On the Compactness, Efficiency, and Representation of 3D Convolutional Networks: Brain Parcellation as a Pretext Task

TL;DR

This paper introduces a compact, efficient 3D convolutional network for brain MRI segmentation, demonstrating superior performance and potential for transfer learning and uncertainty estimation in volumetric medical imaging.

Contribution

It proposes a novel high-resolution, compact 3D CNN architecture utilizing dilated convolutions and residual connections for brain parcellation, advancing efficiency and transfer learning potential.

Findings

Outperforms state-of-the-art volumetric segmentation networks

Achieves an order of magnitude reduction in model size

Enables voxel-level uncertainty estimation using dropout sampling

Abstract

Deep convolutional neural networks are powerful tools for learning visual representations from images. However, designing efficient deep architectures to analyse volumetric medical images remains challenging. This work investigates efficient and flexible elements of modern convolutional networks such as dilated convolution and residual connection. With these essential building blocks, we propose a high-resolution, compact convolutional network for volumetric image segmentation. To illustrate its efficiency of learning 3D representation from large-scale image data, the proposed network is validated with the challenging task of parcellating 155 neuroanatomical structures from brain MR images. Our experiments show that the proposed network architecture compares favourably with state-of-the-art volumetric segmentation networks while being an order of magnitude more compact. We consider the brain parcellation task as a pretext task for volumetric image segmentation; our trained network potentially provides a good starting point for transfer learning. Additionally, we show the feasibility of voxel-level uncertainty estimation using a sampling approximation through dropout.