点击次数：

论文类型：期刊论文

发表时间：2014-04-01

发表刊物：IEEE TRANSACTIONS ON BIOMEDICAL ENGINEERING

收录刊物：SCIE、EI

卷号：61

期号：4

页面范围：1155-1166

ISSN号：0018-9294

关键字：Classification; feature design; latent semantic analysis; patch division

摘要：In this paper, we propose a novel classification method for the four types of lung nodules, i.e., well-circumscribed, vascularized, juxta-pleural, and pleural-tail, in low dose computed tomography scans. The proposed method is based on contextual analysis by combining the lung nodule and surrounding anatomical structures, and has three main stages: an adaptive patch-based division is used to construct concentric multilevel partition; then, a new feature set is designed to incorporate intensity, texture, and gradient information for image patch feature description, and then a contextual latent semantic analysis-based classifier is designed to calculate the probabilistic estimations for the relevant images. Our proposed method was evaluated on a publicly available dataset and clearly demonstrated promising classification performance.