基于词袋模型的医学图像分割  

Medical Image Segmentation Based on Bag of Word

作　　者：史延新[1] 薛鹏翔[1] 刘建伟[1] 时华[1] SHI Yanxin XUE Pengxiang LIU Jianwei SHI Hua(School of Science, Xi ＇an Technological University, Xi ＇ an 710021, China)

机构地区：[1]西安工业大学理学院,西安710021

出　　处：《西安工业大学学报》2017年第3期179-183,共5页Journal of Xi’an Technological University

基　　金：陕西省教育厅专项科研计划项目(14JK1345)

摘　　要：为了提高医学图像分割的准确性,从医学图像的特征出发,提出了一种利用词袋模型配合滑动窗口提取像素点特征的分割方法.通过引入词袋模型,建立分类的视觉词典,分别生成肝脏区域词典和背景区域词典,进而组合得到最终的联合视觉词典,利用滑动窗口等提取像素点的基于词典表达的特征,对词袋模型的图像分割方法进行了优化.通过对腹部CT图像的肝脏和肝癌病灶分割实验,结果表明算法分割结果接近于医生手工分割结果,分割精度较高且具有效性.DICE等系数进一步证实算法的有效性.To improve the accuracy of medical image segmentation, images, a segmentation algorithm using Bag-of-Visual-Words is dictionary is established by Bag-of-Visual-Words to produce liver area dictionary , which are combined into the union visual dictionary. The using the sliding window. The experiment shows that the results obtai almost as good as the manual segmentation results. DICE also based on the features of medical presented. The classified visual dictionary and background region pixel＇s features are acquired by ned by the proposed algorithm is proves its high accuracy and effectiveness.

关 键 词：医学图像 词袋模型 视觉词典 滑动窗口 

分 类 号：TP391.41[自动化与计算机技术—计算机应用技术]