DFEN: Dual Feature Equalization Network for Medical Image Segmentation

TL;DR

The paper introduces DFEN, a novel medical image segmentation network that combines Swin Transformer and CNN to enhance pixel feature representations through image-level and class-level feature equalization, achieving state-of-the-art results.

Contribution

Proposes a dual feature equalization network integrating Swin Transformer and CNN for improved medical image segmentation.

Findings

Achieved state-of-the-art performance on multiple datasets.

Effectively enhances pixel features via image-level and class-level equalization.

Utilizes Swin Transformer for capturing long-range dependencies.

Abstract

Current methods for medical image segmentation primarily focus on extracting contextual feature information from the perspective of the whole image. While these methods have shown effective performance, none of them take into account the fact that pixels at the boundary and regions with a low number of class pixels capture more contextual feature information from other classes, leading to misclassification of pixels by unequal contextual feature information. In this paper, we propose a dual feature equalization network based on the hybrid architecture of Swin Transformer and Convolutional Neural Network, aiming to augment the pixel feature representations by image-level equalization feature information and class-level equalization feature information. Firstly, the image-level feature equalization module is designed to equalize the contextual information of pixels within the image. Secondly, we aggregate regions of the same class to equalize the pixel feature representations of the corresponding class by class-level feature equalization module. Finally, the pixel feature representations are enhanced by learning weights for image-level equalization feature information and class-level equalization feature information. In addition, Swin Transformer is utilized as both the encoder and decoder, thereby bolstering the ability of the model to capture long-range dependencies and spatial correlations. We conducted extensive experiments on Breast Ultrasound Images (BUSI), International Skin Imaging Collaboration (ISIC2017), Automated Cardiac Diagnosis Challenge (ACDC) and PH$^2$ datasets. The experimental results demonstrate that our method have achieved state-of-the-art performance. Our code is publicly available at https://github.com/JianJianYin/DFEN.