信息与控制2025，Vol.54Issue(3)：390-400,11.DOI:10.13976/j.cnki.xk.2024.0643
基于融合Swin Transformer网络的腰椎解剖区域自动分割方法
A Fusion Swin Transformer Network for Automated Segmentation of Lumbar Spine Anatomical Regions
摘要
Abstract
Automated segmentation of the lumbar spine anatomical region plays a crucial role in the automated analysis pipeline of spinal images.Although classical convolutional neural networks can capture global image features,their inherent local priors and weight-sharing characteristics limit their ability to model long-range dependencies.To address these issues,a Swin Transformer hybrid network is proposed for the segmentation of the lumbar anatomical region.Firstly,the Swin Transformer hybrid network and multi-scale dilated convolution are combined as an encoder to a-chieve the hierarchical representation of global and local features.Additionally,a feature coupling module is designed,which couples the features of the Transformer and CNN in the channel and spatial dimensions,enhancing the model's local and long-distance modeling capabilities.Dealing with data scarcity problems,a dataset composed of 663 lumbar vertebrae CT images with voxel-lev-el labeled annotations is proposed.Experiments on this dataset show that the segmentation accura-cy of the proposed model surpasses that of typical medical image segmentation methods.Specifical-ly,the dice coefficient,the Hausdorff distance,and the average surface distance of the proposed model are 88.24％,14.48,and 0.997,respectively.Ablation experiments further verify the effec-tiveness of the proposed modules.关键词
卷积神经网络/医学图像分割/Transformer/多尺度特征提取Key words
CNN(convolutional neural network)/medical image segmentation/Transformer/multi-scale feature extraction分类
计算机与自动化引用本文复制引用
张英迪,史泽林,王欢,崔少千,张磊,刘嘉琛,单修祺,刘云鹏,赵恩波..基于融合Swin Transformer网络的腰椎解剖区域自动分割方法[J].信息与控制,2025,54(3):390-400,11.基金项目
辽宁省自然科学基金项目(2022-KF-12-09) （2022-KF-12-09）
