3D Densely Convolutional Networks for Volumetric Segmentation

TL;DR

This paper introduces a very deep densely convolutional network architecture for volumetric brain segmentation, effectively capturing multi-scale information and improving accuracy and efficiency in challenging low-contrast MRI images.

Contribution

It proposes a novel densely connected 3D network architecture that enhances information flow and multi-scale feature capturing for volumetric segmentation.

Findings

Significant improvement in segmentation accuracy over existing methods.

Enhanced parameter efficiency in 3D brain MRI segmentation.

Successful application in MICCAI infant brain MRI challenge.

Abstract

In the isointense stage, the accurate volumetric image segmentation is a challenging task due to the low contrast between tissues. In this paper, we propose a novel very deep network architecture based on a densely convolutional network for volumetric brain segmentation. The proposed network architecture provides a dense connection between layers that aims to improve the information flow in the network. By concatenating features map of fine and coarse dense blocks, it allows capturing multi-scale contextual information. Experimental results demonstrate significant advantages of the proposed method over existing methods, in terms of both segmentation accuracy and parameter efficiency in MICCAI grand challenge on 6-month infant brain MRI segmentation.