标题:A serialized classification method for pulmonary nodules based on lightweight cascaded convolutional neural network-long short-term memory
作者:Ni Z.; Peng Y.
作者机构:[Ni, Z] College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, China;[ Peng, Y] College of Computer Scie 更多
通讯作者:Peng, Y(pengyanjuncn@163.com)
通讯作者地址:[Peng, Y] College of Computer Science and Engineering, Shandong University of Science and TechnologyChina;
来源:International Journal of Imaging Systems and Technology
出版年:2020
DOI:10.1002/ima.22443
关键词:convolutional neural networks; false positive reduction; long short-term memory; lung cancer; pulmonary nodule classification
摘要:Computer Assisted Diagnosis (CAD) is an effective method to detect lung cancer from computed tomography (CT) scans. The development of artificial neural network makes CAD more accurate in detecting pathological changes. Due to the complexity of the lung environment, the existing neural network training still requires large datasets, excessive time, and memory space. To meet the challenge, we analysis 3D volumes as serialized 2D slices and present a new neural network structure lightweight convolutional neural network (CNN)-long short-term memory (LSTM) for lung nodule classification. Our network contains two main components: (a) optimized lightweight CNN layers with tiny parameter space for extracting visual features of serialized 2D images, and (b) LSTM network for learning relevant information among 2D images. In all experiments, we compared the training results of several models and our model achieved an accuracy of 91.78% for lung nodule classification with an AUC of 93%. We used fewer samples and memory space to train the model, and we achieved faster convergence. Finally, we analyzed and discussed the feasibility of migrating this framework to mobile devices. The framework can also be applied to cope with the small amount of training data and the development of mobile health device in future. © 2020 Wiley Periodicals LLC
收录类别:SCOPUS
资源类型:期刊论文
原文链接:https://www.scopus.com/inward/record.uri?eid=2-s2.0-85086018794&doi=10.1002%2fima.22443&partnerID=40&md5=cdbc01a8076167188654d3987d9723bb
TOP