onto the brain for visualization.


page 1

page 3

page 5

page 6

page 8

page 9


Large-Scale Unsupervised Deep Representation Learning for Brain Structure

Machine Learning (ML) is increasingly being used for computer aided diag...

Deep Learning and Spectral Embedding for Graph Partitioning

We present a graph bisection and partitioning algorithm based on graph n...

Learning and Testing Variable Partitions

Let F be a multivariate function from a product set Σ^n to an Abelian gr...

R*-Grove: Balanced Spatial Partitioning for Large-scale Datasets

The rapid growth of big spatial data urged the research community to dev...

A Novel Tree Visualization to Guide Interactive Exploration of Multi-dimensional Topological Hierarchies

Understanding the response of an output variable to multi-dimensional in...