MA-Unet: An improved version of Unet based on multi-scale and attention mechanism for medical image segmentation

TL;DR

MA-Unet enhances medical image segmentation by integrating multi-scale features and attention mechanisms, effectively addressing semantic ambiguity and global context modeling, resulting in improved performance with fewer parameters.

Contribution

The paper introduces MA-Unet, which incorporates attention gates and multi-scale fusion to improve segmentation accuracy and efficiency over existing models.

Findings

Outperforms state-of-the-art segmentation networks.

Uses fewer parameters while achieving better results.

Effectively models global context and channel dependencies.

Abstract

Although convolutional neural networks (CNNs) are promoting the development of medical image semantic segmentation, the standard model still has some shortcomings. First, the feature mapping from the encoder and decoder sub-networks in the skip connection operation has a large semantic difference. Second, the remote feature dependence is not effectively modeled. Third, the global context information of different scales is ignored. In this paper, we try to eliminate semantic ambiguity in skip connection operations by adding attention gates (AGs), and use attention mechanisms to combine local features with their corresponding global dependencies, explicitly model the dependencies between channels and use multi-scale predictive fusion to utilize global information at different scales. Compared with other state-of-the-art segmentation networks, our model obtains better segmentation performance while introducing fewer parameters.