• 综合
  • 标题
  • 关键词
  • 摘要
  • 学者
  • 期刊-刊名
  • 期刊-ISSN
  • 会议名称
搜索

作者:

Bai, Yunkun (Bai, Yunkun.) | Sun, Guangmin (Sun, Guangmin.) (学者:孙光民) | Li, Yu (Li, Yu.) | Shen, Le (Shen, Le.) | Zhang, Li (Zhang, Li.)

收录:

CPCI-S EI

摘要:

Deep learning-based segmentation algorithms for medical image require massive training datasets with accurate annotations, which is costly since it takes much human effort to manually labeling from scratch. Therefore, interactive image segmentation is important and may greatly improve the efficiency and accuracy of medical image labeling. Some interactive segmentation methods (e.g. Deep Extreme Cut and Deepgrow) may improve the labeling through minimal interactive input. However these methods only utilize the initial manually input information, while existing segmentation results (such as annotations produced by nonprofessionals or conventional segmentation algorithms) cannot be utilized. In this paper, an interactive segmentation method is proposed to make use of both existing segmentation results and human interactive information to optimize the segmentation results progressively. In this framework, the user only needs to click on the foreground or background of the target individual on the medical image, the algorithm could adaptively learn the correlation between them, and automatically completes the segmentation of the target. The main contributions of this paper are: (1) We adjusted and applied a convolutional neural network which takes medical image data and user's clicks information as input to achieve more accurate segmentation of medical images. (2) We designed an iterative training strategy to realize the applicability of the model to deal with different number of clicks data input. (3) We designed an algorithm based on false positive and false negative regions to simulate the user's clicks, so as to provide enough training data. By applying the proposed method, users can easily extract the region of interest or modify the segmentation results by multiple clicks. The experimental results of 6 medical image segmentation tasks show that the proposed method achieves more accurate segmentation results by at most five clicks. © 2021 SPIE.

关键词:

Convolution Convolutional neural networks Deep learning Image annotation Image enhancement Image segmentation Iterative methods Medical image processing

作者机构:

  • [ 1 ] [Bai, Yunkun]Faculty of Information Technology, Beijing University of Technology, No. 100 PingLeYuan, Chaoyang District, Beijing; 100124, China
  • [ 2 ] [Sun, Guangmin]Faculty of Information Technology, Beijing University of Technology, No. 100 PingLeYuan, Chaoyang District, Beijing; 100124, China
  • [ 3 ] [Li, Yu]Faculty of Information Technology, Beijing University of Technology, No. 100 PingLeYuan, Chaoyang District, Beijing; 100124, China
  • [ 4 ] [Shen, Le]Key Laboratory of Particle and Radiation Imaging, Tsinghua University, Ministry of Education, China
  • [ 5 ] [Shen, Le]Department of Engineering Physics, Tsinghua University, Beijing; 100084, China
  • [ 6 ] [Zhang, Li]Key Laboratory of Particle and Radiation Imaging, Tsinghua University, Ministry of Education, China
  • [ 7 ] [Zhang, Li]Department of Engineering Physics, Tsinghua University, Beijing; 100084, China

通讯作者信息:

  • [shen, le]department of engineering physics, tsinghua university, beijing; 100084, china;;[shen, le]key laboratory of particle and radiation imaging, tsinghua university, ministry of education, china

电子邮件地址:

查看成果更多字段

相关关键词:

相关文章:

来源 :

ISSN: 1605-7422

年份: 2021

卷: 11596

语种: 英文

被引次数:

WoS核心集被引频次: 0

SCOPUS被引频次: 1

ESI高被引论文在榜: 0 展开所有

万方被引频次:

中文被引频次:

近30日浏览量: 2

归属院系:

在线人数/总访问数:644/3574768
地址:北京工业大学图书馆(北京市朝阳区平乐园100号 邮编:100124) 联系我们:010-67392185
版权所有:北京工业大学图书馆 站点建设与维护:北京爱琴海乐之技术有限公司