基于孪生ConvNeXt网络的超声内镜胰腺病变诊断方法

Ultrasonographic Endoscopic Diagnosis of Pancreatic Lesions Based on Twinned ConvNeXt Networks

在超声波内镜胰腺病变智能诊断中,针对不同年龄段、不同性别以及胰腺多部位病变检测存在误检、漏检和准确率低等问题,提出一种基于孪生网络架构的诊断模型。该模型由两个改进的ConvNeXt模型组成,并分别执行胰腺部位分类任务以及配合Grad_CAM实现无需癌变部位的标注也可定位癌变区域的任务。其中改进的ConNeXt模型采用特征融合方法结合细节纹理和抽象语义信息,并通过实验探索求解出特征向量的融合比例关系,来提高该模型分类精度和稳定性。实验表明,经过特征融合改进后的孪生ConvNeXt网络模型,在对胰腺部位的分类精度达到98.34%,对癌变部位的分类精度可达99.47%,且Grad_CAM生成的激活区域与真实癌变区域高度一致,为医生提供有效的辅助诊断。

In the intelligent diagnosis of pancreatic lesions by ultrasonic endoscopy,a diagnostic model based on the twin network architecture was proposed to address the problems of misdetection,omission and low accuracy in the detection of pancreatic lesions in different age groups and genders,as well as the detection of pancreatic lesions in multiple sites.The model consists of two improved ConvNeXt models,which perform the task of pancreatic site classification and the task of locating cancerous areas without labelling the cancerous sites with Grad_CAM,respectively.The improved ConNeXt model uses feature fusion to combine detailed texture and abstract semantic information,and the fusion ratio relationship of feature vectors is solved through experimental exploration to improve the classification accuracy and stability of the model.Experiments show that the twin ConvNeXt network model improved by feature fusion achieves a classification accuracy of 98.34% for pancreatic sites and up to 99.47% for cancerous sites,and the activation regions generated by Grad_CAM are highly consistent with the real cancerous regions,which provides an effective auxiliary diagnosis for doctors.