基于像素编码和空间注意力的多尺度医学图像分割方法
Multi-scale medical image segmentation based on pixel encoding and spatial attention mechanism
万雨龙 1周冬明 1王长城 1刘宜松 1白崇斌2
作者信息
- 1. 云南大学信息学院(昆明 650504)
- 2. 云南省红河州第二人民医院(云南建水 654300)
- 折叠
摘要
针对医学图像分割中U型网络(U-Net)及其变体下采样过程中单尺度信息丢失、模型参数量较大的问题,本文提出了一种基于像素编码和空间注意力的多尺度医学图像分割方法.首先,通过重新设计变换器(Transformer)结构输入策略,提出了像素编码模块,使模型能够从多尺度图像特征中提取全局语义信息,获取更丰富的特征信息,同时在Transformer模块中引入可变形卷积,加快收敛速度的同时提升模块性能.其次,引入空间注意力模块并加入残差连接,使模型能够重点关注融合后特征图的前景信息.最后,通过消融实验实现网络轻量化并提升分割精度,加快模型收敛.本文所提算法在国际计算机医学图像辅助协会官方公开多器官分割公共数据集——突触(Synapse)数据库中得到令人满意的结果,戴斯相似性系数(DSC)和95％豪斯多夫距离系数(HD95)分别为77.65和18.34.实验结果表明,本文算法能够提高多器官分割结果,有望完善多尺度医学图像分割算法的空白,并为专业医师提供辅助诊断.
Abstract
In response to the issues of single-scale information loss and large model parameter size during the sampling process in U-Net and its variants for medical image segmentation,this paper proposes a multi-scale medical image segmentation method based on pixel encoding and spatial attention.Firstly,by redesigning the input strategy of the Transformer structure,a pixel encoding module is introduced to enable the model to extract global semantic information from multi-scale image features,obtaining richer feature information.Additionally,deformable convolutions are incorporated into the Transformer module to accelerate convergence speed and improve module performance.Secondly,a spatial attention module with residual connections is introduced to allow the model to focus on the foreground information of the fused feature maps.Finally,through ablation experiments,the network is lightweighted to enhance segmentation accuracy and accelerate model convergence.The proposed algorithm achieves satisfactory results on the Synapse dataset,an official public dataset for multi-organ segmentation provided by the International Conference on Medical Image Computing and Computer Assisted Intervention(MICCAI),with Dice similarity coefficient(DSC)and 95％Hausdorff distance(HD95)scores of 77.65 and 18.34,respectively.The experimental results demonstrate that the proposed algorithm can enhance multi-organ segmentation performance,potentially filling the gap in multi-scale medical image segmentation algorithms,and providing assistance for professional physicians in diagnosis.
关键词
医学图像分割/U型网络/变换器/多尺度语义信息/注意力模块Key words
Medical image segmentation/U-Net/Transformer/Multi-scale semantic information/Attention module引用本文复制引用
基金项目
国家自然科学基金项目(62066047)
国家自然科学基金项目(61966037)
出版年
2024
NETL
NSTL
万方数据