首页 | 本学科首页   官方微博 | 高级检索  
     检索      

基于群体先验影像的低剂量CT影像复原
引用本文:程 璐,张元科,宋 芸,李 晨,郭道顺.基于群体先验影像的低剂量CT影像复原[J].教育技术导刊,2019,18(11):144-148.
作者姓名:程 璐  张元科  宋 芸  李 晨  郭道顺
作者单位:1. 曲阜师范大学 信息科学与工程学院,山东 日照 276800,2. 空军军医大学,陕西 西安 710032
基金项目:国家自然科学基金项目(61871383,61572283);国家重点研发计划项目(2017YFC0107400,2017YFC0107403)
摘    要:为充分利用临床已有群体患者常规剂量影像学特征,提出一种新的基于群体先验影像冗余信息的低剂量CT(LDCT)影像复原模式。该模式利用灰度共生矩阵提取群体影像中纹理特征以组建样本数据库,结合先验样本在线搜索及目标影像感兴趣区先验冗余信息挖掘,并通过目标区自适应规整处理,实现LDCT影像有效复原,充分利用了临床已有群体患者常规剂量影像(群体影像)中高质量影像学特征。对临床肺癌的仿真低剂量数据进行实验,结果表明该模式在噪声抑制和纹理特征保存方面均优于传统算法。

关 键 词:低剂量CT  CT影像复原  群体影像  先验知识  灰度共生矩阵  
收稿时间:2019-02-25

Low-dose CT Image Restoration Based on Priori Images from Population Patients
CHENG Lu,ZHANG Yuan-ke,SONG Yun,LI Chen,GUO Dao-shun.Low-dose CT Image Restoration Based on Priori Images from Population Patients[J].Introduction of Educational Technology,2019,18(11):144-148.
Authors:CHENG Lu  ZHANG Yuan-ke  SONG Yun  LI Chen  GUO Dao-shun
Institution:1. School of Information Science and Engineering, Qufu Normal University,Rizhao 276800, China|2. School of Biomedical Engineering, Air Force Medical University,Xi'an 710032, China
Abstract:Abstract:This paper proposes a novel low-dose CT restoration scheme based on priori redundancy information from population example images. The innovation of the scheme lies in construction of population example images database, where the texture features of the samples are extracted by the gray level co-occurrence matrix technique, and the online search of prior sample, combined with the priori redundancy information extraction and the target regions of interest regularization. The effectiveness of the proposed algorithm is validated by clinical lung cancer studies, and the gain over traditional methods is noticeable in terms of both noise suppression and textures preservation.
Keywords:low-dose CT  CT image restoration  population images  priori redundancy information  gray level co-occurrence matrix  
点击此处可从《教育技术导刊》浏览原始摘要信息
点击此处可从《教育技术导刊》下载免费的PDF全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号