电子学报 ›› 2021, Vol. 49 ›› Issue (4): 706-715.DOI: 10.12263/DZXB.20200101

• 学术论文 • 上一篇    下一篇

结合切片上下文信息的多阶段胰腺定位与分割

王瑞豪, 刘哲, 宋余庆   

  1. 江苏大学计算机科学与通信工程学院, 江苏镇江 212013
  • 收稿日期:2020-01-15 修回日期:2020-06-30 出版日期:2021-04-25 发布日期:2021-04-25
  • 通讯作者: 刘哲
  • 作者简介:王瑞豪 男,1995年4月出生,安徽阜阳人.现为江苏大学计算机科学与通信工程学院硕士研究生,主要研究方向为医学图像处理与分析.E-mail:2221808037@stmail.ujs.edu.cn
  • 基金资助:
    国家自然科学基金(No.61976106,No.61772242,No.61572239);国家博士后科研基金(No.2017M611737);江苏省六大人才高峰(No.DZXX-122);镇江市卫生计生科技重点(No.SHW2017019)

Multi-Stage Pancreas Localization and Segmentation Combined with Slices Context Information

WANG Rui-hao, LIU Zhe, SONG Yu-qing   

  1. School of Computer Science and Communication Engineering, Jiangsu University, Zhenjiang, Jiangsu 212013, China
  • Received:2020-01-15 Revised:2020-06-30 Online:2021-04-25 Published:2021-04-25

摘要: 当前基于深度学习的胰腺分割主要存在以下问题:(1)胰腺的解剖特异性导致深度网络模型容易受到复杂多变背景的干扰;(2)传统两阶段分割方法在粗分割阶段将整张CT图像作为输入,导致依赖粗分割结果得到的定位不够准确;(3)传统两阶段分割方法忽略了切片间的上下文信息,限制了定位和后续分割结果的提升.针对上述问题,本文提出了结合切片上下文信息的多阶段胰腺定位与分割方法.第一阶段利用解剖先验定位粗略缩小输入区域;第二阶段先使用所设计的DASU-Net进行粗略分割,接着利用切片上下文信息优化分割结果;第三阶段使用单张切片定位进一步减少不相关背景,并使用DASU-Net完成精细分割.实验结果表明,本文所提方法能够有效提高胰腺分割的准确率.

关键词: 胰腺分割, 多阶段分割, 切片上下文信息, 解剖先验定位, 单张切片定位

Abstract: Current deep learning-based pancreas segmentation mainly has the following problems:The anatomical specificity of the pancreas makes the deep network model easily disturbed by complex background;in the traditional two-stage segmentation method,the input of the coarse segmentation is the entire CT image,which leads to inaccurate localization based on the segmentation results;the traditional two-stage segmentation ignores the context information between adjacent slices,which limits the localization and subsequent segmentation results.In order to solve the problems above,a multi-stage pancreas localization and segmentation method combined with slices context information is proposed.In the first stage,anatomical prior locating is used to roughly shrink the input area;in the second stage,the proposed DASU-Net is used for coarse segmentation,and then the segmentation results are optimized with slices context information;last stage,single slice locating is used to further shrink irrelevant background,and then fine segmentation is completed by DASU-Net.The experimental results show that the proposed method can effectively improve the accuracy of pancreas segmentation.

Key words: pancreas segmentation, multi-stage segmentation, slices context information, anatomical prior locating, single slice locating

中图分类号: