EAGLE: An Efficient Global Attention Lesion Segmentation Model for Hepatic Echinococcosis

TL;DR

EAGLE is a novel, efficient neural network model that combines state space models and specialized modules to accurately segment hepatic echinococcosis lesions in CT images, outperforming existing methods.

Contribution

The paper introduces EAGLE, a U-shaped network with PVSS encoder and HVSS decoder, integrating CVSSB and HWTB modules for efficient global and local feature fusion in medical image segmentation.

Findings

Achieves a DSC of 89.76%, surpassing MSVM-UNet by 1.61%.

Demonstrates state-of-the-art performance on HE CT slices.

Efficiently models long-range dependencies with linear complexity.

Abstract

Hepatic echinococcosis (HE) is a widespread parasitic disease in underdeveloped pastoral areas with limited medical resources. While CNN-based and Transformer-based models have been widely applied to medical image segmentation, CNNs lack global context modeling due to local receptive fields, and Transformers, though capable of capturing long-range dependencies, are computationally expensive. Recently, state space models (SSMs), such as Mamba, have gained attention for their ability to model long sequences with linear complexity. In this paper, we propose EAGLE, a U-shaped network composed of a Progressive Visual State Space (PVSS) encoder and a Hybrid Visual State Space (HVSS) decoder that work collaboratively to achieve efficient and accurate segmentation of hepatic echinococcosis (HE) lesions. The proposed Convolutional Vision State Space Block (CVSSB) module is designed to fuse local and global features, while the Haar Wavelet Transformation Block (HWTB) module compresses spatial information into the channel dimension to enable lossless downsampling. Due to the lack of publicly available HE datasets, we collected CT slices from 260 patients at a local hospital. Experimental results show that EAGLE achieves state-of-the-art performance with a Dice Similarity Coefficient (DSC) of 89.76%, surpassing MSVM-UNet by 1.61%.