Crosslink-Net: Double-branch Encoder Segmentation Network via Fusing Vertical and Horizontal Convolutions

TL;DR

Crosslink-Net introduces a double-branch encoder with vertical and horizontal convolutions and an attention loss to improve medical image segmentation, especially for small targets, outperforming traditional methods.

Contribution

The paper proposes a novel double-branch encoder architecture with non-square convolutions and an attention loss, enhancing segmentation accuracy for complex medical images.

Findings

Effective on four datasets

Improves segmentation of small targets

Outperforms existing methods

Abstract

Accurate image segmentation plays a crucial role in medical image analysis, yet it faces great challenges of various shapes, diverse sizes, and blurry boundaries. To address these difficulties, square kernel-based encoder-decoder architecture has been proposed and widely used, but its performance remains still unsatisfactory. To further cope with these challenges, we present a novel double-branch encoder architecture. Our architecture is inspired by two observations: 1) Since the discrimination of features learned via square convolutional kernels needs to be further improved, we propose to utilize non-square vertical and horizontal convolutional kernels in the double-branch encoder, so features learned by the two branches can be expected to complement each other. 2) Considering that spatial attention can help models to better focus on the target region in a large-sized image, we develop an attention loss to further emphasize the segmentation on small-sized targets. Together, the above two schemes give rise to a novel double-branch encoder segmentation framework for medical image segmentation, namely Crosslink-Net. The experiments validate the effectiveness of our model on four datasets. The code is released at https://github.com/Qianyu1226/Crosslink-Net.