An Effective UNet Using Feature Interaction and Fusion for Organ Segmentation in Medical Image

TL;DR

This paper introduces a novel U-Net variant with feature interaction and fusion modules that enhances organ segmentation accuracy in medical images by leveraging advanced feature modeling and multi-scale fusion.

Contribution

The work proposes three plug-and-play modules for U-Net that improve feature interaction, attention, and multi-scale fusion, leading to superior segmentation performance.

Findings

Achieved highest Dice scores of 86.05% and 92.58% on two datasets.

Outperformed existing state-of-the-art methods in accuracy.

Maintained a balance between performance and computational complexity.

Abstract

Nowadays, pre-trained encoders are widely used in medical image segmentation due to their strong capability in extracting rich and generalized feature representations. However, existing methods often fail to fully leverage these features, limiting segmentation performance. In this work, a novel U-shaped model is proposed to address the above issue, including three plug-and-play modules. A channel spatial interaction module is introduced to improve the quality of skip connection features by modeling inter-stage interactions between the encoder and decoder. A channel attention-based module integrating squeeze-and-excitation mechanisms with convolutional layers is employed in the decoder blocks to strengthen the representation of critical features while suppressing irrelevant ones. A multi-level fusion module is designed to aggregate multi-scale decoder features, improving spatial detail and consistency in the final prediction. Comprehensive experiments on the synapse multi-organ segmentation dataset and automated cardiac diagnosis challenge dataset demonstrate that the proposed model outperforms existing state-of-the-art methods, achieving the highest average Dice score of 86.05% and 92.58%, yielding improvements of 1.15% and 0.26%, respectively. In addition, the proposed model provides a balance between accuracy and computational complexity, with only 86.91 million parameters and 23.26 giga floating-point operations.