English

应用科学学报 ›› 2017, Vol. 35 ›› Issue (1): 99-106.doi: 10.3969/j.issn.0255-8297.2017.01.011

• 信号与信息处理 • 上一篇    下一篇

利用群体CT计划图像的多任务前列腺自动分割

戴修斌1, 邓黄健2, 刘代富1, 刘可1, 周青蓉1   

  1. 1. 南京邮电大学 地理与生物信息学院, 南京 210023;
    2. 南京邮电大学 通信与信息工程学院, 南京 210003
  • 收稿日期:2016-08-07 修回日期:2016-10-08 出版日期:2017-01-30 发布日期:2017-01-30
  • 作者简介:戴修斌,博士,副研究员,研究方向:医学图像处理、机器学习,E-mail:daixb@njupt.edu.cn
  • 基金资助:

    国家自然科学基金（No.31671006）资助

Multi-task Automatic Prostate Segmentation with Group CT Planning Images

DAI Xiu-bin1, Deng Huang-jian2, LIU Dai-fu1, LIU Ke1, ZHOU Qing-rong1   

  1. 1. College of Geographic and Biologic Information, Nanjing University of Posts and Telecommunications, Nanjing 210023, China;
    2. College of Communication and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China
  • Received:2016-08-07 Revised:2016-10-08 Online:2017-01-30 Published:2017-01-30

PDF

277

摘要：

为了实现CT计划图像中前列腺的自动分割，提出一种基于群体CT计划图像的多任务前列腺分割方法.将群体CT计划图像分别映射到不同参考图像空间，形成多个训练任务.利用随机森林算法和自动上下文模型训练出一系列随机森林分类器，将分类器作用在待分割CT计划图像上获得多个分类概率图，最后使用多数投票法求得最终分割结果.实验表明，与单任务分割方法相比，基于群体CT图像的多任务分割能有效提高CT计划图像中前列腺的分割准确率.

关键词: CT计划图像, 群体图像, 放射治疗, 前列腺分割, 多训练任务

Abstract:

To automatically and accurately segment prostates in CT planning images, a multi-task CT prostate segmentation method is proposed based on group images.The group images with those from other patients are frst mapped to various spaces of reference images to form a multiple training task.The random forest method and the automatic context model are used to train a series of classifers.The trained classifers are then iteratively applied to CT images to be segmented.Multiple classifcation probability maps are thus produced.The fnal segmentation result is obtained using a majority voting method.Experimental results show that, compared with single-task segmentation, proposed multi-task segmentation based on group images can effectively improve accuracy of prostate segmentation for CT planning images.

Key words: group images, CT planning images, multiple training task, radiation treatment, prostate segmentation

中图分类号: