Multi-view Convolutional Neural Network for lung nodule false positive reduction

作者：

Highlights：

• The Computer Aided Detection System detects nodules attached to vessels/lung wall.

• Specially designed Multi-view Convolutional Neural Network perfectly suits the inputs.

• Exploits 3D features of the nodules in multiple 2D views without 3D complexity.

• System is automated, produces consistent outputs with high sensitivity and accuracy.

摘要

•The Computer Aided Detection System detects nodules attached to vessels/lung wall.•Specially designed Multi-view Convolutional Neural Network perfectly suits the inputs.•Exploits 3D features of the nodules in multiple 2D views without 3D complexity.•System is automated, produces consistent outputs with high sensitivity and accuracy.

论文关键词：Lung nodules,Computer Aided Detection,Convolutional Neural Networks,Computed tomography

论文评审过程：Received 19 April 2019, Revised 24 September 2019, Accepted 10 October 2019, Available online 11 October 2019, Version of Record 10 October 2020.

论文官网地址：https://doi.org/10.1016/j.eswa.2019.113017