Automatic Detection of Pulmonary Nodules in Multi-slice CT Based on 3D Neural Networks With adaptive Initial Weights
Detection of pulmonary nodules combined of extraction by multi-directions PCA and identification by 3D (three dimension) BP neural network is presented in the paper, which is different from most lung CAD algorithms, that it does not require any a priori information by human intervention but solely the information contained by the CT image itself, and it is capable to perform full automation which support the radiologists in their final decision. The technique is tested against 60 cases of different pulmonary nodules which are screened out by cancer experts. Results confirm the validity of technique as well as enhanced performance.
component 3D neural network multi-directions PCA CT images
Qing-zhu Wang Ke Wang Yang Guo Xin-zhu Wang
School of Communication Engineering, Jilin University, Changchnn, China Aviation information countermeasure department, Aviation University of air force line, Changchun, Ch
国际会议
长沙
英文
833-836
2010-05-11（万方平台首次上网日期，不代表论文的发表时间）