COVIDSeg:新冠肺炎肺部CT图像轻量化分割模型

COVIDSeg:the lightweight segmentation model for the lung CT images of COVID-19 patients

新型冠状病毒肺炎(COVID-19)严重威胁人类健康,计算机自动分割患者肺部CT(computed tomography)图像是辅助医生进行快速准确诊断的重要手段。为此,提出针对新冠肺炎肺部CT图像分割的轻量化模型COVIDSeg。模型采用编码器-解码器结构,提出压缩-扩展通道注意力模块(squeeze and extend channel attention block,SECA)和残差多尺度注意力模块(residual multi-scale channel attention block,RMSCA)构成编码子网络主要组成模块,提出双通路结构连接编码子网络的各模块,通路内特征逐层传递,通路之间多级特征信息交互,促进不同层级有效信息的传递和表达;采用特征聚合模块作为解码子网络的主要组成模块,通过多尺度特征解码实现多路径解码器。在4个公开使用的COVID-19 CT图像数据集的实验测试表明,提出的轻量化新冠肺炎CT图像分割模型COVIDSeg在多项指标上优于当前主流的医学图像分割模型。通过消融实验分析主要模块对模型性能的影响,验证了提出的缩减-扩展通道注意力模块SECA和残差多尺度注意力模块RMSCA的有效性。分割结果可视化显示,模型对新冠肺炎肺部CT图像的分割结果与图像的真实Mask标记基本相同。

COVID-19 has severely been threatening human being.The computer aided automatic segmentation of lung CT(computed tomography)images is an important way to help medicine doctors to make fast and accurate diagnostic decisions.Therefore,a lightweight model referred to as COVIDSeg is proposed in this paper for segmenting the lung CT images of COVID-19 patients.This model adopts encoder-decoder structure.The squeeze and extend channel attention block(SECA)and the residual multi-scale channel attention block(RMSCA)are proposed to compose the main components of the encoder subnetwork.The dual-path structure is proposed to connect each module of the encoder network.The features are transferred layer by layer along the path,and features from different layers interact between pathways,so that the feature information can be transferred and expressed between different layers.The feature aggregation module is used as the main component of the decoder network,so as to realize the multipath decoder via multiscale feature decoding.This COVIDSeg model is tested on four public COVID-19 CT image datasets.The experimental results show that the proposed lightweight model COVIDSeg for segmenting the COVID-19 CT images outperforms the current main medical image segmentation models in terms of several popular metrics,and it is so far the best model for segmenting the lung CT images of COVID-19 patients.Furthermore,the ablation experiment was carried out to test the influence over the COVIDSeg model performance from its main modules.The experimental results show that the proposed SECA module and RMSCA module are effective to advance the performance of the COVIDSeg model.The segmentation results are visualized for this COVIDSeg model for the lung CT images of COVID-19 patients,and it is found that the segmentation results are basically identical to the real Mask of the images.