Contextual Hourglass Networks for Segmentation and Density Estimation

TL;DR

This paper introduces a novel method for hourglass networks that combines feature maps across different spatial scales, enhancing medical image segmentation and counting performance.

Contribution

It extends hourglass architectures by enabling feature map integration across layers with varying spatial dimensions, improving accuracy.

Findings

Achieved up to 17% performance improvement over existing hourglass networks.

Applicable to any hourglass architecture for segmentation and counting.

Demonstrated effectiveness on medical imaging tasks.

Abstract

Hourglass networks such as the U-Net and V-Net are popular neural architectures for medical image segmentation and counting problems. Typical instances of hourglass networks contain shortcut connections between mirroring layers. These shortcut connections improve the performance and it is hypothesized that this is due to mitigating effects on the vanishing gradient problem and the ability of the model to combine feature maps from earlier and later layers. We propose a method for not only combining feature maps of mirroring layers but also feature maps of layers with different spatial dimensions. For instance, the method enables the integration of the bottleneck feature map with those of the reconstruction layers. The proposed approach is applicable to any hourglass architecture. We evaluated the contextual hourglass networks on image segmentation and object counting problems in the medical domain. We achieve competitive results outperforming popular hourglass networks by up to 17 percentage points.