基于稀疏表达的胃部疾病检测  

Sparse representation for gastropathy disease diagnosis

作　　者：范慧杰[1,2] 丛杨[1] 杨云生[3] 唐延东[1] 

机构地区：[1]中国科学院沈阳自动化研究所,机器人学国家重点实验室,沈阳110016 [2]中国科学院大学,北京100049 [3]中国人民解放军总医院,北京100853

出　　处：《科学通报》2013年第S2期145-151,共7页Chinese Science Bulletin

基　　金：国家自然科学基金(61105013;61375014);国家科技支撑计划(2012BAI14B03)资助

摘　　要：提出了一种基于稀疏表达的自动胃病检测算法,通过训练少量样本就可以进行精确、稳定的病灶检测.根据实际工作中样本数量(特别是疾病样本)采集有限这一特点,建立了一个基于小样本的、具有稀疏和低秩特性的大尺度字典选择模型,实现了用最少的原子来构建超完备字典.在疾病检测阶段,设计了一种新的加权稀疏集中度指标(WSCI,weighted sparsity concentration index)判别输入样本是否有效,然后采用两级判别机制对有效的输入样本进行检测:首先将输入样本划分为健康或者疾病类别;然后将病灶看作健康图像中的异常现象,对判别为健康类别的图像进行再次检测,以防止漏报现象的出现.我们将本文算法与现有的胃病检测算法进行比较,对比结果表明本文算法在检测的精度和算法适用性方面都有较大提高.Automatic diagnosis of gastropathy disease plays an important role in supporting the clinician and speeding up the examination process. In this paper, we propose a general algorithm for stomach disease detection using sparse representation, which can get robust result even using a small size of high-dimensional training dataset. First, a noval large scale dictionary selection model based on the low rank property is designed to initialize the meaningful dictionary with minimal size. Then in comparison with the state-of-the-arts, we consider disease diagnosing as both supervised classification issue and one-class classification issue, where a new criterion, weighted sparsity concentration index(WSCI) is designed for outlier detection. Experiments on our dataset and comparisons with state-of-the-arts demonstrate the effectiveness and effciency of our algorithm.

关 键 词：胃病诊断 胶囊内窥镜 稀疏表达 字典选择 异常检测 

分 类 号：R573[医药卫生—消化系统]