Medical image segmentation based on multi-scale convolution and parallel reverse attention
10.3969/j.issn.1005-202X.2025.01.005
- VernacularTitle:基于多尺度卷积与并行反向注意力的医学图像分割
- Author:
Mengfei CHEN
1
;
Raofen WANG
;
Hailing WANG
;
Peng LI
;
Xiaomei GONG
Author Information
1. 上海工程技术大学电子电气工程学院,上海201620
- Publication Type:Journal Article
- Keywords:
medical image segmentation;
multi-scale convolution;
multi-layer perceptron;
partial decoder;
reverse attention module
- From:
Chinese Journal of Medical Physics
2025;42(1):27-36
- CountryChina
- Language:Chinese
-
Abstract:
A medical image segmentation network (RPR-MLP) based on multi-scale convolution and parallel reverse attention is presented. In the encoder,Res2net modules and tokenized multi-layer perceptron modules are used as the backbone structure to extract multi-scale information and enhance the diversity of semantic features. Meanwhile,the accuracy of semantic information extraction in the decoder is improved through parallel partial decoder. Additionally,reverse attention module re-emphasizes the focus on important regions for further improving the accuracy of segmentation results. The proposed method achieves Dice scores of 0.8967 and 0.8762 on the Kvasir and ISIC 2018 public datasets,respectively,demonstrating its effectiveness and generalization ability in medical image segmentation. Furthermore,when applied to the lung tumor CT image dataset (LungCancer dataset) collected in the study,the proposed network has Dice score,IoU and F1 score of 0.7278,58.83％and 67.85％,respectively,outperforming baseline network (UNeXt) and common CNN (U-Net,AttU-Net,U-Net++and PraNet) by 0.0301-0.0578、3.16％-4.70％,and 6.72％-18.53％,respectively. The study confirms the effectiveness and generalization ability of RPR-MLP network on different datasets,providing important technical support for lung tumor image segmentation.
