基于CT图像语义的COVID-19实例分割与分类网络

COVID-19 Instance Segmentation and Classification Network Based on CT Image Semantics

为了辅助临床医生进行COVID-19患者的诊断及治疗,提出了一个从患者肺部CT图像中分类、检测和分割COVID-19病变的辅助诊断网络AIS-Net。首先,该网络将语义分割与实例分割融合,提升了实例分割精度,提出了信息增强注意力模块(IEAM),用于提升输入特征关键信息的权重。为了提高网络对假阴性的关注度,提出了一个实例分割监督方法,用于不同尺度的病变进行监控。其次,设计了一个包含主分类头与辅助分类头的模块,对新冠肺炎、普通肺炎和非肺炎进行分类。在辅助分类中引入了Swin Transformer,提出了区分普通肺炎与新冠肺炎病变的方法。在CC-CCII分割数据集上实例分割的平均精度均值(mAP)为56.53%,比目前最好的方法提升了11.77%;Dice系数、灵敏度、特异度分别为80%,85.1%,99.3%,比目前最好的方法分别提升了4.7%,3.7%,1.2%。在COVIDX-CT分类数据集上实现了99.07%的总体准确度,比目前最好的方法提升了0.92%。AIS-Net可通过CT图像对COVID-19患者进行有效诊断,并对病变部位进行分割及检测。

To assist clinicians in the diagnosis and treatment of COVID-19 patients,a computer-aided diagnosis network AIS-Net is proposed to classify,detect and segment COVID-19 lesions in CT images.First,the network integrates semantic and instance segmentation to improve the accuracy.Then,the two modules are designed,the information enhanced attention module(IEAM)for weighing input features and the instance segmentation monitoring module focusing on the lesions at different scales.Furthermore,the classification module with the main header and the auxiliary header discerns COVID-19 pneumonia,common pneumonia,and non-pneumonia.Finally,the Swin Transformer is introduced into the auxiliary classification to distinguish the lesions of common pneumonia and COVID-19.On the CC-CCII dataset,the mean average precision(mAP)of instance segmentation is 56.53%,which is 11.77%higher than the state-of-the art(SOTA).Dice coefficient,sensitivity and specificity is 80%,85.1%and 99.3%respectively,which is 4.7%,3.7%and 1.2%higher than the SOTA.The overall classification accuracy is 99.07%on the COVIDX-CT dataset,0.92%higher than the SOTA.AIS-Net can effectively diagnose COVID-19 patients through CT images,and segment and detect the lesion sites.