计算机工程与应用2019，Vol.55Issue(24)：171-177,7.DOI:10.3778/j.issn.1002-8331.1809-0190
融合多维度卷积神经网络的肺结节分类方法
Fusing Multi-Dimensional Convolution Neural Network for Lung Nodules Classification
摘要
Abstract
In order to solve the problem of low classification precision and high false positive in the classification task of lung nodules in CT image, a benign and malignant classification model of lung nodules based on weighted fusion multi-dimensional convolution neural network is proposed. The model contains two sub-models:a multi-scale dense convolu-tional network model based on two-dimensional images to capture more extensive nodule variation features and promote feature reuse, and the three-dimensional convolutional neural network model based on three-dimensional images to make full use of spatial context information of nodules. 2D and 3D CT images are used to train the sub-models. The weights of the sub-models are calculated according to the classification errors, and then the weights are used to fuse the sub-models classification results. The more accurate classification results are obtained. The classification accuracy of the model is 94.25% and the AUC value is 98% on the public dataset LIDC-IDRI. The experimental results show that the weighted fusion multi-dimensional model can effectively improve the classification performance of lung nodules.关键词
肺结节分类/卷积神经网络/深度学习/多维度/加权融合/CT图像Key words
lung nodule classification/convolutional neural network/deep learning/multi-dimensional/weighted fusion/CT image分类
信息技术与安全科学引用本文复制引用
吴保荣,强彦,王三虎,唐笑先,刘希靖..融合多维度卷积神经网络的肺结节分类方法[J].计算机工程与应用,2019,55(24):171-177,7.基金项目
国家自然科学基金(No.61572344) （No.61572344）
虚拟现实技术与系统国家重点实验室开放基金(No.BUAA-VR-17KF-14) （No.BUAA-VR-17KF-14）
虚拟现实技术与系统国家重点实验室开放基金(No.VRLAB2018B07) （No.VRLAB2018B07）
山西省回国留学人员科研资助项目(No.2016-038). （No.2016-038）
