Human-recognizable CT image features of subsolid lung nodules associated with diagnosis and classification by convolutional neural networks
Human-recognizable CT image features of subsolid lung nodules associated with diagnosis and classification by convolutional neural networks
复制标题
DOI：
10.1007/s00330-021-07901-1
复制
发表时间：
2021-04-13
影响因子：
5.9
通讯作者：
Xie, Xueqian
中科院分区：
文献类型：
--
作者：
Jiang, Beibei;Zhang, Yaping;Xie, Xueqian
目的卷积神经网络（cnn）对亚实性结节（ssn）分类的可解释性对临床医生来说是不够的。我们的目的是开发CNN模型来对CT图像上的ssn进行分类，并研究与CNN分类相关的图像特征。方法CT图像包含直径为
Objectives The interpretability of convolutional neural networks (CNNs) for classifying subsolid nodules (SSNs) is insufficient for clinicians. Our purpose was to develop CNN models to classify SSNs on CT images and to investigate image features associated with the CNN classification. Methods CT images containing SSNs with a diameter of