计算机科学与探索2025，Vol.19Issue(4)：976-988,13.DOI:10.3778/j.issn.1673-9418.2406001
位置信息增强的TransUnet医学图像分割方法
Positional Enhancement TransUnet for Medical Image Segmentation
摘要
Abstract
Medical image segmentation can assist doctors to quickly and accurately identify organs and lesions in medical images,which is of great value in improving the efficiency of clinical diagnosis.U-Net combined with Transformer is the mainstream method in the field of medical image segmentation.However,Transformer has weak ability to extract local in-formation,and the U-Net structure will lose detailed location information during upsampling and downsampling.To ad-dress the above problems,this paper proposes a TransUnet medical image segmentation network with enhanced position information,PETransUnet.The network first uses the positional efficient attention block(PEA)to enhance the position in-formation of features.Secondly,the dual attention bridge block(DAB)is used to make up for the semantic gap between the features in the encoding stage and the decoding stage.Finally,the cross-channel attention fusion block(CCAF)is used to reduce the position information lost during upsampling.The proposed method is validated on the publicly available Synapse dataset,achieving Dice coefficient of 82.92%and HD95 coefficient of 18.87%.On the ACDC dataset,a Dice co-efficient of 90.73%is attained.On the LITS17 dataset,the Dice coefficients for liver and liver tumor segmentation are 94.85%and 74.47%,respectively.Comparative analysis with recent algorithms shows higher segmentation accuracy.关键词
医学图像分割/Transformer/特征融合/位置编码Key words
medical image segmentation/Transformer/feature fusion/position encoding分类
信息技术与安全科学引用本文复制引用
赵亮,刘晨,王春艳..位置信息增强的TransUnet医学图像分割方法[J].计算机科学与探索,2025,19(4):976-988,13.基金项目
辽宁省教育厅青年基金项目(LJKQZ2021154).This work was supported by the Youth Fund of Liaoning Provincial Department of Education(LJKQZ2021154). （LJKQZ2021154）
