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

TL;DR

AutoAtlas is a neural network architecture for unsupervised partitioning and feature learning of 3D brain MRI data, capturing subject-specific structures and enabling interpretability of brain features.

Contribution

The paper introduces AutoAtlas, a novel neural network that performs unsupervised brain partitioning and representation learning, adaptable to individual variations and useful for predictive modeling.

Findings

Partitions adapt to individual brain structures

AutoAtlas features outperform FreeSurfer in metadata prediction

Partition-based features enable brain visualization

Abstract

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 neural network to perform multi-label partitioning based on local texture in the volume, and a second neural network to compress 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.