作者投稿和查稿 主编审稿 专家审稿 编委审稿 远程编辑

计算机工程 ›› 2019, Vol. 45 ›› Issue (7): 273-281. doi: 10.19678/j.issn.1000-3428.0052534

• 图形图像处理 • 上一篇    下一篇

基于mDixon序列下腹部MRI数据的sCT生成方法

陈扬洋1, 钱鹏江1, 赵开发1, 苏冠豪2   

  1. 1. 江南大学 数字媒体学院, 江苏 无锡 214122;
    2. 凯斯西储大学 凯斯西储大学附属医院放射科和影像研究中心, 美国 克利夫兰 44106
  • 收稿日期:2018-09-03 修回日期:2018-10-08 出版日期:2019-07-15 发布日期:2019-07-23
  • 作者简介:陈扬洋(1994-),男,硕士研究生,主研方向为医学图像处理、模式识别;钱鹏江,教授、博士;赵开发,硕士研究生;苏冠豪,博士。
  • 基金资助:
    国家自然科学基金(61772241,61702225);中央高校基本科研业务费专项资金(JUSRP51614A)。

sCT Generation Method for Abdominal MRI Data Based on mDixon Sequence

CHEN Yangyang1, QIAN Pengjiang1, ZHAO Kaifa1, SU Kuanhao2   

  1. 1. School of Digital Media, Jiangnan University, Wuxi, Jiangsu 214122, China;
    2. Department of Radiology and Case Center for Imaging Research, University Hospitals, Case Western Reserve University, Cleveland 44106, USA
  • Received:2018-09-03 Revised:2018-10-08 Online:2019-07-15 Published:2019-07-23

摘要: 为通过磁共振成像(MRI)数据生成合成计算机断层扫描(sCT),根据mDixon序列的下腹部MRI数据,提出迁移模糊聚类(TFCM)与支持向量机相结合的方法。借助病人MRI源数据提供的高级历史知识,利用TFCM对下腹部MRI数据进行处理,采用有监督学习方法对聚类结果投票,完成图像组织分割,并对分割的组织区域赋予相应的CT值来生成sCT。实验结果证明,该方法可以将下腹部MRI数据分割成脂肪、空气、骨头和软组织4类,并准确生成sCT,其预测值绝对误差最小仅为81 HU,相较于FCM方法,分类结果更优。

关键词: 磁共振成像, 合成计算机断层扫描, 下腹部, mDixon序列, 迁移模糊聚类, 有监督学习

Abstract: In order to generate Synthetic Computed Tomography (sCT) from Magnetic Resonance Imaging (MRI) data,this paper proposes the TFCM-SVM method for the abdominal MRI data based on mDixon seguence.With the advanced historical knowledge provided by the MRI source data of patients,this method uses Transfer Fuzzy Clustering Means (TFCM) to process abdominal MRI data.The supervised learning method is used to perform the final segmentation with voting strategies on the clustering result.Finally,the corresponding CT values are assigned to the segmented tissues to generate sCT.Experimental results show that the method can reliably partition abdominal MRI data into the four groups regarding fat,bone,air,and soft tissue,and robustly generate sCT.The Mean Absolute Prediction Deviation(MAPD) of the prediction value is only 81 HU,which is significantly improved compared with the FCM method.

Key words: Magnetic Resonance Imaging(MRI), Synthetic Computed Tomography(sCT), abdomen, mDixon sequence, Transfer Fuzzy Clustering Means(TFCM), supervised learning

中图分类号: