基于图卷积神经网络的胸部放射影像疾病分类方法北大核心CSCD

医学X射线作为胸部疾病的常规检查手段,可以对早期不明显的胸部疾病进行诊断,并且观察出病变部位。但是,同一张放射影像上呈现出多种疾病特征,对分类任务而言是一个挑战。此外,疾病标签之间存在着不同的对应关系,进一步导致了分类任务的困难。针对以上问题,本文将图卷积神经网络(graph convolutional neural network,GCN)与传统卷积神经网络(convolutional neural network,CNN)相结合,提出了一种将标签特征与图像特征融合的多标签胸部放射影像疾病分类方法。该方法利用图卷积神经网络对标签的全局相关性进行建模,即在疾病标签上构建有向关系图,有向图中每个节点表示一种标签类别,再将该图输入图卷积神经网络以提取标签特征,最后与图像特征融合以进行分类。本文所提出的方法在ChestX-ray14数据集上的实验结果显示对14种胸部疾病的平均AUC达到了0.843,与目前3种经典方法以及先进方法进行比较,本文方法能够有效提高分类性能。

Classification of chest radiographic image diseases based on graph convolutional neural network

Medical X-rays,as a routine examination method for chest diseases,can diagnose early and unobvious chest diseases and observe the lesions.However,the charact eristics of multiple diseases on the same radiographic image are a challenge to the classifi cation problem. In addition,there are different correspondences between disease labels,which f urther leads to the difficulty of classification tasks.In response to the above problems,this paper combines the graph convolutional neural network (GCN) with the traditional convolutional neural network (CNN),and proposes a multi-label chest radiographic image disease classification method that co mbines label features with image features.This method uses the graph convolutional neural ne twork to model the global correlation of the labels,that is,constructs a directed relat ionship graph on the disease label,each node in the directed graph represents a label category, and then inputs the graph into the graph convolutional neural network to extract the label featu res,and finally merges with the image features to sort.The experimental results of the method p roposed in this paper on the ChestX-ray14 dataset show that the average AUC of 14 chest disease s reaches 0.843.Compared with the current three classic methods and advanced methods,the method in this paper can effectively improve the classification performance.