AutoAtlas: Neural Network for 3D Unsupervised Partitioning and Representation Learning
This work addresses the need for automated, unsupervised analysis of brain MRI data for researchers in neuroimaging, though it appears incremental as it builds on existing partitioning and representation learning methods.
The authors tackled the problem of unsupervised partitioning and representation learning for 3D brain MRI volumes, resulting in a neural network called AutoAtlas that produces subject-specific structural partitions and low-dimensional features for predicting metadata, with comparisons to FreeSurfer.
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.