• 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:

Dong, Daqiang (Dong, Daqiang.) | Fu, Guanghui (Fu, Guanghui.) | Li, Jianqiang (Li, Jianqiang.) (学者:李建强) | Pei, Yan (Pei, Yan.) | Chen, Yueda (Chen, Yueda.)

收录:

EI Scopus SCIE

摘要:

Computed tomography (CT) is the primary diagnostic tool for brain diseases. To determine the appropriate treatment plan, it is necessary to ascertain the patient's bleeding volume. Automatic segmentation algorithms for hemorrhagic lesions can significantly improve efficiency and avoid treatment delays. However, for deep supervised learning algorithms, a large amount of labeled training data is usually required, making them difficult to apply clinically. In this study, we propose an unsupervised domain adaptation method that is an unsupervised domain adaptation segmentation model that can be trained across modalities and diseases. We call it AMD-DAS for brain CT hemorrhage segmentation tasks. This circumvents the heavy data labeling task by converting the source domain data (MRI with glioma) to our task's required data (CT with Intraparenchymal hemorrhage (IPH)). Our model implements a two-stage domain adaptation process to achieve this objective. In the first stage, we train a pseudo-CT image synthesis network using the CycleGAN architecture through a matching mechanism and domain adaptation approach. In the second stage, we use the model trained in the first stage to synthesize the pseudo-CT images. We use the pseudo-CT with source domain labels and real CT images to train a domain-adaptation segmentation model. Our method exhibits a better performance than the basic one-stage domain adaptation segmentation method (+11.55 Dice score) and achieves an 86.93 Dice score in the IPH unsupervised segmentation task. Our model can be trained without using a ground-truth label, therefore increasing its application potential. Our implementation is publicly available at https://github.com/GuanghuiFU/AMD-DAS-Brain-CT-Segmentation.

关键词:

Imagesynthesis Domainadaptation Semanticsegmentation Intraparenchymalhemorrhage Deeplearning

作者机构:

  • [ 1 ] [Dong, Daqiang]Beijing Univ Technol, Beijing, Peoples R China
  • [ 2 ] [Fu, Guanghui]Beijing Univ Technol, Beijing, Peoples R China
  • [ 3 ] [Li, Jianqiang]Beijing Univ Technol, Beijing, Peoples R China
  • [ 4 ] [Fu, Guanghui]Sorbonne Univ, Hop Pitie Salpetriere, AP HP, Inst Cerveau,Paris Brain Inst ICM,CNRS,Inria,Inser, F-75013, Paris, Himachal Prades, India
  • [ 5 ] [Pei, Yan]Univ Aizu, Comp Sci Div, Aizu Wakamatsu, Fukushima, Japan
  • [ 6 ] [Chen, Yueda]Tianjin Huanhu Hosp, Tianjin, Peoples R China

通讯作者信息:

查看成果更多字段

相关关键词:

相关文章:

来源 :

EXPERT SYSTEMS WITH APPLICATIONS

ISSN: 0957-4174

年份: 2022

卷: 207

8 . 5

JCR@2022

8 . 5 0 0

JCR@2022

ESI学科: ENGINEERING;

ESI高被引阀值:49

JCR分区:1

中科院分区:1

被引次数:

WoS核心集被引频次: 14

SCOPUS被引频次: 22

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: 1

归属院系:

在线人数/总访问数:558/4943159
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